diff --git a/CHANGELOG.md b/CHANGELOG.md index ce4cfde9..c3693393 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,7 @@ ## Changelog +### CUDA 12.5 + ### CUDA 12.4 * Added graphConditionalNodes Sample diff --git a/Common/helper_multiprocess.cpp b/Common/helper_multiprocess.cpp index 937830e3..61fe0855 100644 --- a/Common/helper_multiprocess.cpp +++ b/Common/helper_multiprocess.cpp @@ -168,7 +168,7 @@ int waitProcess(Process *process) { #endif } -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) int ipcCreateSocket(ipcHandle *&handle, const char *name, const std::vector &processes) { int server_fd; @@ -262,41 +262,48 @@ int ipcRecvShareableHandle(ipcHandle *handle, ShareableHandle *shHandle) { // Union to guarantee alignment requirements for control array union { struct cmsghdr cm; - char control[CMSG_SPACE(sizeof(int))]; + // This will not work on QNX as QNX CMSG_SPACE calls __cmsg_alignbytes + // And __cmsg_alignbytes is a runtime function instead of compile-time macros + // char control[CMSG_SPACE(sizeof(int))] + char* control; } control_un; + size_t sizeof_control = CMSG_SPACE(sizeof(int)) * sizeof(char); + control_un.control = (char*) malloc(sizeof_control); struct cmsghdr *cmptr; ssize_t n; int receivedfd; char dummy_buffer[1]; ssize_t sendResult; - msg.msg_control = control_un.control; - msg.msg_controllen = sizeof(control_un.control); + msg.msg_controllen = sizeof_control; iov[0].iov_base = (void *)dummy_buffer; iov[0].iov_len = sizeof(dummy_buffer); msg.msg_iov = iov; msg.msg_iovlen = 1; - if ((n = recvmsg(handle->socket, &msg, 0)) <= 0) { perror("IPC failure: Receiving data over socket failed"); + free(control_un.control); return -1; } if (((cmptr = CMSG_FIRSTHDR(&msg)) != NULL) && (cmptr->cmsg_len == CMSG_LEN(sizeof(int)))) { if ((cmptr->cmsg_level != SOL_SOCKET) || (cmptr->cmsg_type != SCM_RIGHTS)) { + free(control_un.control); return -1; } memmove(&receivedfd, CMSG_DATA(cmptr), sizeof(receivedfd)); *(int *)shHandle = receivedfd; } else { + free(control_un.control); return -1; } + free(control_un.control); return 0; } @@ -340,9 +347,12 @@ int ipcSendShareableHandle(ipcHandle *handle, union { struct cmsghdr cm; - char control[CMSG_SPACE(sizeof(int))]; + char* control; } control_un; + size_t sizeof_control = CMSG_SPACE(sizeof(int)) * sizeof(char); + control_un.control = (char*) malloc(sizeof_control); + struct cmsghdr *cmptr; ssize_t readResult; struct sockaddr_un cliaddr; @@ -360,7 +370,7 @@ int ipcSendShareableHandle(ipcHandle *handle, int sendfd = (int)shareableHandles[data]; msg.msg_control = control_un.control; - msg.msg_controllen = sizeof(control_un.control); + msg.msg_controllen = sizeof_control; cmptr = CMSG_FIRSTHDR(&msg); cmptr->cmsg_len = CMSG_LEN(sizeof(int)); @@ -380,9 +390,11 @@ int ipcSendShareableHandle(ipcHandle *handle, ssize_t sendResult = sendmsg(handle->socket, &msg, 0); if (sendResult <= 0) { perror("IPC failure: Sending data over socket failed"); + free(control_un.control); return -1; } + free(control_un.control); return 0; } diff --git a/Common/helper_multiprocess.h b/Common/helper_multiprocess.h index 9ea927d4..5c760718 100644 --- a/Common/helper_multiprocess.h +++ b/Common/helper_multiprocess.h @@ -84,7 +84,7 @@ int waitProcess(Process *process); #define checkIpcErrors(ipcFuncResult) \ if (ipcFuncResult == -1) { fprintf(stderr, "Failure at %u %s\n", __LINE__, __FILE__); exit(EXIT_FAILURE); } -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) struct ipcHandle_st { int socket; char *socketName; diff --git a/README.md b/README.md index 692f6bcc..daecee33 100644 --- a/README.md +++ b/README.md @@ -1,27 +1,12 @@ # CUDA Samples -Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads). +Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads). ## Release Notes This section describes the release notes for the CUDA Samples on GitHub only. -### CUDA 12.4 - -- Hopper Confidential Computing Modes do not support Video samples, nor do they support host-pinned memory due to the restrictions created by CPU IOMMUs. The following Samples are affected: - - convolutionTexture - - cudaNvSci - - dct8x8 - - lineOfSight - - simpleCubemapTexture - - simpleIPC - - simpleLayeredTexture - - simplePitchLinearTexture - - simpleStream - - simpleTexture - - simpleTextureDrv - - watershedSegmentationNPP - +### CUDA 12.5 ### [older versions...](./CHANGELOG.md) @@ -29,7 +14,7 @@ This section describes the release notes for the CUDA Samples on GitHub only. ### Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. For system requirements and installation instructions of cuda toolkit, please refer to the [Linux Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-linux/), and the [Windows Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html). ### Getting the CUDA Samples diff --git a/Samples/0_Introduction/UnifiedMemoryStreams/Makefile b/Samples/0_Introduction/UnifiedMemoryStreams/Makefile index c1ea802a..ff5ace7f 100644 --- a/Samples/0_Introduction/UnifiedMemoryStreams/Makefile +++ b/Samples/0_Introduction/UnifiedMemoryStreams/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/UnifiedMemoryStreams/README.md b/Samples/0_Introduction/UnifiedMemoryStreams/README.md index d5980924..f4d669ab 100644 --- a/Samples/0_Introduction/UnifiedMemoryStreams/README.md +++ b/Samples/0_Introduction/UnifiedMemoryStreams/README.md @@ -28,7 +28,7 @@ cudaStreamDestroy, cudaFree, cudaMallocManaged, cudaStreamAttachMemAsync, cudaSe ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj index d6c4e88f..6e5348cc 100644 --- a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj +++ b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj index d5f74d95..d3ecb0e0 100644 --- a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj +++ b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.vcxproj b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.vcxproj index 66895d6d..5c45da00 100644 --- a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.vcxproj +++ b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/asyncAPI/Makefile b/Samples/0_Introduction/asyncAPI/Makefile index 3b9985af..2cb94844 100644 --- a/Samples/0_Introduction/asyncAPI/Makefile +++ b/Samples/0_Introduction/asyncAPI/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/asyncAPI/README.md b/Samples/0_Introduction/asyncAPI/README.md index 034bee6f..0771cf13 100644 --- a/Samples/0_Introduction/asyncAPI/README.md +++ b/Samples/0_Introduction/asyncAPI/README.md @@ -27,7 +27,7 @@ cudaProfilerStop, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaMallocHost, cudaPro ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2017.vcxproj b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2017.vcxproj index 32510413..09ead491 100644 --- a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2017.vcxproj +++ b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2019.vcxproj b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2019.vcxproj index b8d2da1c..a3885ed8 100644 --- a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2019.vcxproj +++ b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2022.vcxproj b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2022.vcxproj index 75f97cea..3f28901c 100644 --- a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2022.vcxproj +++ b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/c++11_cuda/Makefile b/Samples/0_Introduction/c++11_cuda/Makefile index 3defa373..135bb299 100644 --- a/Samples/0_Introduction/c++11_cuda/Makefile +++ b/Samples/0_Introduction/c++11_cuda/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/c++11_cuda/README.md b/Samples/0_Introduction/c++11_cuda/README.md index b5d31356..9829f7d1 100644 --- a/Samples/0_Introduction/c++11_cuda/README.md +++ b/Samples/0_Introduction/c++11_cuda/README.md @@ -30,7 +30,7 @@ cudaMalloc, cudaMemcpy, cudaMemset, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2017.vcxproj b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2017.vcxproj index de0b22e3..b1cb188a 100644 --- a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2017.vcxproj +++ b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2019.vcxproj b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2019.vcxproj index 29eb0cb0..458ab956 100644 --- a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2019.vcxproj +++ b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2022.vcxproj b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2022.vcxproj index 3e41e156..5956254d 100644 --- a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2022.vcxproj +++ b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/clock/Makefile b/Samples/0_Introduction/clock/Makefile index 62519008..a10dabd5 100644 --- a/Samples/0_Introduction/clock/Makefile +++ b/Samples/0_Introduction/clock/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/clock/README.md b/Samples/0_Introduction/clock/README.md index 2936534c..d7e1a47d 100644 --- a/Samples/0_Introduction/clock/README.md +++ b/Samples/0_Introduction/clock/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/clock/clock_vs2017.vcxproj b/Samples/0_Introduction/clock/clock_vs2017.vcxproj index adeba8de..2665281e 100644 --- a/Samples/0_Introduction/clock/clock_vs2017.vcxproj +++ b/Samples/0_Introduction/clock/clock_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/clock/clock_vs2019.vcxproj b/Samples/0_Introduction/clock/clock_vs2019.vcxproj index 35d1213f..f35dff0d 100644 --- a/Samples/0_Introduction/clock/clock_vs2019.vcxproj +++ b/Samples/0_Introduction/clock/clock_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/clock/clock_vs2022.vcxproj b/Samples/0_Introduction/clock/clock_vs2022.vcxproj index c1e1b62f..363b2b0a 100644 --- a/Samples/0_Introduction/clock/clock_vs2022.vcxproj +++ b/Samples/0_Introduction/clock/clock_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/clock_nvrtc/Makefile b/Samples/0_Introduction/clock_nvrtc/Makefile index 5eb485ec..908488c5 100644 --- a/Samples/0_Introduction/clock_nvrtc/Makefile +++ b/Samples/0_Introduction/clock_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/clock_nvrtc/README.md b/Samples/0_Introduction/clock_nvrtc/README.md index 7b6dfc68..f42090ea 100644 --- a/Samples/0_Introduction/clock_nvrtc/README.md +++ b/Samples/0_Introduction/clock_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2017.vcxproj index def5e0c7..c0b592a7 100644 --- a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2019.vcxproj index 0eb1dbc9..9366faf9 100644 --- a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2022.vcxproj index 52890c16..4abb584b 100644 --- a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/concurrentKernels/Makefile b/Samples/0_Introduction/concurrentKernels/Makefile index 42cefe0d..2034a18c 100644 --- a/Samples/0_Introduction/concurrentKernels/Makefile +++ b/Samples/0_Introduction/concurrentKernels/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/concurrentKernels/README.md b/Samples/0_Introduction/concurrentKernels/README.md index c35e94bb..4f4162e6 100644 --- a/Samples/0_Introduction/concurrentKernels/README.md +++ b/Samples/0_Introduction/concurrentKernels/README.md @@ -27,7 +27,7 @@ cudaStreamDestroy, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaMallocHost, cudaEv ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2017.vcxproj b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2017.vcxproj index c6045130..8f763ca7 100644 --- a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2017.vcxproj +++ b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2019.vcxproj b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2019.vcxproj index 27ab6f83..19c9ef89 100644 --- a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2019.vcxproj +++ b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2022.vcxproj b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2022.vcxproj index 00658c64..27f8e5fc 100644 --- a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2022.vcxproj +++ b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/cppIntegration/Makefile b/Samples/0_Introduction/cppIntegration/Makefile index fa6a8f7c..05856802 100644 --- a/Samples/0_Introduction/cppIntegration/Makefile +++ b/Samples/0_Introduction/cppIntegration/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/cppIntegration/README.md b/Samples/0_Introduction/cppIntegration/README.md index a5a5fd8f..9aad8ada 100644 --- a/Samples/0_Introduction/cppIntegration/README.md +++ b/Samples/0_Introduction/cppIntegration/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2017.vcxproj b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2017.vcxproj index f6cddcb0..92f3da7d 100644 --- a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2017.vcxproj +++ b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2019.vcxproj b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2019.vcxproj index 734c4170..28b9b562 100644 --- a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2019.vcxproj +++ b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2022.vcxproj b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2022.vcxproj index df318c2e..27d38565 100644 --- a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2022.vcxproj +++ b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/0_Introduction/cppOverload/Makefile b/Samples/0_Introduction/cppOverload/Makefile index 0fff096c..c6856a44 100644 --- a/Samples/0_Introduction/cppOverload/Makefile +++ b/Samples/0_Introduction/cppOverload/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/cppOverload/README.md b/Samples/0_Introduction/cppOverload/README.md index 87770ff9..dafa4af6 100644 --- a/Samples/0_Introduction/cppOverload/README.md +++ b/Samples/0_Introduction/cppOverload/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFuncSetCacheConfig, cudaFree, cudaMallocHost, cudaSetDevice, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/cppOverload/cppOverload_vs2017.vcxproj b/Samples/0_Introduction/cppOverload/cppOverload_vs2017.vcxproj index aa5d1ccb..69f6e844 100644 --- a/Samples/0_Introduction/cppOverload/cppOverload_vs2017.vcxproj +++ b/Samples/0_Introduction/cppOverload/cppOverload_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/cppOverload/cppOverload_vs2019.vcxproj b/Samples/0_Introduction/cppOverload/cppOverload_vs2019.vcxproj index f6b64340..afceeec7 100644 --- a/Samples/0_Introduction/cppOverload/cppOverload_vs2019.vcxproj +++ b/Samples/0_Introduction/cppOverload/cppOverload_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/cppOverload/cppOverload_vs2022.vcxproj b/Samples/0_Introduction/cppOverload/cppOverload_vs2022.vcxproj index b8dc6fed..e7929d37 100644 --- a/Samples/0_Introduction/cppOverload/cppOverload_vs2022.vcxproj +++ b/Samples/0_Introduction/cppOverload/cppOverload_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/cudaOpenMP/Makefile b/Samples/0_Introduction/cudaOpenMP/Makefile index 6e1993f4..ac9b315f 100644 --- a/Samples/0_Introduction/cudaOpenMP/Makefile +++ b/Samples/0_Introduction/cudaOpenMP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/cudaOpenMP/README.md b/Samples/0_Introduction/cudaOpenMP/README.md index a957032b..63ac988c 100644 --- a/Samples/0_Introduction/cudaOpenMP/README.md +++ b/Samples/0_Introduction/cudaOpenMP/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaGetLastError, cudaSetDevice, cudaG ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2017.vcxproj b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2017.vcxproj index 085c6771..52eac9f4 100644 --- a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2017.vcxproj +++ b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2019.vcxproj b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2019.vcxproj index 0f723d40..6bd63cfd 100644 --- a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2019.vcxproj +++ b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2022.vcxproj b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2022.vcxproj index 5ab734ea..c9ea7301 100644 --- a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2022.vcxproj +++ b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/fp16ScalarProduct/Makefile b/Samples/0_Introduction/fp16ScalarProduct/Makefile index 74b5adb6..fbe28187 100644 --- a/Samples/0_Introduction/fp16ScalarProduct/Makefile +++ b/Samples/0_Introduction/fp16ScalarProduct/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/fp16ScalarProduct/README.md b/Samples/0_Introduction/fp16ScalarProduct/README.md index 176cb405..b91345aa 100644 --- a/Samples/0_Introduction/fp16ScalarProduct/README.md +++ b/Samples/0_Introduction/fp16ScalarProduct/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaMallocHost, cudaFreeHost, cudaMalloc, cudaGetDevicePro ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2017.vcxproj b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2017.vcxproj index ea629117..2e938be4 100644 --- a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2017.vcxproj +++ b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2019.vcxproj b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2019.vcxproj index 3e4e145d..a97f8665 100644 --- a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2019.vcxproj +++ b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2022.vcxproj b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2022.vcxproj index 643e4ad5..741b93d3 100644 --- a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2022.vcxproj +++ b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/matrixMul/Makefile b/Samples/0_Introduction/matrixMul/Makefile index eab4472e..7f0d467f 100644 --- a/Samples/0_Introduction/matrixMul/Makefile +++ b/Samples/0_Introduction/matrixMul/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/matrixMul/README.md b/Samples/0_Introduction/matrixMul/README.md index 74093d77..d6c029b3 100644 --- a/Samples/0_Introduction/matrixMul/README.md +++ b/Samples/0_Introduction/matrixMul/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaProfilerStop, cudaMalloc, cudaFree, cudaMallocHos ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/matrixMul/matrixMul_vs2017.vcxproj b/Samples/0_Introduction/matrixMul/matrixMul_vs2017.vcxproj index bfd5f7be..a31aed07 100644 --- a/Samples/0_Introduction/matrixMul/matrixMul_vs2017.vcxproj +++ b/Samples/0_Introduction/matrixMul/matrixMul_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/matrixMul/matrixMul_vs2019.vcxproj b/Samples/0_Introduction/matrixMul/matrixMul_vs2019.vcxproj index 976abd29..63e2c132 100644 --- a/Samples/0_Introduction/matrixMul/matrixMul_vs2019.vcxproj +++ b/Samples/0_Introduction/matrixMul/matrixMul_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/matrixMul/matrixMul_vs2022.vcxproj b/Samples/0_Introduction/matrixMul/matrixMul_vs2022.vcxproj index d8630eb9..290236ec 100644 --- a/Samples/0_Introduction/matrixMul/matrixMul_vs2022.vcxproj +++ b/Samples/0_Introduction/matrixMul/matrixMul_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDrv/Makefile b/Samples/0_Introduction/matrixMulDrv/Makefile index f9ad912c..520b4a37 100644 --- a/Samples/0_Introduction/matrixMulDrv/Makefile +++ b/Samples/0_Introduction/matrixMulDrv/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/matrixMulDrv/README.md b/Samples/0_Introduction/matrixMulDrv/README.md index 72897274..0b141e1a 100644 --- a/Samples/0_Introduction/matrixMulDrv/README.md +++ b/Samples/0_Introduction/matrixMulDrv/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuDeviceGetName, cuDeviceTotalMem, c ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2017.vcxproj b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2017.vcxproj index 7fdbe3f3..fae4fa68 100644 --- a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2017.vcxproj +++ b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2019.vcxproj b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2019.vcxproj index 06e39510..4a6d0e74 100644 --- a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2019.vcxproj +++ b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2022.vcxproj b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2022.vcxproj index 0c979db5..61a20820 100644 --- a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2022.vcxproj +++ b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDynlinkJIT/Makefile b/Samples/0_Introduction/matrixMulDynlinkJIT/Makefile index 1b78b299..9f81b76f 100644 --- a/Samples/0_Introduction/matrixMulDynlinkJIT/Makefile +++ b/Samples/0_Introduction/matrixMulDynlinkJIT/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/matrixMulDynlinkJIT/README.md b/Samples/0_Introduction/matrixMulDynlinkJIT/README.md index fddb2c74..9428da91 100644 --- a/Samples/0_Introduction/matrixMulDynlinkJIT/README.md +++ b/Samples/0_Introduction/matrixMulDynlinkJIT/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuDeviceGetName, cuParamSeti, cuModuleLoadDataEx, cuModuleGetFunct ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2017.vcxproj b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2017.vcxproj index ecf61f95..1ef02556 100644 --- a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2017.vcxproj +++ b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -116,6 +116,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2019.vcxproj b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2019.vcxproj index b2744de0..0bc0d3cc 100644 --- a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2019.vcxproj +++ b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2022.vcxproj b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2022.vcxproj index 9f81aa72..b1104d61 100644 --- a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2022.vcxproj +++ b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/0_Introduction/matrixMul_nvrtc/Makefile b/Samples/0_Introduction/matrixMul_nvrtc/Makefile index 5750def2..d81d15fa 100644 --- a/Samples/0_Introduction/matrixMul_nvrtc/Makefile +++ b/Samples/0_Introduction/matrixMul_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/matrixMul_nvrtc/README.md b/Samples/0_Introduction/matrixMul_nvrtc/README.md index cc60f1a1..00dc0ae7 100644 --- a/Samples/0_Introduction/matrixMul_nvrtc/README.md +++ b/Samples/0_Introduction/matrixMul_nvrtc/README.md @@ -30,7 +30,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuCtxSynchronize, cuMemAlloc, cuMemF ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2017.vcxproj index 697f9cce..c2300ec3 100644 --- a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -113,6 +113,6 @@ xcopy /y /e /s "$(CudaToolkitDir)include\cooperative_groups" .\cooperative_group - + diff --git a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2019.vcxproj index 3cbf8d6c..2a3d15b1 100644 --- a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ xcopy /y /e /s "$(CudaToolkitDir)include\cooperative_groups" .\cooperative_group - + diff --git a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2022.vcxproj index 43210acc..c78926f3 100644 --- a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ xcopy /y /e /s "$(CudaToolkitDir)include\cooperative_groups" .\cooperative_group - + diff --git a/Samples/0_Introduction/mergeSort/Makefile b/Samples/0_Introduction/mergeSort/Makefile index 33fdba18..b0f1ed0c 100644 --- a/Samples/0_Introduction/mergeSort/Makefile +++ b/Samples/0_Introduction/mergeSort/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/mergeSort/README.md b/Samples/0_Introduction/mergeSort/README.md index 916ff4a3..0865f1ae 100644 --- a/Samples/0_Introduction/mergeSort/README.md +++ b/Samples/0_Introduction/mergeSort/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/mergeSort/mergeSort_vs2017.vcxproj b/Samples/0_Introduction/mergeSort/mergeSort_vs2017.vcxproj index 7aabd7c6..2e88e6b0 100644 --- a/Samples/0_Introduction/mergeSort/mergeSort_vs2017.vcxproj +++ b/Samples/0_Introduction/mergeSort/mergeSort_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/0_Introduction/mergeSort/mergeSort_vs2019.vcxproj b/Samples/0_Introduction/mergeSort/mergeSort_vs2019.vcxproj index fda7eb26..7a3664ad 100644 --- a/Samples/0_Introduction/mergeSort/mergeSort_vs2019.vcxproj +++ b/Samples/0_Introduction/mergeSort/mergeSort_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/mergeSort/mergeSort_vs2022.vcxproj b/Samples/0_Introduction/mergeSort/mergeSort_vs2022.vcxproj index 6c3223dd..9788c718 100644 --- a/Samples/0_Introduction/mergeSort/mergeSort_vs2022.vcxproj +++ b/Samples/0_Introduction/mergeSort/mergeSort_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleAWBarrier/Makefile b/Samples/0_Introduction/simpleAWBarrier/Makefile index e0b09e0b..ecc1a81a 100644 --- a/Samples/0_Introduction/simpleAWBarrier/Makefile +++ b/Samples/0_Introduction/simpleAWBarrier/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAWBarrier/README.md b/Samples/0_Introduction/simpleAWBarrier/README.md index 6ee52f1d..699b2d05 100644 --- a/Samples/0_Introduction/simpleAWBarrier/README.md +++ b/Samples/0_Introduction/simpleAWBarrier/README.md @@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaFree, cudaDeviceGetAttribute, cudaMallocHost, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2017.vcxproj b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2017.vcxproj index 04891e79..bb0d370e 100644 --- a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2019.vcxproj b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2019.vcxproj index 285b8410..dbee7ab4 100644 --- a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2022.vcxproj b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2022.vcxproj index 58daef61..46890ff8 100644 --- a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert/Makefile b/Samples/0_Introduction/simpleAssert/Makefile index 97051382..c5bda357 100644 --- a/Samples/0_Introduction/simpleAssert/Makefile +++ b/Samples/0_Introduction/simpleAssert/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAssert/README.md b/Samples/0_Introduction/simpleAssert/README.md index f5199bd9..9db26069 100644 --- a/Samples/0_Introduction/simpleAssert/README.md +++ b/Samples/0_Introduction/simpleAssert/README.md @@ -27,7 +27,7 @@ cudaDeviceSynchronize, cudaGetErrorString ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2017.vcxproj b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2017.vcxproj index 32bc9ed5..b1c2d63a 100644 --- a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2019.vcxproj b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2019.vcxproj index ce25e9c8..030afce1 100644 --- a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2022.vcxproj b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2022.vcxproj index 7841bf67..a8b9f906 100644 --- a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert_nvrtc/Makefile b/Samples/0_Introduction/simpleAssert_nvrtc/Makefile index cf55bdc2..a8a09697 100644 --- a/Samples/0_Introduction/simpleAssert_nvrtc/Makefile +++ b/Samples/0_Introduction/simpleAssert_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAssert_nvrtc/README.md b/Samples/0_Introduction/simpleAssert_nvrtc/README.md index 587d2b07..5a633d76 100644 --- a/Samples/0_Introduction/simpleAssert_nvrtc/README.md +++ b/Samples/0_Introduction/simpleAssert_nvrtc/README.md @@ -30,7 +30,7 @@ cuModuleGetFunction, cuLaunchKernel, cuCtxSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2017.vcxproj index cdc057ad..d9e8ef6c 100644 --- a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2019.vcxproj index d28b3e12..e723140e 100644 --- a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2022.vcxproj index 351efb75..998b46bd 100644 --- a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics/Makefile b/Samples/0_Introduction/simpleAtomicIntrinsics/Makefile index 9de4a6a9..31be5b08 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics/Makefile +++ b/Samples/0_Introduction/simpleAtomicIntrinsics/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics/README.md b/Samples/0_Introduction/simpleAtomicIntrinsics/README.md index 99177ff4..f584d3de 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics/README.md +++ b/Samples/0_Introduction/simpleAtomicIntrinsics/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaFree, cudaMallocHost, cudaFreeHost, cudaStreamSyn ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2017.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2017.vcxproj index 2d9027f6..2f316522 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2019.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2019.vcxproj index 063c5bdc..c9812b1d 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2022.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2022.vcxproj index 3ec20b8f..2a511d70 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/Makefile b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/Makefile index 73ada20b..f70e2d3c 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/Makefile +++ b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/README.md b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/README.md index b8829eb4..753c5c9d 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/README.md +++ b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2017.vcxproj index 21cb7fce..25761054 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2019.vcxproj index 5dbd093c..5f7cabf2 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2022.vcxproj index 323163a0..9bcdf7fc 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleAttributes/Makefile b/Samples/0_Introduction/simpleAttributes/Makefile index 5e2459ce..1e6a1a48 100644 --- a/Samples/0_Introduction/simpleAttributes/Makefile +++ b/Samples/0_Introduction/simpleAttributes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAttributes/README.md b/Samples/0_Introduction/simpleAttributes/README.md index 082d6933..cba3752e 100644 --- a/Samples/0_Introduction/simpleAttributes/README.md +++ b/Samples/0_Introduction/simpleAttributes/README.md @@ -27,7 +27,7 @@ cudaFree, cudaMallocHost, cudaFreeHost, cudaStreamSynchronize, cudaStreamSetAttr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2017.vcxproj b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2017.vcxproj index 731c0fdc..838513f5 100644 --- a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2019.vcxproj b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2019.vcxproj index 5f0e908e..71673c72 100644 --- a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2022.vcxproj b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2022.vcxproj index 27a96333..2609e135 100644 --- a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleCUDA2GL/Makefile b/Samples/0_Introduction/simpleCUDA2GL/Makefile index 14de6141..ef6d0228 100644 --- a/Samples/0_Introduction/simpleCUDA2GL/Makefile +++ b/Samples/0_Introduction/simpleCUDA2GL/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleCUDA2GL/README.md b/Samples/0_Introduction/simpleCUDA2GL/README.md index bbf27477..6c17427f 100644 --- a/Samples/0_Introduction/simpleCUDA2GL/README.md +++ b/Samples/0_Introduction/simpleCUDA2GL/README.md @@ -30,7 +30,7 @@ cudaHostAlloc, cudaGraphicsUnmapResources, cudaMalloc, cudaFree, cudaGraphicsRes ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2017.vcxproj b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2017.vcxproj index 651d829a..d4f9e60d 100644 --- a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2019.vcxproj b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2019.vcxproj index b4ee9c5a..1e349c6c 100644 --- a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2022.vcxproj b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2022.vcxproj index 75c0b736..63a46adf 100644 --- a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/0_Introduction/simpleCallback/Makefile b/Samples/0_Introduction/simpleCallback/Makefile index f8a66113..7e64be2b 100644 --- a/Samples/0_Introduction/simpleCallback/Makefile +++ b/Samples/0_Introduction/simpleCallback/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleCallback/README.md b/Samples/0_Introduction/simpleCallback/README.md index 3f7bdddc..2dd97e18 100644 --- a/Samples/0_Introduction/simpleCallback/README.md +++ b/Samples/0_Introduction/simpleCallback/README.md @@ -27,7 +27,7 @@ cudaHostAlloc, cudaStreamDestroy, cudaFree, cudaSetDevice, cudaGetDeviceCount, c ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2017.vcxproj b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2017.vcxproj index e34a6867..6542b9e7 100644 --- a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2019.vcxproj b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2019.vcxproj index 9f2743ad..8b9087fe 100644 --- a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2022.vcxproj b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2022.vcxproj index dfc3e5f4..cdb95825 100644 --- a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleCooperativeGroups/Makefile b/Samples/0_Introduction/simpleCooperativeGroups/Makefile index baa1349e..68c718fb 100644 --- a/Samples/0_Introduction/simpleCooperativeGroups/Makefile +++ b/Samples/0_Introduction/simpleCooperativeGroups/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleCooperativeGroups/README.md b/Samples/0_Introduction/simpleCooperativeGroups/README.md index e39b39e5..ebb1a9a5 100644 --- a/Samples/0_Introduction/simpleCooperativeGroups/README.md +++ b/Samples/0_Introduction/simpleCooperativeGroups/README.md @@ -27,7 +27,7 @@ cudaDeviceSynchronize, cudaGetErrorString ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2017.vcxproj b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2017.vcxproj index afe9cacf..31385b13 100644 --- a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2019.vcxproj b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2019.vcxproj index 261d57c7..7611542c 100644 --- a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2022.vcxproj b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2022.vcxproj index 570f7146..01a13b67 100644 --- a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleCubemapTexture/Makefile b/Samples/0_Introduction/simpleCubemapTexture/Makefile index 8ff8ef72..6f6a37bf 100644 --- a/Samples/0_Introduction/simpleCubemapTexture/Makefile +++ b/Samples/0_Introduction/simpleCubemapTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleCubemapTexture/README.md b/Samples/0_Introduction/simpleCubemapTexture/README.md index 775b444d..87e4a5cb 100644 --- a/Samples/0_Introduction/simpleCubemapTexture/README.md +++ b/Samples/0_Introduction/simpleCubemapTexture/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaCreateChannelDesc, cudaFreeArray, cudaFree, cudaPitchedPtr, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2017.vcxproj b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2017.vcxproj index 68588c2d..594ad5c8 100644 --- a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2019.vcxproj b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2019.vcxproj index 33876489..eeab65c0 100644 --- a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2022.vcxproj b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2022.vcxproj index 36e1d840..fd5a497c 100644 --- a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleDrvRuntime/Makefile b/Samples/0_Introduction/simpleDrvRuntime/Makefile index e1606837..700b865e 100644 --- a/Samples/0_Introduction/simpleDrvRuntime/Makefile +++ b/Samples/0_Introduction/simpleDrvRuntime/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleDrvRuntime/README.md b/Samples/0_Introduction/simpleDrvRuntime/README.md index 570629a0..52a2ed1e 100644 --- a/Samples/0_Introduction/simpleDrvRuntime/README.md +++ b/Samples/0_Introduction/simpleDrvRuntime/README.md @@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaFree, cudaMallocHost, cudaFreeHost, cudaStreamSyn ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2017.vcxproj b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2017.vcxproj index 9bee3337..bafc145d 100644 --- a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2019.vcxproj b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2019.vcxproj index ad82ef76..ee2639bc 100644 --- a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2022.vcxproj b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2022.vcxproj index 31c72324..ca0dcbf7 100644 --- a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleHyperQ/Makefile b/Samples/0_Introduction/simpleHyperQ/Makefile index 14b34ace..ef839105 100644 --- a/Samples/0_Introduction/simpleHyperQ/Makefile +++ b/Samples/0_Introduction/simpleHyperQ/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleHyperQ/README.md b/Samples/0_Introduction/simpleHyperQ/README.md index 0473f04b..fcbe2e98 100644 --- a/Samples/0_Introduction/simpleHyperQ/README.md +++ b/Samples/0_Introduction/simpleHyperQ/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaStreamDestroy, cudaMalloc, cudaFree, cudaMallocHost, cudaEventSy ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2017.vcxproj b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2017.vcxproj index d2069877..d01592ce 100644 --- a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2019.vcxproj b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2019.vcxproj index 5a122c71..7d0be42c 100644 --- a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2022.vcxproj b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2022.vcxproj index ce864e35..f70085be 100644 --- a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleIPC/Makefile b/Samples/0_Introduction/simpleIPC/Makefile index a4d1b885..a860c59f 100644 --- a/Samples/0_Introduction/simpleIPC/Makefile +++ b/Samples/0_Introduction/simpleIPC/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleIPC/README.md b/Samples/0_Introduction/simpleIPC/README.md index 0bd5381e..bd80ca7e 100644 --- a/Samples/0_Introduction/simpleIPC/README.md +++ b/Samples/0_Introduction/simpleIPC/README.md @@ -30,7 +30,7 @@ cudaSetDevice, cudaIpcCloseMemHandle, cudaEventDestroy, cudaGetDeviceCount, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2017.vcxproj b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2017.vcxproj index 26b2f325..53cbc764 100644 --- a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2019.vcxproj b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2019.vcxproj index b9285fdf..d71adcb2 100644 --- a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2022.vcxproj b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2022.vcxproj index 78564400..3660d699 100644 --- a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleLayeredTexture/Makefile b/Samples/0_Introduction/simpleLayeredTexture/Makefile index b1a0b9dd..03781a5a 100644 --- a/Samples/0_Introduction/simpleLayeredTexture/Makefile +++ b/Samples/0_Introduction/simpleLayeredTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleLayeredTexture/README.md b/Samples/0_Introduction/simpleLayeredTexture/README.md index 521e0e1c..f13fae26 100644 --- a/Samples/0_Introduction/simpleLayeredTexture/README.md +++ b/Samples/0_Introduction/simpleLayeredTexture/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaCreateChannelDesc, cudaFreeArray, cudaFree, cudaPitchedPtr, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2017.vcxproj b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2017.vcxproj index 229f4be9..4e44f622 100644 --- a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2019.vcxproj b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2019.vcxproj index 503dde2d..65c2c947 100644 --- a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2022.vcxproj b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2022.vcxproj index c951db56..b7874159 100644 --- a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleMPI/Makefile b/Samples/0_Introduction/simpleMPI/Makefile index 3cd4f240..86eda321 100644 --- a/Samples/0_Introduction/simpleMPI/Makefile +++ b/Samples/0_Introduction/simpleMPI/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -277,15 +290,9 @@ ifeq ($(TARGET_ARCH),armv7l) SAMPLE_ENABLED := 0 endif -# This sample is not supported on aarch64 -ifeq ($(TARGET_ARCH),aarch64) - $(info >>> WARNING - simpleMPI is not supported on aarch64 - waiving sample <<<) - SAMPLE_ENABLED := 0 -endif - -# This sample is not supported on sbsa -ifeq ($(TARGET_ARCH),sbsa) - $(info >>> WARNING - simpleMPI is not supported on sbsa - waiving sample <<<) +# This sample is not supported on QNX +ifeq ($(TARGET_OS),qnx) + $(info >>> WARNING - simpleMPI is not supported on QNX - waiving sample <<<) SAMPLE_ENABLED := 0 endif diff --git a/Samples/0_Introduction/simpleMPI/README.md b/Samples/0_Introduction/simpleMPI/README.md index de7f9a74..1a8a152a 100644 --- a/Samples/0_Introduction/simpleMPI/README.md +++ b/Samples/0_Introduction/simpleMPI/README.md @@ -18,7 +18,7 @@ Linux, Windows ## Supported CPU Architecture -x86_64, ppc64le +x86_64, ppc64le, aarch64 ## CUDA APIs involved @@ -30,7 +30,7 @@ cudaMalloc, cudaGetLastError, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run @@ -52,9 +52,9 @@ $ cd $ make ``` The samples makefiles can take advantage of certain options: -* **TARGET_ARCH=** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, ppc64le. +* **TARGET_ARCH=** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, ppc64le, aarch64. By default, TARGET_ARCH is set to HOST_ARCH. On a x86_64 machine, not setting TARGET_ARCH is the equivalent of setting TARGET_ARCH=x86_64.
-`$ make TARGET_ARCH=x86_64`
`$ make TARGET_ARCH=ppc64le`
+`$ make TARGET_ARCH=x86_64`
`$ make TARGET_ARCH=ppc64le`
`$ make TARGET_ARCH=aarch64`
See [here](http://docs.nvidia.com/cuda/cuda-samples/index.html#cross-samples) for more details. * **dbg=1** - build with debug symbols ``` diff --git a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2017.vcxproj b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2017.vcxproj index 478d99f1..f5400226 100644 --- a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2019.vcxproj b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2019.vcxproj index f65e9ff4..609623d2 100644 --- a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2022.vcxproj b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2022.vcxproj index 2de0bb62..a3fdbe3a 100644 --- a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiCopy/Makefile b/Samples/0_Introduction/simpleMultiCopy/Makefile index 2db21586..69a8d606 100644 --- a/Samples/0_Introduction/simpleMultiCopy/Makefile +++ b/Samples/0_Introduction/simpleMultiCopy/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleMultiCopy/README.md b/Samples/0_Introduction/simpleMultiCopy/README.md index 83017ed9..d531a50c 100644 --- a/Samples/0_Introduction/simpleMultiCopy/README.md +++ b/Samples/0_Introduction/simpleMultiCopy/README.md @@ -27,7 +27,7 @@ cudaHostAlloc, cudaStreamDestroy, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaSet ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2017.vcxproj b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2017.vcxproj index da5010b6..421cd586 100644 --- a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2019.vcxproj b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2019.vcxproj index 3822a996..ca10e64f 100644 --- a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2022.vcxproj b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2022.vcxproj index b7911f33..47f9f6ec 100644 --- a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiGPU/Makefile b/Samples/0_Introduction/simpleMultiGPU/Makefile index 02a154c5..3ede2ba0 100644 --- a/Samples/0_Introduction/simpleMultiGPU/Makefile +++ b/Samples/0_Introduction/simpleMultiGPU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleMultiGPU/README.md b/Samples/0_Introduction/simpleMultiGPU/README.md index 5d4e5153..3fc5e0b3 100644 --- a/Samples/0_Introduction/simpleMultiGPU/README.md +++ b/Samples/0_Introduction/simpleMultiGPU/README.md @@ -27,7 +27,7 @@ cudaStreamDestroy, cudaFree, cudaMallocHost, cudaSetDevice, cudaFreeHost, cudaSt ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2017.vcxproj b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2017.vcxproj index 04dbe5b0..451fff95 100644 --- a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2019.vcxproj b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2019.vcxproj index b3c91b60..74770e5f 100644 --- a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2022.vcxproj b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2022.vcxproj index 25abe00c..b1a4cb76 100644 --- a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleOccupancy/Makefile b/Samples/0_Introduction/simpleOccupancy/Makefile index a0542a70..9a593fec 100644 --- a/Samples/0_Introduction/simpleOccupancy/Makefile +++ b/Samples/0_Introduction/simpleOccupancy/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleOccupancy/README.md b/Samples/0_Introduction/simpleOccupancy/README.md index 792bbba6..2f327a6e 100644 --- a/Samples/0_Introduction/simpleOccupancy/README.md +++ b/Samples/0_Introduction/simpleOccupancy/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaEventRecord, cudaGetDevice, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2017.vcxproj b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2017.vcxproj index e994ee58..10d6e40b 100644 --- a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2019.vcxproj b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2019.vcxproj index 3e63206b..32e8e61f 100644 --- a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2022.vcxproj b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2022.vcxproj index 09ddb244..c80c6147 100644 --- a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleP2P/Makefile b/Samples/0_Introduction/simpleP2P/Makefile index f2fdab24..7e420c95 100644 --- a/Samples/0_Introduction/simpleP2P/Makefile +++ b/Samples/0_Introduction/simpleP2P/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleP2P/README.md b/Samples/0_Introduction/simpleP2P/README.md index 8c6f4f41..15179b35 100644 --- a/Samples/0_Introduction/simpleP2P/README.md +++ b/Samples/0_Introduction/simpleP2P/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaMalloc, cudaFree, cudaMallocHost, cudaEventCreateWithFlags, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2017.vcxproj b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2017.vcxproj index ac3c8d0c..5c8dbaea 100644 --- a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2019.vcxproj b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2019.vcxproj index b015cb9d..77e81b2b 100644 --- a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2022.vcxproj b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2022.vcxproj index add2eb24..97c851af 100644 --- a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simplePitchLinearTexture/Makefile b/Samples/0_Introduction/simplePitchLinearTexture/Makefile index 956ee1ee..fece95a5 100644 --- a/Samples/0_Introduction/simplePitchLinearTexture/Makefile +++ b/Samples/0_Introduction/simplePitchLinearTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simplePitchLinearTexture/README.md b/Samples/0_Introduction/simplePitchLinearTexture/README.md index 30aff62b..921f3891 100644 --- a/Samples/0_Introduction/simplePitchLinearTexture/README.md +++ b/Samples/0_Introduction/simplePitchLinearTexture/README.md @@ -27,7 +27,7 @@ cudaMallocArray, cudaFreeArray, cudaFree, cudaMallocPitch, cudaDestroyTextureObj ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2017.vcxproj b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2017.vcxproj index ac8b3493..d776730d 100644 --- a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2017.vcxproj +++ b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2019.vcxproj b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2019.vcxproj index 543b83d5..55786b7b 100644 --- a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2019.vcxproj +++ b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2022.vcxproj b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2022.vcxproj index 7ca473b0..82797c87 100644 --- a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2022.vcxproj +++ b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simplePrintf/Makefile b/Samples/0_Introduction/simplePrintf/Makefile index 45f43aa6..ff66e2de 100644 --- a/Samples/0_Introduction/simplePrintf/Makefile +++ b/Samples/0_Introduction/simplePrintf/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simplePrintf/README.md b/Samples/0_Introduction/simplePrintf/README.md index db910ee0..69dba7a2 100644 --- a/Samples/0_Introduction/simplePrintf/README.md +++ b/Samples/0_Introduction/simplePrintf/README.md @@ -27,7 +27,7 @@ cudaGetDeviceProperties, cudaDeviceSynchronize, cudaGetDevice ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2017.vcxproj b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2017.vcxproj index 76824ecf..7ec3664d 100644 --- a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2017.vcxproj +++ b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2019.vcxproj b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2019.vcxproj index 3105be18..edcc68af 100644 --- a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2019.vcxproj +++ b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2022.vcxproj b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2022.vcxproj index 4a26d560..8e9a45dd 100644 --- a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2022.vcxproj +++ b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleSeparateCompilation/Makefile b/Samples/0_Introduction/simpleSeparateCompilation/Makefile index cca7ac69..7e16c0c0 100644 --- a/Samples/0_Introduction/simpleSeparateCompilation/Makefile +++ b/Samples/0_Introduction/simpleSeparateCompilation/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleSeparateCompilation/README.md b/Samples/0_Introduction/simpleSeparateCompilation/README.md index 78f15355..0fc29062 100644 --- a/Samples/0_Introduction/simpleSeparateCompilation/README.md +++ b/Samples/0_Introduction/simpleSeparateCompilation/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaMemcpyFromSymbol, cudaFree, cudaGetLastError, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2017.vcxproj b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2017.vcxproj index 8bd58918..45d5b939 100644 --- a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2019.vcxproj b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2019.vcxproj index 5fd52629..8870c6b6 100644 --- a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2022.vcxproj b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2022.vcxproj index 97ed8121..1300538f 100644 --- a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/0_Introduction/simpleStreams/Makefile b/Samples/0_Introduction/simpleStreams/Makefile index f59124a2..1972fe54 100644 --- a/Samples/0_Introduction/simpleStreams/Makefile +++ b/Samples/0_Introduction/simpleStreams/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleStreams/README.md b/Samples/0_Introduction/simpleStreams/README.md index 108d9f9e..439f733a 100644 --- a/Samples/0_Introduction/simpleStreams/README.md +++ b/Samples/0_Introduction/simpleStreams/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaSetDeviceFlags, cudaSetDevice, cudaEventDestroy, cudaStreamCreat ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2017.vcxproj b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2017.vcxproj index cc497a19..97b2ca7a 100644 --- a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2019.vcxproj b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2019.vcxproj index 2d5d9aad..3fb865a5 100644 --- a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2022.vcxproj b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2022.vcxproj index 972e6b4e..3c7ecd2f 100644 --- a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleSurfaceWrite/Makefile b/Samples/0_Introduction/simpleSurfaceWrite/Makefile index 89f6dfc6..fdc32d5f 100644 --- a/Samples/0_Introduction/simpleSurfaceWrite/Makefile +++ b/Samples/0_Introduction/simpleSurfaceWrite/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleSurfaceWrite/README.md b/Samples/0_Introduction/simpleSurfaceWrite/README.md index d1396a43..a61c1d2e 100644 --- a/Samples/0_Introduction/simpleSurfaceWrite/README.md +++ b/Samples/0_Introduction/simpleSurfaceWrite/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaCreateChannelDesc, cudaMallocArray, cudaFreeArray, cudaFree, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2017.vcxproj b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2017.vcxproj index 6142e3cd..c324440c 100644 --- a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2019.vcxproj b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2019.vcxproj index b5973a72..2e5bea8a 100644 --- a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2022.vcxproj b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2022.vcxproj index 2cd54658..c80a558e 100644 --- a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates/Makefile b/Samples/0_Introduction/simpleTemplates/Makefile index 410c37de..db7c590f 100644 --- a/Samples/0_Introduction/simpleTemplates/Makefile +++ b/Samples/0_Introduction/simpleTemplates/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleTemplates/README.md b/Samples/0_Introduction/simpleTemplates/README.md index 07fbba69..5ab565a0 100644 --- a/Samples/0_Introduction/simpleTemplates/README.md +++ b/Samples/0_Introduction/simpleTemplates/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaGetDeviceProperties, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2017.vcxproj b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2017.vcxproj index 996c9cbd..ec166d6f 100644 --- a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2019.vcxproj b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2019.vcxproj index 1afdd93f..7a43b57d 100644 --- a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2022.vcxproj b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2022.vcxproj index 66337427..c0d0da5f 100644 --- a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates_nvrtc/Makefile b/Samples/0_Introduction/simpleTemplates_nvrtc/Makefile index 78ab245c..24a5bd91 100644 --- a/Samples/0_Introduction/simpleTemplates_nvrtc/Makefile +++ b/Samples/0_Introduction/simpleTemplates_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleTemplates_nvrtc/README.md b/Samples/0_Introduction/simpleTemplates_nvrtc/README.md index d0c83eec..09f98362 100644 --- a/Samples/0_Introduction/simpleTemplates_nvrtc/README.md +++ b/Samples/0_Introduction/simpleTemplates_nvrtc/README.md @@ -30,7 +30,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuCtxSynchronize, cuMemAlloc, cuMemF ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2017.vcxproj index 24b7f31b..6e087899 100644 --- a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2019.vcxproj index acd83544..3f04d345 100644 --- a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2022.vcxproj index a9adfad1..d3933144 100644 --- a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture/Makefile b/Samples/0_Introduction/simpleTexture/Makefile index bc6e97f5..f6e4cde6 100644 --- a/Samples/0_Introduction/simpleTexture/Makefile +++ b/Samples/0_Introduction/simpleTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleTexture/README.md b/Samples/0_Introduction/simpleTexture/README.md index 901e3b15..fdca8911 100644 --- a/Samples/0_Introduction/simpleTexture/README.md +++ b/Samples/0_Introduction/simpleTexture/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaCreateChannelDesc, cudaMallocArray, cudaFreeArray, cudaFree, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2017.vcxproj b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2017.vcxproj index f4140e6a..676a5f50 100644 --- a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2019.vcxproj b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2019.vcxproj index 9824a29e..9f154c4e 100644 --- a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2022.vcxproj b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2022.vcxproj index 4aacd5ca..d74f2865 100644 --- a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture3D/Makefile b/Samples/0_Introduction/simpleTexture3D/Makefile index 93124c22..fd8987cc 100644 --- a/Samples/0_Introduction/simpleTexture3D/Makefile +++ b/Samples/0_Introduction/simpleTexture3D/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleTexture3D/README.md b/Samples/0_Introduction/simpleTexture3D/README.md index 5aaa8d7d..48f9961c 100644 --- a/Samples/0_Introduction/simpleTexture3D/README.md +++ b/Samples/0_Introduction/simpleTexture3D/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFreeArray, cudaFree, cudaPitchedPtr, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2017.vcxproj b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2017.vcxproj index e3412d29..e1efe32b 100644 --- a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2019.vcxproj b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2019.vcxproj index 6531811a..a928284c 100644 --- a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2022.vcxproj b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2022.vcxproj index 0e40b768..cfd623aa 100644 --- a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/0_Introduction/simpleTextureDrv/Makefile b/Samples/0_Introduction/simpleTextureDrv/Makefile index d57e1596..b11d1847 100644 --- a/Samples/0_Introduction/simpleTextureDrv/Makefile +++ b/Samples/0_Introduction/simpleTextureDrv/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleTextureDrv/README.md b/Samples/0_Introduction/simpleTextureDrv/README.md index e918d88c..461d408c 100644 --- a/Samples/0_Introduction/simpleTextureDrv/README.md +++ b/Samples/0_Introduction/simpleTextureDrv/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuModuleLoadData, cuDeviceGetName, cuDeviceGetAttr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2017.vcxproj b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2017.vcxproj index b1c2fd0e..04e3ac72 100644 --- a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2019.vcxproj b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2019.vcxproj index de277452..6652d2a6 100644 --- a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2022.vcxproj b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2022.vcxproj index 44d37eae..cb683fd3 100644 --- a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics/Makefile b/Samples/0_Introduction/simpleVoteIntrinsics/Makefile index 8e30c98b..4e338815 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics/Makefile +++ b/Samples/0_Introduction/simpleVoteIntrinsics/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleVoteIntrinsics/README.md b/Samples/0_Introduction/simpleVoteIntrinsics/README.md index 81df332f..7558f259 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics/README.md +++ b/Samples/0_Introduction/simpleVoteIntrinsics/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2017.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2017.vcxproj index edc30560..0d9aa253 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2019.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2019.vcxproj index 64e031c2..f1074a43 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2022.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2022.vcxproj index dc5fec0b..0ce06db4 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/Makefile b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/Makefile index 538ddbca..4999d92b 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/Makefile +++ b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/README.md b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/README.md index 55bcc1c7..a3487a98 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/README.md +++ b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/README.md @@ -30,7 +30,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuCtxSynchronize, cuMemAlloc, cuMemF ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2017.vcxproj index 9e4b7391..24a1590b 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2019.vcxproj index fb4d7730..e0ab48c8 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2022.vcxproj index e638c176..c71c942c 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleZeroCopy/Makefile b/Samples/0_Introduction/simpleZeroCopy/Makefile index 79cb6a85..00082494 100644 --- a/Samples/0_Introduction/simpleZeroCopy/Makefile +++ b/Samples/0_Introduction/simpleZeroCopy/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleZeroCopy/README.md b/Samples/0_Introduction/simpleZeroCopy/README.md index 08e02fa7..faf5b407 100644 --- a/Samples/0_Introduction/simpleZeroCopy/README.md +++ b/Samples/0_Introduction/simpleZeroCopy/README.md @@ -27,7 +27,7 @@ cudaHostAlloc, cudaSetDeviceFlags, cudaHostRegister, cudaSetDevice, cudaGetDevic ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2017.vcxproj b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2017.vcxproj index dc529e96..5f085b82 100644 --- a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2019.vcxproj b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2019.vcxproj index 3f89ba08..ad045a0f 100644 --- a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2022.vcxproj b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2022.vcxproj index 1631f981..128d6fb2 100644 --- a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/systemWideAtomics/Makefile b/Samples/0_Introduction/systemWideAtomics/Makefile index ce22b796..13efbdbe 100644 --- a/Samples/0_Introduction/systemWideAtomics/Makefile +++ b/Samples/0_Introduction/systemWideAtomics/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/systemWideAtomics/README.md b/Samples/0_Introduction/systemWideAtomics/README.md index e9e22eb7..35d4886e 100644 --- a/Samples/0_Introduction/systemWideAtomics/README.md +++ b/Samples/0_Introduction/systemWideAtomics/README.md @@ -30,7 +30,7 @@ cudaDeviceSynchronize, cudaMallocManaged, cudaGetDeviceProperties, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/template/Makefile b/Samples/0_Introduction/template/Makefile index 5bb987e9..dfc9ff87 100644 --- a/Samples/0_Introduction/template/Makefile +++ b/Samples/0_Introduction/template/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/template/README.md b/Samples/0_Introduction/template/README.md index ded8e64d..af7fa757 100644 --- a/Samples/0_Introduction/template/README.md +++ b/Samples/0_Introduction/template/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/template/template_vs2017.vcxproj b/Samples/0_Introduction/template/template_vs2017.vcxproj index 600260f8..119b05e4 100644 --- a/Samples/0_Introduction/template/template_vs2017.vcxproj +++ b/Samples/0_Introduction/template/template_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/template/template_vs2019.vcxproj b/Samples/0_Introduction/template/template_vs2019.vcxproj index 797a4ef3..6ff2612f 100644 --- a/Samples/0_Introduction/template/template_vs2019.vcxproj +++ b/Samples/0_Introduction/template/template_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/template/template_vs2022.vcxproj b/Samples/0_Introduction/template/template_vs2022.vcxproj index 597a4ac5..bc842729 100644 --- a/Samples/0_Introduction/template/template_vs2022.vcxproj +++ b/Samples/0_Introduction/template/template_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd/Makefile b/Samples/0_Introduction/vectorAdd/Makefile index 4ac555e7..ea143965 100644 --- a/Samples/0_Introduction/vectorAdd/Makefile +++ b/Samples/0_Introduction/vectorAdd/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/vectorAdd/README.md b/Samples/0_Introduction/vectorAdd/README.md index d0030dc1..bcafb84a 100644 --- a/Samples/0_Introduction/vectorAdd/README.md +++ b/Samples/0_Introduction/vectorAdd/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaGetLastError, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2017.vcxproj b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2017.vcxproj index 8bf1ac17..84929809 100644 --- a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2017.vcxproj +++ b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2019.vcxproj b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2019.vcxproj index 8a12b05c..b94d33f0 100644 --- a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2019.vcxproj +++ b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2022.vcxproj b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2022.vcxproj index 4622684c..e1632be2 100644 --- a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2022.vcxproj +++ b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddDrv/Makefile b/Samples/0_Introduction/vectorAddDrv/Makefile index c163e969..99154c3b 100644 --- a/Samples/0_Introduction/vectorAddDrv/Makefile +++ b/Samples/0_Introduction/vectorAddDrv/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/vectorAddDrv/README.md b/Samples/0_Introduction/vectorAddDrv/README.md index 14884af7..ededa2ac 100644 --- a/Samples/0_Introduction/vectorAddDrv/README.md +++ b/Samples/0_Introduction/vectorAddDrv/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuModuleLoadData, cuCtxSynchronize, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2017.vcxproj b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2017.vcxproj index 0e1ea43f..d9af8d39 100644 --- a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2017.vcxproj +++ b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2019.vcxproj b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2019.vcxproj index 8c375560..3addd31e 100644 --- a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2019.vcxproj +++ b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2022.vcxproj b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2022.vcxproj index fca354cb..f50024ec 100644 --- a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2022.vcxproj +++ b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddMMAP/Makefile b/Samples/0_Introduction/vectorAddMMAP/Makefile index a9ede4b7..8bddeb07 100644 --- a/Samples/0_Introduction/vectorAddMMAP/Makefile +++ b/Samples/0_Introduction/vectorAddMMAP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/vectorAddMMAP/README.md b/Samples/0_Introduction/vectorAddMMAP/README.md index 15ff121e..701e08e3 100644 --- a/Samples/0_Introduction/vectorAddMMAP/README.md +++ b/Samples/0_Introduction/vectorAddMMAP/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuDeviceCanAccessPeer, cuModuleGetFunction, cuMemSetAccess, cuMemR ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2017.vcxproj b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2017.vcxproj index 61d096f5..369a9007 100644 --- a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2017.vcxproj +++ b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2019.vcxproj b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2019.vcxproj index 53db107f..4c278e7c 100644 --- a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2019.vcxproj +++ b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2022.vcxproj b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2022.vcxproj index 04bc86aa..174356b2 100644 --- a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2022.vcxproj +++ b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd_nvrtc/Makefile b/Samples/0_Introduction/vectorAdd_nvrtc/Makefile index bf27a058..fe592312 100644 --- a/Samples/0_Introduction/vectorAdd_nvrtc/Makefile +++ b/Samples/0_Introduction/vectorAdd_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/vectorAdd_nvrtc/README.md b/Samples/0_Introduction/vectorAdd_nvrtc/README.md index d291647a..863f4c5a 100644 --- a/Samples/0_Introduction/vectorAdd_nvrtc/README.md +++ b/Samples/0_Introduction/vectorAdd_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2017.vcxproj index 481f7382..d798dd6f 100644 --- a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2019.vcxproj index ab08b3e5..274fda17 100644 --- a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2022.vcxproj index 0a3755dc..cec326eb 100644 --- a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/bandwidthTest/Makefile b/Samples/1_Utilities/bandwidthTest/Makefile index 3132ee58..d7a50c57 100644 --- a/Samples/1_Utilities/bandwidthTest/Makefile +++ b/Samples/1_Utilities/bandwidthTest/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/1_Utilities/bandwidthTest/README.md b/Samples/1_Utilities/bandwidthTest/README.md index a0e94443..392e4897 100644 --- a/Samples/1_Utilities/bandwidthTest/README.md +++ b/Samples/1_Utilities/bandwidthTest/README.md @@ -27,7 +27,7 @@ cudaHostAlloc, cudaMemcpy, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaGetErrorSt ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2017.vcxproj b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2017.vcxproj index a883411c..6e44223c 100644 --- a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2017.vcxproj +++ b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2019.vcxproj b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2019.vcxproj index 9eedbf30..b297efad 100644 --- a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2019.vcxproj +++ b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2022.vcxproj b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2022.vcxproj index 94c05285..28997ae9 100644 --- a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2022.vcxproj +++ b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/deviceQuery/Makefile b/Samples/1_Utilities/deviceQuery/Makefile index c1f2ab45..89446f20 100644 --- a/Samples/1_Utilities/deviceQuery/Makefile +++ b/Samples/1_Utilities/deviceQuery/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/1_Utilities/deviceQuery/README.md b/Samples/1_Utilities/deviceQuery/README.md index a21c297f..cce64760 100644 --- a/Samples/1_Utilities/deviceQuery/README.md +++ b/Samples/1_Utilities/deviceQuery/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaGetErrorString, cudaDeviceCanAccessPeer, cudaSetDevic ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2017.vcxproj b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2017.vcxproj index 115deff4..a3af850e 100644 --- a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2017.vcxproj +++ b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2019.vcxproj b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2019.vcxproj index 5fd4e6d6..2da4aff8 100644 --- a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2019.vcxproj +++ b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2022.vcxproj b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2022.vcxproj index e29d50b4..e7686820 100644 --- a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2022.vcxproj +++ b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/deviceQueryDrv/Makefile b/Samples/1_Utilities/deviceQueryDrv/Makefile index a99867d4..a5305e22 100644 --- a/Samples/1_Utilities/deviceQueryDrv/Makefile +++ b/Samples/1_Utilities/deviceQueryDrv/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/1_Utilities/deviceQueryDrv/README.md b/Samples/1_Utilities/deviceQueryDrv/README.md index 75bbdb7a..e71a2c74 100644 --- a/Samples/1_Utilities/deviceQueryDrv/README.md +++ b/Samples/1_Utilities/deviceQueryDrv/README.md @@ -30,7 +30,7 @@ cudaSetDevice ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2017.vcxproj b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2017.vcxproj index 1cf2343b..8dce62cb 100644 --- a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2017.vcxproj +++ b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2019.vcxproj b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2019.vcxproj index eae85136..6fc82222 100644 --- a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2019.vcxproj +++ b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2022.vcxproj b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2022.vcxproj index 8295af48..494cd796 100644 --- a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2022.vcxproj +++ b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/topologyQuery/Makefile b/Samples/1_Utilities/topologyQuery/Makefile index ff050adf..4c3ee47e 100644 --- a/Samples/1_Utilities/topologyQuery/Makefile +++ b/Samples/1_Utilities/topologyQuery/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/1_Utilities/topologyQuery/README.md b/Samples/1_Utilities/topologyQuery/README.md index abc31e63..6f0c48e8 100644 --- a/Samples/1_Utilities/topologyQuery/README.md +++ b/Samples/1_Utilities/topologyQuery/README.md @@ -27,7 +27,7 @@ cudaGetDeviceCount, cudaDeviceGetAttribute ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2017.vcxproj b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2017.vcxproj index 4d1e149e..d7accfa5 100644 --- a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2017.vcxproj +++ b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2019.vcxproj b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2019.vcxproj index 8ec1ecd3..be5ffb30 100644 --- a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2019.vcxproj +++ b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2022.vcxproj b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2022.vcxproj index 882066db..19969769 100644 --- a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2022.vcxproj +++ b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/Makefile b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/Makefile index 178e8458..19bb6649 100644 --- a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/Makefile +++ b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/README.md b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/README.md index 49768f8c..d753a314 100644 --- a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/README.md +++ b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaMalloc, cudaProducerPresentFrame, cudaFree, cudaGetErrorString, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/Makefile b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/Makefile index c70bcc3b..d061a588 100644 --- a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/Makefile +++ b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/README.md b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/README.md index d7e93891..3dda94de 100644 --- a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/README.md +++ b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/README.md @@ -33,7 +33,7 @@ cudaProducerReadYUVFrame, cudaProducerTest, cudaProducerDeinit, cudaDeviceCreate ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/Makefile b/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/Makefile index 0241761a..f4384df1 100644 --- a/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/Makefile +++ b/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/README.md b/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/README.md index 71780f87..9668be56 100644 --- a/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/README.md +++ b/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaDeviceSynchronize, cudaGetValueMis ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2017.vcxproj index 54064e64..cb7a6cff 100644 --- a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2019.vcxproj index 5b17e0d6..b05ac540 100644 --- a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2022.vcxproj index 5e90a300..786a0159 100644 --- a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/FunctionPointers/Makefile b/Samples/2_Concepts_and_Techniques/FunctionPointers/Makefile index e7b1ebab..62e075d9 100644 --- a/Samples/2_Concepts_and_Techniques/FunctionPointers/Makefile +++ b/Samples/2_Concepts_and_Techniques/FunctionPointers/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/FunctionPointers/README.md b/Samples/2_Concepts_and_Techniques/FunctionPointers/README.md index bd5f9ebc..883676df 100644 --- a/Samples/2_Concepts_and_Techniques/FunctionPointers/README.md +++ b/Samples/2_Concepts_and_Techniques/FunctionPointers/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2017.vcxproj index 00448128..c0e3a3d3 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2019.vcxproj index e0ff27e7..1111fea7 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2022.vcxproj index baecaf80..13c12d12 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/Makefile b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/Makefile index ebb1ba53..7287ec6a 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/Makefile +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/README.md b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/README.md index d9bd5496..e534a2af 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/README.md +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaSetDevice, cudaGetDeviceCount, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2017.vcxproj index dc8b864b..112f2f96 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2019.vcxproj index 3966e3e2..6dd7acd1 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2022.vcxproj index b0076d1d..2b780145 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/Makefile b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/Makefile index cbef9171..8725a325 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/Makefile +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/README.md b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/README.md index 18edc893..7de22e0c 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/README.md +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaSetDevice, cudaGetDeviceCount, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2017.vcxproj index 6831478f..de2f2ffd 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2019.vcxproj index 82e2de5e..fca132d8 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2022.vcxproj index 88b2c63e..09bdd5d9 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/Makefile b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/Makefile index 9baf49b5..7f921e79 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/Makefile +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/README.md b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/README.md index 51cc0299..43c16ba4 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/README.md +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaSetDevice, cudaGetDeviceCount, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2017.vcxproj index fb05b83c..378dac27 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2019.vcxproj index d3d6c035..23c30ef7 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2022.vcxproj index d9623eb5..ff376500 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/Makefile b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/Makefile index 9a2f2d3a..40c89515 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/Makefile +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/README.md b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/README.md index 5855ec67..a26ae785 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/README.md +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaSetDevice, cudaGetDeviceCount, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2017.vcxproj index 6172e5a6..399b3422 100644 --- a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2019.vcxproj index b5fb4530..812091d7 100644 --- a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2022.vcxproj index 1e14b94d..89d23c01 100644 --- a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/Makefile b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/Makefile index 85eacfd1..860f5779 100644 --- a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/Makefile +++ b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/README.md b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/README.md index 147b8c0e..4984ce2a 100644 --- a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/README.md +++ b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaSetDevice, cudaGetDeviceCount, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/boxFilter/Makefile b/Samples/2_Concepts_and_Techniques/boxFilter/Makefile index 09ae6e24..1f4275f8 100644 --- a/Samples/2_Concepts_and_Techniques/boxFilter/Makefile +++ b/Samples/2_Concepts_and_Techniques/boxFilter/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/boxFilter/README.md b/Samples/2_Concepts_and_Techniques/boxFilter/README.md index cd7e5737..9ed5b0e4 100644 --- a/Samples/2_Concepts_and_Techniques/boxFilter/README.md +++ b/Samples/2_Concepts_and_Techniques/boxFilter/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaCreateChannelDesc, cudaMallocArray, cudaFreeArra ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2017.vcxproj index 2ca9d0e2..a6e28e9b 100644 --- a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2019.vcxproj index 15e20ab6..9674a20e 100644 --- a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -115,6 +115,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2022.vcxproj index 2d57f772..97e9675a 100644 --- a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -115,6 +115,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionSeparable/Makefile b/Samples/2_Concepts_and_Techniques/convolutionSeparable/Makefile index 781fb328..baca6908 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionSeparable/Makefile +++ b/Samples/2_Concepts_and_Techniques/convolutionSeparable/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/convolutionSeparable/README.md b/Samples/2_Concepts_and_Techniques/convolutionSeparable/README.md index f7cb1045..c79eb31a 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionSeparable/README.md +++ b/Samples/2_Concepts_and_Techniques/convolutionSeparable/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMemcpyToSymbol, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2017.vcxproj index 7f2abb7a..51d47a0c 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2019.vcxproj index 51bfba1a..29479be7 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2022.vcxproj index 8b59e3e8..fe26e001 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionTexture/Makefile b/Samples/2_Concepts_and_Techniques/convolutionTexture/Makefile index f2b678b6..ad059e93 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionTexture/Makefile +++ b/Samples/2_Concepts_and_Techniques/convolutionTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/convolutionTexture/README.md b/Samples/2_Concepts_and_Techniques/convolutionTexture/README.md index 773a30d0..5e5ffb26 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionTexture/README.md +++ b/Samples/2_Concepts_and_Techniques/convolutionTexture/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree, cudaMemcpyToArray, cudaDev ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2017.vcxproj index e73eefb6..29d9c841 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2019.vcxproj index e7d49b94..975a15ca 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2022.vcxproj index 07a46bcf..d962dd89 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/cuHook/Makefile b/Samples/2_Concepts_and_Techniques/cuHook/Makefile index 9f0cf2f8..9ccdd509 100644 --- a/Samples/2_Concepts_and_Techniques/cuHook/Makefile +++ b/Samples/2_Concepts_and_Techniques/cuHook/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/cuHook/README.md b/Samples/2_Concepts_and_Techniques/cuHook/README.md index 3139a554..7427c465 100644 --- a/Samples/2_Concepts_and_Techniques/cuHook/README.md +++ b/Samples/2_Concepts_and_Techniques/cuHook/README.md @@ -32,7 +32,7 @@ cudaDeviceReset, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/dct8x8/Makefile b/Samples/2_Concepts_and_Techniques/dct8x8/Makefile index 285446d0..181007c9 100644 --- a/Samples/2_Concepts_and_Techniques/dct8x8/Makefile +++ b/Samples/2_Concepts_and_Techniques/dct8x8/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/dct8x8/README.md b/Samples/2_Concepts_and_Techniques/dct8x8/README.md index a9b76320..22ee2698 100644 --- a/Samples/2_Concepts_and_Techniques/dct8x8/README.md +++ b/Samples/2_Concepts_and_Techniques/dct8x8/README.md @@ -27,7 +27,7 @@ cudaMallocArray, cudaFreeArray, cudaFree, cudaMallocPitch, cudaDestroyTextureObj ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2017.vcxproj index de5ff96d..a9725ce1 100644 --- a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -115,6 +115,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2019.vcxproj index 1b6c3019..c3b57f43 100644 --- a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2022.vcxproj index c45920a0..b768ea11 100644 --- a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/eigenvalues/Makefile b/Samples/2_Concepts_and_Techniques/eigenvalues/Makefile index 67505f65..560b4a4e 100644 --- a/Samples/2_Concepts_and_Techniques/eigenvalues/Makefile +++ b/Samples/2_Concepts_and_Techniques/eigenvalues/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/eigenvalues/README.md b/Samples/2_Concepts_and_Techniques/eigenvalues/README.md index 7f5e05cf..235fac21 100644 --- a/Samples/2_Concepts_and_Techniques/eigenvalues/README.md +++ b/Samples/2_Concepts_and_Techniques/eigenvalues/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2017.vcxproj index 197d0ba5..3a64c938 100644 --- a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -122,6 +122,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2019.vcxproj index 105d42b1..c0cdb058 100644 --- a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2022.vcxproj index f73eb0d1..b400c36a 100644 --- a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/histogram/Makefile b/Samples/2_Concepts_and_Techniques/histogram/Makefile index 0aff0de0..6d85b831 100644 --- a/Samples/2_Concepts_and_Techniques/histogram/Makefile +++ b/Samples/2_Concepts_and_Techniques/histogram/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/histogram/README.md b/Samples/2_Concepts_and_Techniques/histogram/README.md index accddad9..a6088c65 100644 --- a/Samples/2_Concepts_and_Techniques/histogram/README.md +++ b/Samples/2_Concepts_and_Techniques/histogram/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2017.vcxproj index 99ec61c1..2aaf05f5 100644 --- a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2019.vcxproj index c88213d2..d8d3088f 100644 --- a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2022.vcxproj index d271430f..200790fe 100644 --- a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/imageDenoising/Makefile b/Samples/2_Concepts_and_Techniques/imageDenoising/Makefile index ecbf667d..00f062c2 100644 --- a/Samples/2_Concepts_and_Techniques/imageDenoising/Makefile +++ b/Samples/2_Concepts_and_Techniques/imageDenoising/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/imageDenoising/README.md b/Samples/2_Concepts_and_Techniques/imageDenoising/README.md index 967440ed..9242b34f 100644 --- a/Samples/2_Concepts_and_Techniques/imageDenoising/README.md +++ b/Samples/2_Concepts_and_Techniques/imageDenoising/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2017.vcxproj index eef04d37..4c3ad411 100644 --- a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -123,6 +123,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2019.vcxproj index 5c35ac7b..7ec5d28a 100644 --- a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2022.vcxproj index 67dcf534..2fd97ad9 100644 --- a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX/Makefile b/Samples/2_Concepts_and_Techniques/inlinePTX/Makefile index d05a24d2..e2d4c251 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX/Makefile +++ b/Samples/2_Concepts_and_Techniques/inlinePTX/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX/README.md b/Samples/2_Concepts_and_Techniques/inlinePTX/README.md index 60c7b0f2..2760047c 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX/README.md +++ b/Samples/2_Concepts_and_Techniques/inlinePTX/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaMallocHost, cudaGetLastError, cudaGridSize, cudaBlockS ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2017.vcxproj index 5ff4b037..13a492e0 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2019.vcxproj index dd8c00c2..614f178a 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2022.vcxproj index 55bba92a..505f4e81 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/Makefile b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/Makefile index 291d4854..c358fb0b 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/Makefile +++ b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/README.md b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/README.md index 78a27257..6e535bd5 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/README.md +++ b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2017.vcxproj index 1ebd81ca..0ea3ea6e 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2019.vcxproj index 1583691c..7563d019 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2022.vcxproj index d8965838..62ce6a5d 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/interval/Makefile b/Samples/2_Concepts_and_Techniques/interval/Makefile index 9e369a5d..b2e314c7 100644 --- a/Samples/2_Concepts_and_Techniques/interval/Makefile +++ b/Samples/2_Concepts_and_Techniques/interval/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/interval/README.md b/Samples/2_Concepts_and_Techniques/interval/README.md index 65498b66..9eafdaba 100644 --- a/Samples/2_Concepts_and_Techniques/interval/README.md +++ b/Samples/2_Concepts_and_Techniques/interval/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFuncSetCacheConfig, cudaMalloc, cudaFree, cudaGetLastError, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/interval/interval_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/interval/interval_vs2017.vcxproj index cabde889..a351db75 100644 --- a/Samples/2_Concepts_and_Techniques/interval/interval_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/interval/interval_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -213,6 +213,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/interval/interval_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/interval/interval_vs2019.vcxproj index 2cb000aa..40bc8ee0 100644 --- a/Samples/2_Concepts_and_Techniques/interval/interval_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/interval/interval_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -209,6 +209,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/interval/interval_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/interval/interval_vs2022.vcxproj index 2d37616b..e84d4017 100644 --- a/Samples/2_Concepts_and_Techniques/interval/interval_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/interval/interval_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -209,6 +209,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/particles/Makefile b/Samples/2_Concepts_and_Techniques/particles/Makefile index 5da2007a..f45b0588 100644 --- a/Samples/2_Concepts_and_Techniques/particles/Makefile +++ b/Samples/2_Concepts_and_Techniques/particles/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/particles/README.md b/Samples/2_Concepts_and_Techniques/particles/README.md index da3453b6..f86cac02 100644 --- a/Samples/2_Concepts_and_Techniques/particles/README.md +++ b/Samples/2_Concepts_and_Techniques/particles/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/particles/particles_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/particles/particles_vs2017.vcxproj index f9bb1f46..d3ae2eff 100644 --- a/Samples/2_Concepts_and_Techniques/particles/particles_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/particles/particles_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -129,6 +129,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/particles/particles_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/particles/particles_vs2019.vcxproj index 97d4bc7d..f96d4a30 100644 --- a/Samples/2_Concepts_and_Techniques/particles/particles_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/particles/particles_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -125,6 +125,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/particles/particles_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/particles/particles_vs2022.vcxproj index 00f0b6de..49b56ad1 100644 --- a/Samples/2_Concepts_and_Techniques/particles/particles_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/particles/particles_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -125,6 +125,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/radixSortThrust/Makefile b/Samples/2_Concepts_and_Techniques/radixSortThrust/Makefile index 92be51ab..503eecc7 100644 --- a/Samples/2_Concepts_and_Techniques/radixSortThrust/Makefile +++ b/Samples/2_Concepts_and_Techniques/radixSortThrust/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/radixSortThrust/README.md b/Samples/2_Concepts_and_Techniques/radixSortThrust/README.md index f4b01c26..2ffa76f2 100644 --- a/Samples/2_Concepts_and_Techniques/radixSortThrust/README.md +++ b/Samples/2_Concepts_and_Techniques/radixSortThrust/README.md @@ -27,7 +27,7 @@ cudaEventSynchronize, cudaEventRecord, cudaGetDevice, cudaEventDestroy, cudaEven ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2017.vcxproj index 53fee37c..07d1e44b 100644 --- a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2019.vcxproj index 8812d1f7..abee20c7 100644 --- a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2022.vcxproj index a9fd806e..a8c87aa1 100644 --- a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reduction/Makefile b/Samples/2_Concepts_and_Techniques/reduction/Makefile index 8ec8d635..297c1e47 100644 --- a/Samples/2_Concepts_and_Techniques/reduction/Makefile +++ b/Samples/2_Concepts_and_Techniques/reduction/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/reduction/README.md b/Samples/2_Concepts_and_Techniques/reduction/README.md index 5bb81f5b..ac916704 100644 --- a/Samples/2_Concepts_and_Techniques/reduction/README.md +++ b/Samples/2_Concepts_and_Techniques/reduction/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaSetDevice, cudaDeviceSynchronize, cudaGetDevice, cudaM ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2017.vcxproj index 972b6588..fc77c7ce 100644 --- a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2019.vcxproj index a35184ce..265821a8 100644 --- a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2022.vcxproj index 6cd327dc..a9ed5d63 100644 --- a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/Makefile b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/Makefile index eaaf0c2f..d86bffa0 100644 --- a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/Makefile +++ b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/README.md b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/README.md index 0383fdde..706766aa 100644 --- a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/README.md +++ b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaSetDevice, cudaDeviceSynchronize, cudaLaunchCooperativ ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2017.vcxproj index 1ecfd78d..7ae7db26 100644 --- a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2019.vcxproj index 0368b554..b14e94ab 100644 --- a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2022.vcxproj index 186cecd9..6880c059 100644 --- a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scalarProd/Makefile b/Samples/2_Concepts_and_Techniques/scalarProd/Makefile index 316337e7..7ed7d15a 100644 --- a/Samples/2_Concepts_and_Techniques/scalarProd/Makefile +++ b/Samples/2_Concepts_and_Techniques/scalarProd/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/scalarProd/README.md b/Samples/2_Concepts_and_Techniques/scalarProd/README.md index 28761f4b..139d1ca0 100644 --- a/Samples/2_Concepts_and_Techniques/scalarProd/README.md +++ b/Samples/2_Concepts_and_Techniques/scalarProd/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2017.vcxproj index e543b834..21a49a06 100644 --- a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2019.vcxproj index 8f601364..11eafdeb 100644 --- a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2022.vcxproj index 3fb523af..684470fb 100644 --- a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scan/Makefile b/Samples/2_Concepts_and_Techniques/scan/Makefile index 20a84991..5a98f27c 100644 --- a/Samples/2_Concepts_and_Techniques/scan/Makefile +++ b/Samples/2_Concepts_and_Techniques/scan/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/scan/README.md b/Samples/2_Concepts_and_Techniques/scan/README.md index f238733c..5db006d3 100644 --- a/Samples/2_Concepts_and_Techniques/scan/README.md +++ b/Samples/2_Concepts_and_Techniques/scan/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/scan/scan_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/scan/scan_vs2017.vcxproj index 92989700..8bb47bad 100644 --- a/Samples/2_Concepts_and_Techniques/scan/scan_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scan/scan_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scan/scan_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/scan/scan_vs2019.vcxproj index b7dc4323..e5b883a7 100644 --- a/Samples/2_Concepts_and_Techniques/scan/scan_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scan/scan_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scan/scan_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/scan/scan_vs2022.vcxproj index eeb05f2e..f2d6c8b8 100644 --- a/Samples/2_Concepts_and_Techniques/scan/scan_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scan/scan_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/Makefile b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/Makefile index 8befa5f5..d4f259a4 100644 --- a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/Makefile +++ b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/README.md b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/README.md index 84093d06..1959b9a8 100644 --- a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/README.md +++ b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaMemGetInfo, cudaEventSynchronize, cudaEventRecord, cudaMemset, c ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2017.vcxproj index e1ae6ca8..574587fe 100644 --- a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2019.vcxproj index 25844764..9e2b5210 100644 --- a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2022.vcxproj index 14237327..5e4c219f 100644 --- a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/shfl_scan/Makefile b/Samples/2_Concepts_and_Techniques/shfl_scan/Makefile index 627a2bc4..df10b672 100644 --- a/Samples/2_Concepts_and_Techniques/shfl_scan/Makefile +++ b/Samples/2_Concepts_and_Techniques/shfl_scan/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/shfl_scan/README.md b/Samples/2_Concepts_and_Techniques/shfl_scan/README.md index 12cb7c58..8d04c940 100644 --- a/Samples/2_Concepts_and_Techniques/shfl_scan/README.md +++ b/Samples/2_Concepts_and_Techniques/shfl_scan/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaFree, cudaMallocHost, cudaEventSynchronize, cudaEventRecord, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2017.vcxproj index 7df3fe37..219eb2eb 100644 --- a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2019.vcxproj index 37df0fe3..7c282184 100644 --- a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2022.vcxproj index 9464b380..bc515779 100644 --- a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/sortingNetworks/Makefile b/Samples/2_Concepts_and_Techniques/sortingNetworks/Makefile index 9e8e0b57..8b88373e 100644 --- a/Samples/2_Concepts_and_Techniques/sortingNetworks/Makefile +++ b/Samples/2_Concepts_and_Techniques/sortingNetworks/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/sortingNetworks/README.md b/Samples/2_Concepts_and_Techniques/sortingNetworks/README.md index c23943cd..1b100131 100644 --- a/Samples/2_Concepts_and_Techniques/sortingNetworks/README.md +++ b/Samples/2_Concepts_and_Techniques/sortingNetworks/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2017.vcxproj index 5d05456f..8d625e4f 100644 --- a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2019.vcxproj index 961caf42..65834bc5 100644 --- a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2022.vcxproj index dfa17e1e..90191737 100644 --- a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/Makefile b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/Makefile index b551270f..9611c8f2 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/Makefile +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/README.md b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/README.md index 05d3b3c8..a93e1121 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/README.md +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/README.md @@ -27,7 +27,7 @@ cudaDeviceGetDefaultMemPool, cudaFreeAsync, cudaStreamCreateWithFlags, cudaStrea ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2017.vcxproj index ab20053e..31f3d7d4 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2019.vcxproj index 91e4c4d4..343b5af4 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2022.vcxproj index 27021701..d3a4fdaf 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/Makefile b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/Makefile index 37d08561..dfe39104 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/Makefile +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/README.md b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/README.md index 625d637b..e6633880 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/README.md +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/README.md @@ -30,7 +30,7 @@ cudaDeviceGetAttribute, cudaMemPoolImportFromShareableHandle, cudaSetDevice, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/Makefile b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/Makefile index 532ef73f..9115e953 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/Makefile +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/README.md b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/README.md index 9736488a..775bc09b 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/README.md +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/README.md @@ -27,7 +27,7 @@ cudaDeviceGetDefaultMemPool, cudaFreeAsync, cudaStreamCreateWithFlags, cudaMemPo ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2017.vcxproj index a1e20527..701b8efa 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2019.vcxproj index e7d30501..a662490b 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2022.vcxproj index 12e5fa5a..bb9274fe 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadFenceReduction/Makefile b/Samples/2_Concepts_and_Techniques/threadFenceReduction/Makefile index 5f4646b1..58a1f676 100644 --- a/Samples/2_Concepts_and_Techniques/threadFenceReduction/Makefile +++ b/Samples/2_Concepts_and_Techniques/threadFenceReduction/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/threadFenceReduction/README.md b/Samples/2_Concepts_and_Techniques/threadFenceReduction/README.md index 36af664d..15c1f3e7 100644 --- a/Samples/2_Concepts_and_Techniques/threadFenceReduction/README.md +++ b/Samples/2_Concepts_and_Techniques/threadFenceReduction/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2017.vcxproj index 116b3f08..c554d152 100644 --- a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2019.vcxproj index 40f1241b..5a223653 100644 --- a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2022.vcxproj index 88b7d1b7..40dbf185 100644 --- a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadMigration/Makefile b/Samples/2_Concepts_and_Techniques/threadMigration/Makefile index d7e735bc..f3d42a2a 100644 --- a/Samples/2_Concepts_and_Techniques/threadMigration/Makefile +++ b/Samples/2_Concepts_and_Techniques/threadMigration/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/threadMigration/README.md b/Samples/2_Concepts_and_Techniques/threadMigration/README.md index 00562b43..89357423 100644 --- a/Samples/2_Concepts_and_Techniques/threadMigration/README.md +++ b/Samples/2_Concepts_and_Techniques/threadMigration/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuModuleLoadData, cuDeviceGetName, cuDeviceGet, cu ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2017.vcxproj index ec306a40..9268bf34 100644 --- a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2019.vcxproj index d569019f..7a0f24a9 100644 --- a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2022.vcxproj index 265cfeaf..5de98212 100644 --- a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/StreamPriorities/Makefile b/Samples/3_CUDA_Features/StreamPriorities/Makefile index 5083641e..36fdbc14 100644 --- a/Samples/3_CUDA_Features/StreamPriorities/Makefile +++ b/Samples/3_CUDA_Features/StreamPriorities/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/StreamPriorities/README.md b/Samples/3_CUDA_Features/StreamPriorities/README.md index 6e634cc1..1657bddf 100644 --- a/Samples/3_CUDA_Features/StreamPriorities/README.md +++ b/Samples/3_CUDA_Features/StreamPriorities/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaStreamCreateWithPriority, cudaDeviceGetStreamPriorityRange, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/bf16TensorCoreGemm/Makefile b/Samples/3_CUDA_Features/bf16TensorCoreGemm/Makefile index 6fa432f3..bd3bd57d 100644 --- a/Samples/3_CUDA_Features/bf16TensorCoreGemm/Makefile +++ b/Samples/3_CUDA_Features/bf16TensorCoreGemm/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/bf16TensorCoreGemm/README.md b/Samples/3_CUDA_Features/bf16TensorCoreGemm/README.md index 08f90795..9f72eebe 100644 --- a/Samples/3_CUDA_Features/bf16TensorCoreGemm/README.md +++ b/Samples/3_CUDA_Features/bf16TensorCoreGemm/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2017.vcxproj b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2017.vcxproj index 8a417b82..42c52f3a 100644 --- a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2019.vcxproj b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2019.vcxproj index 76f95d03..aed75387 100644 --- a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2022.vcxproj b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2022.vcxproj index 3ef22781..decbc4da 100644 --- a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/binaryPartitionCG/Makefile b/Samples/3_CUDA_Features/binaryPartitionCG/Makefile index 5cbfd13d..076405a8 100644 --- a/Samples/3_CUDA_Features/binaryPartitionCG/Makefile +++ b/Samples/3_CUDA_Features/binaryPartitionCG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/binaryPartitionCG/README.md b/Samples/3_CUDA_Features/binaryPartitionCG/README.md index ff46f83b..1b26aec5 100644 --- a/Samples/3_CUDA_Features/binaryPartitionCG/README.md +++ b/Samples/3_CUDA_Features/binaryPartitionCG/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaFree, cudaMallocHost, cudaFreeHost, cudaStreamSyn ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2017.vcxproj b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2017.vcxproj index 284bdda1..de633f56 100644 --- a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2019.vcxproj b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2019.vcxproj index 218f5385..dd6c16ca 100644 --- a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2022.vcxproj b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2022.vcxproj index b6971e40..f8e04a5b 100644 --- a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/bindlessTexture/Makefile b/Samples/3_CUDA_Features/bindlessTexture/Makefile index 43672676..5dacf277 100644 --- a/Samples/3_CUDA_Features/bindlessTexture/Makefile +++ b/Samples/3_CUDA_Features/bindlessTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/bindlessTexture/README.md b/Samples/3_CUDA_Features/bindlessTexture/README.md index 2fe6af3f..18414d86 100644 --- a/Samples/3_CUDA_Features/bindlessTexture/README.md +++ b/Samples/3_CUDA_Features/bindlessTexture/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaGetMipmappedArrayLevel, cudaGraphicsMapResources, cudaDestroySur ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2017.vcxproj b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2017.vcxproj index 646b9c92..0705c0b8 100644 --- a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2019.vcxproj b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2019.vcxproj index b602feb7..83ecf371 100644 --- a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2022.vcxproj b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2022.vcxproj index c6ef32c2..21287f55 100644 --- a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/Makefile b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/Makefile index 7ad291ba..ddba4038 100644 --- a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/Makefile +++ b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/README.md b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/README.md index a0c1d2ee..843cff41 100644 --- a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/README.md +++ b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/README.md @@ -28,7 +28,7 @@ cudaStreamCreateWithFlags, cudaMemcpy, cudaMemcpyAsync, cudaFree, cudaGetErrorSt ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2017.vcxproj b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2017.vcxproj index 1265858b..19930bf5 100644 --- a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2019.vcxproj b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2019.vcxproj index 0edcea44..072d1d9f 100644 --- a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2022.vcxproj b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2022.vcxproj index 4c0a0eed..2fb87778 100644 --- a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpBezierTessellation/Makefile b/Samples/3_CUDA_Features/cdpBezierTessellation/Makefile index 470f8622..08b4c3f3 100644 --- a/Samples/3_CUDA_Features/cdpBezierTessellation/Makefile +++ b/Samples/3_CUDA_Features/cdpBezierTessellation/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cdpBezierTessellation/README.md b/Samples/3_CUDA_Features/cdpBezierTessellation/README.md index aba89c4d..2b3cc6cb 100644 --- a/Samples/3_CUDA_Features/cdpBezierTessellation/README.md +++ b/Samples/3_CUDA_Features/cdpBezierTessellation/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaFree, cudaGetDeviceCount, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2017.vcxproj b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2017.vcxproj index 60104969..be39cd4e 100644 --- a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2019.vcxproj b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2019.vcxproj index 73583e9e..52bc6f32 100644 --- a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2022.vcxproj b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2022.vcxproj index 718b47a2..d5788874 100644 --- a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpQuadtree/Makefile b/Samples/3_CUDA_Features/cdpQuadtree/Makefile index 0a08289b..f3924409 100644 --- a/Samples/3_CUDA_Features/cdpQuadtree/Makefile +++ b/Samples/3_CUDA_Features/cdpQuadtree/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cdpQuadtree/README.md b/Samples/3_CUDA_Features/cdpQuadtree/README.md index 86c37ced..13fc0f3f 100644 --- a/Samples/3_CUDA_Features/cdpQuadtree/README.md +++ b/Samples/3_CUDA_Features/cdpQuadtree/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaFree, cudaGetLastError, cudaDeviceSetLimit, cudaMalloc, cudaGetD ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2017.vcxproj b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2017.vcxproj index f99f787d..2b3a9765 100644 --- a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2019.vcxproj b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2019.vcxproj index 7a06bca8..29419939 100644 --- a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2022.vcxproj b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2022.vcxproj index 6354943a..72c46482 100644 --- a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimplePrint/Makefile b/Samples/3_CUDA_Features/cdpSimplePrint/Makefile index 67f6ebcb..b3618196 100644 --- a/Samples/3_CUDA_Features/cdpSimplePrint/Makefile +++ b/Samples/3_CUDA_Features/cdpSimplePrint/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cdpSimplePrint/README.md b/Samples/3_CUDA_Features/cdpSimplePrint/README.md index e0a4b857..e975d689 100644 --- a/Samples/3_CUDA_Features/cdpSimplePrint/README.md +++ b/Samples/3_CUDA_Features/cdpSimplePrint/README.md @@ -28,7 +28,7 @@ cudaDeviceSynchronize, cudaGetLastError, cudaGetDeviceProperties, cudaDeviceSetL ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2017.vcxproj b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2017.vcxproj index 49b9beb5..7d5b3cab 100644 --- a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2019.vcxproj b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2019.vcxproj index 2246a2e0..0cb3dca1 100644 --- a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2022.vcxproj b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2022.vcxproj index 3cee6542..724c2244 100644 --- a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimpleQuicksort/Makefile b/Samples/3_CUDA_Features/cdpSimpleQuicksort/Makefile index 882d5f4b..e1901094 100644 --- a/Samples/3_CUDA_Features/cdpSimpleQuicksort/Makefile +++ b/Samples/3_CUDA_Features/cdpSimpleQuicksort/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cdpSimpleQuicksort/README.md b/Samples/3_CUDA_Features/cdpSimpleQuicksort/README.md index a5366db1..a4aa7761 100644 --- a/Samples/3_CUDA_Features/cdpSimpleQuicksort/README.md +++ b/Samples/3_CUDA_Features/cdpSimpleQuicksort/README.md @@ -28,7 +28,7 @@ cudaStreamCreateWithFlags, cudaMemcpy, cudaStreamDestroy, cudaFree, cudaDeviceSy ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2017.vcxproj b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2017.vcxproj index 492b07b8..bbd3960a 100644 --- a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2019.vcxproj b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2019.vcxproj index 821d377e..3a327e4c 100644 --- a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2022.vcxproj b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2022.vcxproj index 9fe6560e..e6cd2990 100644 --- a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaCompressibleMemory/Makefile b/Samples/3_CUDA_Features/cudaCompressibleMemory/Makefile index 6504cea1..382e7d06 100644 --- a/Samples/3_CUDA_Features/cudaCompressibleMemory/Makefile +++ b/Samples/3_CUDA_Features/cudaCompressibleMemory/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cudaCompressibleMemory/README.md b/Samples/3_CUDA_Features/cudaCompressibleMemory/README.md index 504ddf3a..a223d3c5 100644 --- a/Samples/3_CUDA_Features/cudaCompressibleMemory/README.md +++ b/Samples/3_CUDA_Features/cudaCompressibleMemory/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaEventSynchronize, cudaEventRecord, cudaEventElapsedTime, cudaOcc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2017.vcxproj b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2017.vcxproj index db1e33a2..44adc75b 100644 --- a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2019.vcxproj b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2019.vcxproj index a63f55e6..f6adc4fe 100644 --- a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2022.vcxproj b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2022.vcxproj index 9673006c..0a11b00e 100644 --- a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaTensorCoreGemm/Makefile b/Samples/3_CUDA_Features/cudaTensorCoreGemm/Makefile index 9e9f26a7..fe0d35a5 100644 --- a/Samples/3_CUDA_Features/cudaTensorCoreGemm/Makefile +++ b/Samples/3_CUDA_Features/cudaTensorCoreGemm/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cudaTensorCoreGemm/README.md b/Samples/3_CUDA_Features/cudaTensorCoreGemm/README.md index 98d6aedc..e89c6d0a 100644 --- a/Samples/3_CUDA_Features/cudaTensorCoreGemm/README.md +++ b/Samples/3_CUDA_Features/cudaTensorCoreGemm/README.md @@ -31,7 +31,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2017.vcxproj b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2017.vcxproj index af507379..511eabfd 100644 --- a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2019.vcxproj b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2019.vcxproj index 55a737c7..dfdb635e 100644 --- a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2022.vcxproj b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2022.vcxproj index 3d7d79ed..23be7cbe 100644 --- a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/Makefile b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/Makefile index 134a0759..a1fd5b5e 100644 --- a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/Makefile +++ b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/README.md b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/README.md index cee17b9e..2320afba 100644 --- a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/README.md +++ b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2017.vcxproj b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2017.vcxproj index 0a99ba5e..e8fc315f 100644 --- a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2019.vcxproj b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2019.vcxproj index 1eab00a4..b514747a 100644 --- a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2022.vcxproj b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2022.vcxproj index d1ffc909..7c2d8d63 100644 --- a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/Makefile b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/Makefile index 3c92e0e8..a7e77128 100644 --- a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/Makefile +++ b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/README.md b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/README.md index 1e771697..807d0e34 100644 --- a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/README.md +++ b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/README.md @@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaMalloc, cudaDeviceGetAttribute, cudaFree, cudaMal ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2017.vcxproj b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2017.vcxproj index 0da843f6..59465e73 100644 --- a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2019.vcxproj b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2019.vcxproj index 5726eec7..ab59f6df 100644 --- a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2022.vcxproj b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2022.vcxproj index c7a38b13..961bf1bc 100644 --- a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphConditionalNodes/Makefile b/Samples/3_CUDA_Features/graphConditionalNodes/Makefile index d32d3432..e7b0ae9f 100644 --- a/Samples/3_CUDA_Features/graphConditionalNodes/Makefile +++ b/Samples/3_CUDA_Features/graphConditionalNodes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/graphConditionalNodes/README.md b/Samples/3_CUDA_Features/graphConditionalNodes/README.md index a67268b6..8fd835cb 100644 --- a/Samples/3_CUDA_Features/graphConditionalNodes/README.md +++ b/Samples/3_CUDA_Features/graphConditionalNodes/README.md @@ -27,7 +27,7 @@ cudaDeviceSynchronize, cudaDriverGetVersion, cudaFree, cudaGraphAddNode, cudaGra ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2017.vcxproj b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2017.vcxproj index 67ba0b34..09578ddf 100644 --- a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2019.vcxproj b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2019.vcxproj index 63d2f354..648745f5 100644 --- a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2022.vcxproj b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2022.vcxproj index 06c23e44..13139435 100644 --- a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryFootprint/Makefile b/Samples/3_CUDA_Features/graphMemoryFootprint/Makefile index a65a991c..bbf756db 100644 --- a/Samples/3_CUDA_Features/graphMemoryFootprint/Makefile +++ b/Samples/3_CUDA_Features/graphMemoryFootprint/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/graphMemoryFootprint/README.md b/Samples/3_CUDA_Features/graphMemoryFootprint/README.md index 7bdd6fb1..7e0ffde4 100644 --- a/Samples/3_CUDA_Features/graphMemoryFootprint/README.md +++ b/Samples/3_CUDA_Features/graphMemoryFootprint/README.md @@ -27,7 +27,7 @@ cudaGraphAddMemAllocNode, cudaStreamCreateWithFlags, cudaGraphInstantiate, cudaS ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2017.vcxproj b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2017.vcxproj index 43ba1263..277241cd 100644 --- a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2019.vcxproj b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2019.vcxproj index 5d808b0b..314adf82 100644 --- a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2022.vcxproj b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2022.vcxproj index 8014d073..76a918a7 100644 --- a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryNodes/Makefile b/Samples/3_CUDA_Features/graphMemoryNodes/Makefile index 630e29a8..d90d79cb 100644 --- a/Samples/3_CUDA_Features/graphMemoryNodes/Makefile +++ b/Samples/3_CUDA_Features/graphMemoryNodes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/graphMemoryNodes/README.md b/Samples/3_CUDA_Features/graphMemoryNodes/README.md index bcde2bdd..1c993f6a 100644 --- a/Samples/3_CUDA_Features/graphMemoryNodes/README.md +++ b/Samples/3_CUDA_Features/graphMemoryNodes/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaDeviceGetAttribute, cudaDriverGetVersion, cudaGraphLaunch, cudaE ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2017.vcxproj b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2017.vcxproj index ecc8ed9a..254388cd 100644 --- a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2019.vcxproj b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2019.vcxproj index d194794c..80809dcd 100644 --- a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2022.vcxproj b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2022.vcxproj index e58656a4..cddca771 100644 --- a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/immaTensorCoreGemm/Makefile b/Samples/3_CUDA_Features/immaTensorCoreGemm/Makefile index ca600724..d8e65764 100644 --- a/Samples/3_CUDA_Features/immaTensorCoreGemm/Makefile +++ b/Samples/3_CUDA_Features/immaTensorCoreGemm/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/immaTensorCoreGemm/README.md b/Samples/3_CUDA_Features/immaTensorCoreGemm/README.md index df65de28..88f21201 100644 --- a/Samples/3_CUDA_Features/immaTensorCoreGemm/README.md +++ b/Samples/3_CUDA_Features/immaTensorCoreGemm/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2017.vcxproj b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2017.vcxproj index b97bf3d8..99ef813d 100644 --- a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2019.vcxproj b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2019.vcxproj index 9aeda604..7a5efa2e 100644 --- a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2022.vcxproj b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2022.vcxproj index 8155f810..71195f50 100644 --- a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/jacobiCudaGraphs/Makefile b/Samples/3_CUDA_Features/jacobiCudaGraphs/Makefile index ff0b63b0..b0fded60 100644 --- a/Samples/3_CUDA_Features/jacobiCudaGraphs/Makefile +++ b/Samples/3_CUDA_Features/jacobiCudaGraphs/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/jacobiCudaGraphs/README.md b/Samples/3_CUDA_Features/jacobiCudaGraphs/README.md index 9f0f24ad..0370d726 100644 --- a/Samples/3_CUDA_Features/jacobiCudaGraphs/README.md +++ b/Samples/3_CUDA_Features/jacobiCudaGraphs/README.md @@ -25,7 +25,7 @@ cudaExtent, cudaGraphLaunch, cudaGraphAddMemcpyNode, cudaMallocHost, cudaPitched ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2017.vcxproj b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2017.vcxproj index 4f4f19bb..6e236cb1 100644 --- a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2019.vcxproj b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2019.vcxproj index 5fff35e5..9f78ed56 100644 --- a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2022.vcxproj b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2022.vcxproj index a1dcc71c..a8982742 100644 --- a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/Makefile b/Samples/3_CUDA_Features/memMapIPCDrv/Makefile index 2ed35d4c..4bbaa725 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/Makefile +++ b/Samples/3_CUDA_Features/memMapIPCDrv/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/README.md b/Samples/3_CUDA_Features/memMapIPCDrv/README.md index 704c02a2..d15b4c92 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/README.md +++ b/Samples/3_CUDA_Features/memMapIPCDrv/README.md @@ -30,7 +30,7 @@ cuDeviceCanAccessPeer, cuMemImportFromShareableHandle, cuModuleLoadDataEx, cuMod ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2017.vcxproj b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2017.vcxproj index 6ec4f3e0..aeb0450b 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2019.vcxproj b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2019.vcxproj index 65f4dedc..31acef95 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2022.vcxproj b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2022.vcxproj index ae47cf79..5a370729 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIpc.cpp b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIpc.cpp index 19d6aa60..73cc6296 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIpc.cpp +++ b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIpc.cpp @@ -80,14 +80,14 @@ bool findModulePath(const char *, string &, char **, string &); // CU_MEM_HANDLE_TYPE_WIN32 meaning that NT HANDLEs will be used. The // ipcHandleTypeFlag variable is a convenience variable and is passed by value // to individual requests. -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) CUmemAllocationHandleType ipcHandleTypeFlag = CU_MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR; #else CUmemAllocationHandleType ipcHandleTypeFlag = CU_MEM_HANDLE_TYPE_WIN32; #endif -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) #define cpu_atomic_add32(a, x) __sync_add_and_fetch(a, x) #elif defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64) #define cpu_atomic_add32(a, x) InterlockedAdd((volatile LONG *)a, x) @@ -121,7 +121,7 @@ static void barrierWait(volatile int *barrier, volatile int *sense, // Windows-specific LPSECURITYATTRIBUTES void getDefaultSecurityDescriptor(CUmemAllocationProp *prop) { -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) return; #elif defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64) static const char sddl[] = "D:P(OA;;GARCSDWDWOCCDCLCSWLODTWPRPCRFA;;;WD)"; @@ -456,7 +456,7 @@ static void parentProcess(char *app) { checkCudaErrors(cuDeviceGetAttribute( &attributeVal, CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED, devices[i])); -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) checkCudaErrors(cuDeviceGetAttribute( &deviceSupportsIpcHandle, CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED, diff --git a/Samples/3_CUDA_Features/newdelete/Makefile b/Samples/3_CUDA_Features/newdelete/Makefile index a9284d9a..62d559bd 100644 --- a/Samples/3_CUDA_Features/newdelete/Makefile +++ b/Samples/3_CUDA_Features/newdelete/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/newdelete/README.md b/Samples/3_CUDA_Features/newdelete/README.md index b0a78947..b28d236a 100644 --- a/Samples/3_CUDA_Features/newdelete/README.md +++ b/Samples/3_CUDA_Features/newdelete/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaDeviceSetLimit, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/newdelete/newdelete_vs2017.vcxproj b/Samples/3_CUDA_Features/newdelete/newdelete_vs2017.vcxproj index c3ec63c7..1f9e4628 100644 --- a/Samples/3_CUDA_Features/newdelete/newdelete_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/newdelete/newdelete_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/newdelete/newdelete_vs2019.vcxproj b/Samples/3_CUDA_Features/newdelete/newdelete_vs2019.vcxproj index 46e9d946..7c9e690e 100644 --- a/Samples/3_CUDA_Features/newdelete/newdelete_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/newdelete/newdelete_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/newdelete/newdelete_vs2022.vcxproj b/Samples/3_CUDA_Features/newdelete/newdelete_vs2022.vcxproj index 50254100..e273c0f4 100644 --- a/Samples/3_CUDA_Features/newdelete/newdelete_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/newdelete/newdelete_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/ptxjit/Makefile b/Samples/3_CUDA_Features/ptxjit/Makefile index 1dbec277..d527d631 100644 --- a/Samples/3_CUDA_Features/ptxjit/Makefile +++ b/Samples/3_CUDA_Features/ptxjit/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/ptxjit/README.md b/Samples/3_CUDA_Features/ptxjit/README.md index cc990237..9f76f157 100644 --- a/Samples/3_CUDA_Features/ptxjit/README.md +++ b/Samples/3_CUDA_Features/ptxjit/README.md @@ -30,7 +30,7 @@ cudaMalloc, cudaDriverGetVersion, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2017.vcxproj b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2017.vcxproj index a5ea5550..2fba4834 100644 --- a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2019.vcxproj b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2019.vcxproj index d8840cab..cc631e4d 100644 --- a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2022.vcxproj b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2022.vcxproj index 33554627..5a4fb1b5 100644 --- a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/simpleCudaGraphs/Makefile b/Samples/3_CUDA_Features/simpleCudaGraphs/Makefile index 4d10e5b1..93413b8e 100644 --- a/Samples/3_CUDA_Features/simpleCudaGraphs/Makefile +++ b/Samples/3_CUDA_Features/simpleCudaGraphs/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/simpleCudaGraphs/README.md b/Samples/3_CUDA_Features/simpleCudaGraphs/README.md index 3a531bd8..f0f4c86d 100644 --- a/Samples/3_CUDA_Features/simpleCudaGraphs/README.md +++ b/Samples/3_CUDA_Features/simpleCudaGraphs/README.md @@ -25,7 +25,7 @@ cudaGraphClone, cudaExtent, cudaGraphLaunch, cudaStreamCreate, cudaLaunchHostFun ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2017.vcxproj b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2017.vcxproj index 238c4799..389c20f3 100644 --- a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2019.vcxproj b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2019.vcxproj index 98284f02..05b80cd1 100644 --- a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2022.vcxproj b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2022.vcxproj index ddc5a330..ccda01a5 100644 --- a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/tf32TensorCoreGemm/Makefile b/Samples/3_CUDA_Features/tf32TensorCoreGemm/Makefile index 90f9badd..1ac43916 100644 --- a/Samples/3_CUDA_Features/tf32TensorCoreGemm/Makefile +++ b/Samples/3_CUDA_Features/tf32TensorCoreGemm/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/tf32TensorCoreGemm/README.md b/Samples/3_CUDA_Features/tf32TensorCoreGemm/README.md index d0da4147..d7f38915 100644 --- a/Samples/3_CUDA_Features/tf32TensorCoreGemm/README.md +++ b/Samples/3_CUDA_Features/tf32TensorCoreGemm/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2017.vcxproj b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2017.vcxproj index 5b2ca2ff..bb73ecde 100644 --- a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2019.vcxproj b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2019.vcxproj index 4bdb6603..f4d8adcf 100644 --- a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2022.vcxproj b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2022.vcxproj index fac250eb..4c20fef6 100644 --- a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/Makefile b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/Makefile index 2b14baa1..a98389f7 100644 --- a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/Makefile +++ b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/README.md b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/README.md index 58d4cfdc..c177226d 100644 --- a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/README.md +++ b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/README.md @@ -25,7 +25,7 @@ cudaMemcpy, cudaFree, cudaDeviceGetAttribute, cudaMemset, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2017.vcxproj b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2017.vcxproj index b30b454b..e6c339a6 100644 --- a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2019.vcxproj b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2019.vcxproj index 5fb034ab..ce039e0d 100644 --- a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2022.vcxproj b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2022.vcxproj index 7fff8605..025d764c 100644 --- a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2017.vcxproj index d4ea42af..e210de5e 100644 --- a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2019.vcxproj index 691d52f1..298b13bc 100644 --- a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2022.vcxproj index b37f6c56..18ad7155 100644 --- a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/Makefile b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/Makefile index 479027b1..e19cd92a 100644 --- a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/Makefile +++ b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/README.md b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/README.md index e0aa381d..3cd4a91b 100644 --- a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/README.md +++ b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaDeviceReset, cudaSetDevice, cudaGetDeviceCount, cudaD ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/Makefile b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/Makefile index 4f3844c1..4f890a80 100644 --- a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/Makefile +++ b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2017.vcxproj b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2017.vcxproj index af19db63..4034d3a5 100644 --- a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2019.vcxproj b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2019.vcxproj index 6370c38a..df052e9b 100644 --- a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2022.vcxproj b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2022.vcxproj index 34e84a85..c8dbb814 100644 --- a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/README.md b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/README.md index 8a80dc03..d64f4f70 100644 --- a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/README.md +++ b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/README.md @@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaStreamDestroy, cudaFree, cudaMallocHost, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/batchCUBLAS/Makefile b/Samples/4_CUDA_Libraries/batchCUBLAS/Makefile index 81b4d51b..1e813cf0 100644 --- a/Samples/4_CUDA_Libraries/batchCUBLAS/Makefile +++ b/Samples/4_CUDA_Libraries/batchCUBLAS/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/batchCUBLAS/README.md b/Samples/4_CUDA_Libraries/batchCUBLAS/README.md index eedcbbcb..05325ca7 100644 --- a/Samples/4_CUDA_Libraries/batchCUBLAS/README.md +++ b/Samples/4_CUDA_Libraries/batchCUBLAS/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaGetLastError, cudaDeviceSynchroniz ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2017.vcxproj b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2017.vcxproj index d558f12a..366337a6 100644 --- a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2019.vcxproj b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2019.vcxproj index ad9dcd1f..de7cd45e 100644 --- a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2022.vcxproj b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2022.vcxproj index e375d131..445f5cb1 100644 --- a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/Makefile b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/Makefile index d984775a..27201be9 100644 --- a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/Makefile +++ b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/README.md b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/README.md index 6324ea35..28b1b353 100644 --- a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/README.md +++ b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaMallocPitch, cudaFree, cudaDeviceGetAttribute, cudaMa ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj index 16b67492..ac5e1bd4 100644 --- a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj index f3949f2d..e38256c6 100644 --- a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2022.vcxproj index 85d8c31c..4dad43f6 100644 --- a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/boxFilterNPP/Makefile b/Samples/4_CUDA_Libraries/boxFilterNPP/Makefile index 64fcaacd..8b531a63 100644 --- a/Samples/4_CUDA_Libraries/boxFilterNPP/Makefile +++ b/Samples/4_CUDA_Libraries/boxFilterNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/boxFilterNPP/README.md b/Samples/4_CUDA_Libraries/boxFilterNPP/README.md index a157bf86..32133125 100644 --- a/Samples/4_CUDA_Libraries/boxFilterNPP/README.md +++ b/Samples/4_CUDA_Libraries/boxFilterNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaDriverGetVersion ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2017.vcxproj index 7f5c9e49..b2f443b3 100644 --- a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2019.vcxproj index d55e4f70..359195e9 100644 --- a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2022.vcxproj index 4e31516f..7a908eb8 100644 --- a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/Makefile b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/Makefile index 1b99eafc..5afef823 100644 --- a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/Makefile +++ b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/README.md b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/README.md index a8fdeaec..32f33996 100644 --- a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/README.md +++ b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaFree, cudaSetDevice, cudaGetDeviceCount, cudaDeviceIn ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2017.vcxproj index dbc150a5..e46a9b62 100644 --- a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2019.vcxproj index eec60be2..19a29ad2 100644 --- a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2022.vcxproj index b5b97511..13c28a9b 100644 --- a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradient/Makefile b/Samples/4_CUDA_Libraries/conjugateGradient/Makefile index adbd1e65..31300fd3 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradient/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradient/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradient/README.md b/Samples/4_CUDA_Libraries/conjugateGradient/README.md index 0a06a76a..13fbaa97 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradient/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradient/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2017.vcxproj index 4aa7c82e..e05f9b9d 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2019.vcxproj index 8ae8e6e8..7058a1be 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2022.vcxproj index e9b3e152..d1dfd7e4 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/Makefile b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/Makefile index 023e2778..54918c62 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/README.md b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/README.md index eecd04ba..d7dc1bc2 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/README.md @@ -30,7 +30,7 @@ cudaGraphInstantiate, cudaStreamDestroy, cudaStreamBeginCapture, cudaFree, cudaM ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2017.vcxproj index 68c76541..9fbac187 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2019.vcxproj index 99c1068a..b67a0cef 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2022.vcxproj index 8aa21e34..59b4c78b 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/Makefile b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/Makefile index 5feec116..e99a6e5d 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/README.md b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/README.md index a2d80e73..6667faf0 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/README.md @@ -30,7 +30,7 @@ cudaFree, cudaMallocManaged, cudaDeviceSynchronize, cudaEventRecord, cudaLaunchC ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2017.vcxproj index 89669618..da9eb9e1 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2019.vcxproj index 1d622c34..e4dcf97d 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2022.vcxproj index 56341df3..e1487d4c 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/Makefile b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/Makefile index 960c7f81..ed7a5550 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/README.md b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/README.md index 8935fc08..5553a7ef 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/README.md @@ -30,7 +30,7 @@ cudaHostAlloc, cudaMemPrefetchAsync, cudaFree, cudaLaunchCooperativeKernel, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2017.vcxproj index bfa5bd7d..d461b8c7 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2019.vcxproj index 6dbc02e3..79967f30 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2022.vcxproj index c20c196d..03a401d1 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/Makefile b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/Makefile index a8439da7..cf632f1d 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/README.md b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/README.md index 94c2d71e..a7b0f0ab 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaMemset, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2017.vcxproj index 16fed6ba..4b27df41 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2019.vcxproj index a06dda35..b8179313 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2022.vcxproj index 9a3a49cc..b7b5a26f 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientUM/Makefile b/Samples/4_CUDA_Libraries/conjugateGradientUM/Makefile index aef6a0d5..f10e14c5 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientUM/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradientUM/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradientUM/README.md b/Samples/4_CUDA_Libraries/conjugateGradientUM/README.md index 2e34c66a..ac93a42f 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientUM/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradientUM/README.md @@ -28,7 +28,7 @@ cudaFree, cudaMallocManaged, cudaDeviceSynchronize, cudaMalloc, cudaGetDevicePro ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2017.vcxproj index 7f186e69..5c58c38b 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2019.vcxproj index ea1ec6f9..2809c19a 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2022.vcxproj index 8fe68879..a74a7d0a 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuDLAErrorReporting/Makefile b/Samples/4_CUDA_Libraries/cuDLAErrorReporting/Makefile index 02d79f4a..25012e42 100644 --- a/Samples/4_CUDA_Libraries/cuDLAErrorReporting/Makefile +++ b/Samples/4_CUDA_Libraries/cuDLAErrorReporting/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuDLAErrorReporting/README.md b/Samples/4_CUDA_Libraries/cuDLAErrorReporting/README.md index f1c59a24..38db6c24 100644 --- a/Samples/4_CUDA_Libraries/cuDLAErrorReporting/README.md +++ b/Samples/4_CUDA_Libraries/cuDLAErrorReporting/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaStreamDestroy, cudaFree, cudaGetErrorName, cudaSe ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuDLAHybridMode/Makefile b/Samples/4_CUDA_Libraries/cuDLAHybridMode/Makefile index 26f3645e..6e77489b 100644 --- a/Samples/4_CUDA_Libraries/cuDLAHybridMode/Makefile +++ b/Samples/4_CUDA_Libraries/cuDLAHybridMode/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuDLAHybridMode/README.md b/Samples/4_CUDA_Libraries/cuDLAHybridMode/README.md index 93086b66..057f7943 100644 --- a/Samples/4_CUDA_Libraries/cuDLAHybridMode/README.md +++ b/Samples/4_CUDA_Libraries/cuDLAHybridMode/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaStreamDestroy, cudaFree, cudaGetErrorName, cudaSe ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/Makefile b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/Makefile index 8bbd3e20..5db3f123 100644 --- a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/Makefile +++ b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/README.md b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/README.md index 4761d7ab..0a765e8b 100644 --- a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/README.md +++ b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaStreamDestroy, cudaFree, cudaGetErrorName, cudaSe ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/Makefile b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/Makefile index aa97778f..bc6af669 100644 --- a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/Makefile +++ b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -363,7 +376,7 @@ endif ALL_CCFLAGS += --std=c++11 --threads 0 -LIBRARIES += -lcudla -lnvscibuf -lnvscisync +LIBRARIES += -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia -lcudla -lnvscibuf -lnvscisync ifeq ($(SAMPLE_ENABLED),0) EXEC ?= @echo "[@]" diff --git a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/NsightEclipse.xml b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/NsightEclipse.xml index 341a6c76..56792243 100644 --- a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/NsightEclipse.xml @@ -27,6 +27,7 @@ nvscisync + $(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia true main.cpp diff --git a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/README.md b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/README.md index bab80837..fc3e8504 100644 --- a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/README.md +++ b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/README.md @@ -27,7 +27,7 @@ aarch64 ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/Makefile b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/Makefile index be7d600a..5b05995d 100644 --- a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/Makefile +++ b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -363,7 +376,7 @@ endif ALL_CCFLAGS += --std=c++11 --threads 0 -LIBRARIES += -lcudla -lnvscibuf -lnvscisync +LIBRARIES += -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia -lcudla -lnvscibuf -lnvscisync ifeq ($(SAMPLE_ENABLED),0) EXEC ?= @echo "[@]" diff --git a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/NsightEclipse.xml b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/NsightEclipse.xml index 7816fa18..86716175 100644 --- a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/NsightEclipse.xml @@ -27,6 +27,7 @@ nvscisync + $(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia true main.cpp diff --git a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/README.md b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/README.md index 2115512f..8f724901 100644 --- a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/README.md +++ b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/README.md @@ -27,7 +27,7 @@ aarch64 ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/Makefile b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/Makefile index 6218c90d..c278c598 100644 --- a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/Makefile +++ b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/README.md b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/README.md index d1d7995a..c21dedd4 100644 --- a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/README.md +++ b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaStreamDestroy, cudaFree, cudaDeviceSynchronize, cudaMemset, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2017.vcxproj index b7aeb9ba..9c62816b 100644 --- a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2019.vcxproj index b0ec7ccc..8f13a690 100644 --- a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2022.vcxproj index 45a2be68..1d866d4d 100644 --- a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverRf/Makefile b/Samples/4_CUDA_Libraries/cuSolverRf/Makefile index 647f7558..1d8e14ca 100644 --- a/Samples/4_CUDA_Libraries/cuSolverRf/Makefile +++ b/Samples/4_CUDA_Libraries/cuSolverRf/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuSolverRf/README.md b/Samples/4_CUDA_Libraries/cuSolverRf/README.md index 8c2b2a4a..15dbc164 100644 --- a/Samples/4_CUDA_Libraries/cuSolverRf/README.md +++ b/Samples/4_CUDA_Libraries/cuSolverRf/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaStreamDestroy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2017.vcxproj index c6daada3..3708ac5c 100644 --- a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2019.vcxproj index 17b4a26f..61e9154f 100644 --- a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2022.vcxproj index 0d9ab835..24f18755 100644 --- a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/Makefile b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/Makefile index df3ebf35..ba88c0cb 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/Makefile +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/README.md b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/README.md index 1c1c449f..5f46bd1f 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/README.md +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/README.md @@ -33,7 +33,7 @@ cudaStreamDestroy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaStreamCreate ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2017.vcxproj index 8b8d533e..12ab6d13 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2019.vcxproj index 3458a529..7d68f8ce 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2022.vcxproj index 45cb2336..3efa6975 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/Makefile b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/Makefile index 65266657..06b74000 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/Makefile +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/README.md b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/README.md index 8fb030a0..7273ac70 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/README.md +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaStreamDestroy, cudaFree, cudaMalloc, cudaStreamCreate ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2017.vcxproj index bb157a2d..474437ee 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2019.vcxproj index af61d7a0..64d5259d 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2022.vcxproj index e760219e..64882785 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/Makefile b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/Makefile index 85adca6f..da213be6 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/Makefile +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/README.md b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/README.md index 543df6ca..a3c2ad5d 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/README.md +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaStreamDestroy, cudaFree, cudaMalloc, cudaStreamCreate ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2017.vcxproj index 393e60bd..cf8d7ba1 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2019.vcxproj index c6d2fbec..1dd545ed 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2022.vcxproj index 76eb797f..c28bf366 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cudaNvSci/Makefile b/Samples/4_CUDA_Libraries/cudaNvSci/Makefile index 9fed51ff..ac09bb28 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSci/Makefile +++ b/Samples/4_CUDA_Libraries/cudaNvSci/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -415,7 +428,7 @@ endif ALL_CCFLAGS += --std=c++11 --threads 0 -LIBRARIES += -lnvscibuf -lnvscisync +LIBRARIES += -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia -lnvscibuf -lnvscisync ifeq ($(SAMPLE_ENABLED),0) EXEC ?= @echo "[@]" diff --git a/Samples/4_CUDA_Libraries/cudaNvSci/NsightEclipse.xml b/Samples/4_CUDA_Libraries/cudaNvSci/NsightEclipse.xml index 456007c6..704697ba 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSci/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/cudaNvSci/NsightEclipse.xml @@ -62,6 +62,7 @@ nvscisync + $(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia true main.cpp diff --git a/Samples/4_CUDA_Libraries/cudaNvSci/README.md b/Samples/4_CUDA_Libraries/cudaNvSci/README.md index 106fc721..06dd3e56 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSci/README.md +++ b/Samples/4_CUDA_Libraries/cudaNvSci/README.md @@ -33,7 +33,7 @@ cudaExternalMemoryGetMappedBuffer, cudaImportExternalSemaphore, cudaDeviceGetAtt ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/Makefile b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/Makefile index 48ccd9de..05d7a7af 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/Makefile +++ b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -426,7 +439,7 @@ endif ALL_CCFLAGS += --std=c++11 --threads 0 -LIBRARIES += -lnvscibuf -lnvscisync -lnvmedia +LIBRARIES += -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia -lnvscibuf -lnvscisync -lnvmedia ifeq ($(SAMPLE_ENABLED),0) EXEC ?= @echo "[@]" diff --git a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/NsightEclipse.xml b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/NsightEclipse.xml index fef560b2..55d2d131 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/NsightEclipse.xml @@ -58,6 +58,7 @@ nvmedia + $(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia true main.cpp diff --git a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/README.md b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/README.md index a0053bf4..8106f9c1 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/README.md +++ b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/README.md @@ -33,7 +33,7 @@ cudaImportExternalSemaphore, cudaGetMipmappedArrayLevel, cudaSetDevice, cudaDest ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/freeImageInteropNPP/Makefile b/Samples/4_CUDA_Libraries/freeImageInteropNPP/Makefile index b3c105ad..5a42c188 100644 --- a/Samples/4_CUDA_Libraries/freeImageInteropNPP/Makefile +++ b/Samples/4_CUDA_Libraries/freeImageInteropNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/freeImageInteropNPP/README.md b/Samples/4_CUDA_Libraries/freeImageInteropNPP/README.md index cece4a0b..1c467a99 100644 --- a/Samples/4_CUDA_Libraries/freeImageInteropNPP/README.md +++ b/Samples/4_CUDA_Libraries/freeImageInteropNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaSetDevice, cudaGetDeviceCount, cudaDeviceInit, cudaDr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2017.vcxproj index 0d1da49b..762ea36c 100644 --- a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2019.vcxproj index 561d8a05..e598a9f0 100644 --- a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2022.vcxproj index 2c614b09..a73c199c 100644 --- a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/histEqualizationNPP/Makefile b/Samples/4_CUDA_Libraries/histEqualizationNPP/Makefile index a3c4248c..c2a556d8 100644 --- a/Samples/4_CUDA_Libraries/histEqualizationNPP/Makefile +++ b/Samples/4_CUDA_Libraries/histEqualizationNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/histEqualizationNPP/README.md b/Samples/4_CUDA_Libraries/histEqualizationNPP/README.md index ec761042..0f19949b 100644 --- a/Samples/4_CUDA_Libraries/histEqualizationNPP/README.md +++ b/Samples/4_CUDA_Libraries/histEqualizationNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaMemcpy, cudaFree, cudaSetDevice, cudaGetDeviceCount, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2017.vcxproj index d7db4388..8c156fdf 100644 --- a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2019.vcxproj index 6e3f50f4..0f9cad5f 100644 --- a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2022.vcxproj index dd5a22a9..9e594c27 100644 --- a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/jitLto/Makefile b/Samples/4_CUDA_Libraries/jitLto/Makefile index 552eb2e8..9b6cc500 100644 --- a/Samples/4_CUDA_Libraries/jitLto/Makefile +++ b/Samples/4_CUDA_Libraries/jitLto/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/jitLto/README.md b/Samples/4_CUDA_Libraries/jitLto/README.md index f3a1ff3c..d1bf0e4e 100644 --- a/Samples/4_CUDA_Libraries/jitLto/README.md +++ b/Samples/4_CUDA_Libraries/jitLto/README.md @@ -30,7 +30,7 @@ cuModuleLoad, cuModuleLoadDataEx, cuModuleGetFunction, cuMemAlloc, cuMemFree, cu ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2017.vcxproj b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2017.vcxproj index b1e8d29a..b4f3222d 100644 --- a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2019.vcxproj b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2019.vcxproj index 76df93e2..af83084a 100644 --- a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2022.vcxproj b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2022.vcxproj index 1cdec4d5..6f91b8b3 100644 --- a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/lineOfSight/Makefile b/Samples/4_CUDA_Libraries/lineOfSight/Makefile index 54011cbd..0e104243 100644 --- a/Samples/4_CUDA_Libraries/lineOfSight/Makefile +++ b/Samples/4_CUDA_Libraries/lineOfSight/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/lineOfSight/README.md b/Samples/4_CUDA_Libraries/lineOfSight/README.md index 8dfb9159..41215bd8 100644 --- a/Samples/4_CUDA_Libraries/lineOfSight/README.md +++ b/Samples/4_CUDA_Libraries/lineOfSight/README.md @@ -27,7 +27,7 @@ cudaCreateChannelDesc, cudaMallocArray, cudaFreeArray, cudaDeviceSynchronize, cu ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2017.vcxproj b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2017.vcxproj index c4c405e9..8eb4f564 100644 --- a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2019.vcxproj b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2019.vcxproj index 704c323d..36f2383b 100644 --- a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2022.vcxproj b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2022.vcxproj index 37295856..e048d20e 100644 --- a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/Makefile b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/Makefile index c781defa..d23e2b9d 100644 --- a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/Makefile +++ b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/README.md b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/README.md index 1f04407a..b21ed988 100644 --- a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/README.md +++ b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaEventSynchronize, cudaEventRecord, cudaMalloc, cudaEve ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2017.vcxproj b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2017.vcxproj index 61d20323..53fdc902 100644 --- a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2019.vcxproj b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2019.vcxproj index 4b5af02b..d80e4c11 100644 --- a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2022.vcxproj b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2022.vcxproj index aec61c99..f6b27432 100644 --- a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG/Makefile b/Samples/4_CUDA_Libraries/nvJPEG/Makefile index 473813f5..c4c6e29a 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/Makefile +++ b/Samples/4_CUDA_Libraries/nvJPEG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -289,11 +302,6 @@ ifeq ($(TARGET_ARCH),aarch64) SAMPLE_ENABLED := 0 endif endif -# This sample is not supported on sbsa -ifeq ($(TARGET_ARCH),sbsa) - $(info >>> WARNING - nvJPEG is not supported on sbsa - waiving sample <<<) - SAMPLE_ENABLED := 0 -endif ALL_LDFLAGS := ALL_LDFLAGS += $(ALL_CCFLAGS) diff --git a/Samples/4_CUDA_Libraries/nvJPEG/NsightEclipse.xml b/Samples/4_CUDA_Libraries/nvJPEG/NsightEclipse.xml index 3875c29c..8a33531d 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/nvJPEG/NsightEclipse.xml @@ -60,6 +60,9 @@ qnx + + sbsa + 3.5 diff --git a/Samples/4_CUDA_Libraries/nvJPEG/README.md b/Samples/4_CUDA_Libraries/nvJPEG/README.md index 76acd15a..08f1be00 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/README.md +++ b/Samples/4_CUDA_Libraries/nvJPEG/README.md @@ -28,7 +28,7 @@ cudaHostAlloc, cudaStreamCreateWithFlags, cudaStreamDestroy, cudaFree, cudaEvent ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2017.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2017.vcxproj index 024c2f1d..7aac56db 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2019.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2019.vcxproj index a6d24ea3..b58eda10 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2022.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2022.vcxproj index cc063404..cd6ea3c8 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/Makefile b/Samples/4_CUDA_Libraries/nvJPEG_encoder/Makefile index ed4cfe5a..cd6e4484 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/Makefile +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -289,11 +302,6 @@ ifeq ($(TARGET_ARCH),aarch64) SAMPLE_ENABLED := 0 endif endif -# This sample is not supported on sbsa -ifeq ($(TARGET_ARCH),sbsa) - $(info >>> WARNING - nvJPEG_encoder is not supported on sbsa - waiving sample <<<) - SAMPLE_ENABLED := 0 -endif ALL_LDFLAGS := ALL_LDFLAGS += $(ALL_CCFLAGS) diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/NsightEclipse.xml b/Samples/4_CUDA_Libraries/nvJPEG_encoder/NsightEclipse.xml index 6436c0b2..e31c8518 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/NsightEclipse.xml @@ -57,6 +57,9 @@ qnx + + sbsa + 3.5 diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/README.md b/Samples/4_CUDA_Libraries/nvJPEG_encoder/README.md index e54657da..cd3fbb21 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/README.md +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/README.md @@ -28,7 +28,7 @@ cudaFree, cudaGetErrorString, cudaEventSynchronize, cudaDeviceSynchronize, cudaE ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2017.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2017.vcxproj index 6851aac7..019737d4 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2019.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2019.vcxproj index 57c66109..80dbb337 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2022.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2022.vcxproj index d89823db..9255c0ef 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/oceanFFT/Makefile b/Samples/4_CUDA_Libraries/oceanFFT/Makefile index 77705a1f..fc133a35 100644 --- a/Samples/4_CUDA_Libraries/oceanFFT/Makefile +++ b/Samples/4_CUDA_Libraries/oceanFFT/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/oceanFFT/README.md b/Samples/4_CUDA_Libraries/oceanFFT/README.md index 77c92995..fe6f0713 100644 --- a/Samples/4_CUDA_Libraries/oceanFFT/README.md +++ b/Samples/4_CUDA_Libraries/oceanFFT/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMalloc, cudaFree, cudaGraphicsResour ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2017.vcxproj b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2017.vcxproj index 80653b89..34a53e01 100644 --- a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2019.vcxproj b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2019.vcxproj index 505da9b4..d1673803 100644 --- a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2022.vcxproj b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2022.vcxproj index 98375d06..67e4f26c 100644 --- a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/randomFog/Makefile b/Samples/4_CUDA_Libraries/randomFog/Makefile index 8c96318c..c2e1a6b3 100644 --- a/Samples/4_CUDA_Libraries/randomFog/Makefile +++ b/Samples/4_CUDA_Libraries/randomFog/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/randomFog/README.md b/Samples/4_CUDA_Libraries/randomFog/README.md index d42d5fa7..1181ed59 100644 --- a/Samples/4_CUDA_Libraries/randomFog/README.md +++ b/Samples/4_CUDA_Libraries/randomFog/README.md @@ -30,7 +30,7 @@ cudaMalloc, cudaGetErrorString, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2017.vcxproj b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2017.vcxproj index 68db1660..5554d671 100644 --- a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2019.vcxproj b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2019.vcxproj index 9e8ade90..4846f8b3 100644 --- a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2022.vcxproj b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2022.vcxproj index a4571969..ee943bf9 100644 --- a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS/Makefile b/Samples/4_CUDA_Libraries/simpleCUBLAS/Makefile index 63225a72..70e7d8f4 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS/README.md b/Samples/4_CUDA_Libraries/simpleCUBLAS/README.md index a96b9cfe..64495d61 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS/README.md @@ -30,7 +30,7 @@ cudaMalloc, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2017.vcxproj index c89f099b..0d5ff625 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2019.vcxproj index c84679db..72033b46 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2022.vcxproj index 43af9e74..525d4fc8 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLASXT/Makefile b/Samples/4_CUDA_Libraries/simpleCUBLASXT/Makefile index f892667c..7dad756a 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLASXT/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUBLASXT/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUBLASXT/README.md b/Samples/4_CUDA_Libraries/simpleCUBLASXT/README.md index 3b4a4e62..443a3218 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLASXT/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUBLASXT/README.md @@ -30,7 +30,7 @@ cudaGetDeviceProperties, cudaGetDeviceCount, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2017.vcxproj index 67143c59..862f96a3 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2019.vcxproj index 63901551..f92b1d76 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2022.vcxproj index a4025ea2..5f3b48aa 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/Makefile b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/Makefile index 461a74cf..8c3001b9 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/README.md b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/README.md index d01b9a1d..4605545a 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/README.md @@ -30,7 +30,7 @@ cudaGetErrorEnum, cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2017.vcxproj index d4536152..faf4de30 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2019.vcxproj index dad7fc39..d1104b99 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2022.vcxproj index 65182209..9e093294 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT/Makefile b/Samples/4_CUDA_Libraries/simpleCUFFT/Makefile index 4e209436..5282afcf 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUFFT/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT/README.md b/Samples/4_CUDA_Libraries/simpleCUFFT/README.md index 2da3f075..cddeb1d5 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUFFT/README.md @@ -30,7 +30,7 @@ cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2017.vcxproj index 60950cd5..5e73a651 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2019.vcxproj index 4292937a..5dc6cc20 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2022.vcxproj index 45bcca7d..fab04695 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/Makefile b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/Makefile index 15a3c68a..1a5d50d8 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/README.md b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/README.md index 16219370..bbf62e0e 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/README.md @@ -30,7 +30,7 @@ cudaXtFree, cudaMemcpy, cudaFree, cudaSetDevice, cudaGetDeviceCount, cudaDeviceS ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2017.vcxproj index 9fc87821..1e7ee203 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2019.vcxproj index a8d25bb7..5ed65060 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2022.vcxproj index cac438bb..02ccbb23 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/Makefile b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/Makefile index eb4c0c36..ab4f7c91 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/README.md b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/README.md index a5b19e6c..32795573 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/README.md @@ -30,7 +30,7 @@ cudaXtFree, cudaSetDevice, cudaGetDeviceCount, cudaDeviceSynchronize, cudaGetDev ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2017.vcxproj index bfe9b8d8..35c0d171 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2019.vcxproj index 51b2f714..05a67214 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2022.vcxproj index 288c5540..b4d7f285 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_callback/Makefile b/Samples/4_CUDA_Libraries/simpleCUFFT_callback/Makefile index 475d93ae..172f79a1 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_callback/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_callback/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_callback/README.md b/Samples/4_CUDA_Libraries/simpleCUFFT_callback/README.md index e9fa27c5..7e3d8a46 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_callback/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_callback/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaMemcpyFromSymbol, cudaGetDevice, cudaMalloc, cudaGetDe ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/Makefile b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/Makefile index 5379fcf7..dc94c863 100644 --- a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/Makefile +++ b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/README.md b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/README.md index 5d719f32..ab548cab 100644 --- a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/README.md +++ b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaFree, cudaDeviceGetAttribute, cudaDriverGetVersion, c ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2017.vcxproj index f9012f18..cf222514 100644 --- a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2019.vcxproj index 60631742..a306232e 100644 --- a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2022.vcxproj index 214d48e8..2315351b 100644 --- a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2017.vcxproj b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2017.vcxproj index 4c9a4fc4..d3f2a94c 100644 --- a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2019.vcxproj b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2019.vcxproj index 1a89e223..646c6af6 100644 --- a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2022.vcxproj b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2022.vcxproj index 63066ceb..ff15d3f5 100644 --- a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes/Makefile b/Samples/5_Domain_Specific/BlackScholes/Makefile index c5886311..0665dad9 100644 --- a/Samples/5_Domain_Specific/BlackScholes/Makefile +++ b/Samples/5_Domain_Specific/BlackScholes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/BlackScholes/README.md b/Samples/5_Domain_Specific/BlackScholes/README.md index 6e6f16a5..3ea0baab 100644 --- a/Samples/5_Domain_Specific/BlackScholes/README.md +++ b/Samples/5_Domain_Specific/BlackScholes/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2017.vcxproj b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2017.vcxproj index 40d52f99..1269021e 100644 --- a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2019.vcxproj b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2019.vcxproj index aa7f2419..f9878409 100644 --- a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2022.vcxproj b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2022.vcxproj index e603ba4b..7ac2934b 100644 --- a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes_nvrtc/Makefile b/Samples/5_Domain_Specific/BlackScholes_nvrtc/Makefile index c2b6f52b..75aa63dd 100644 --- a/Samples/5_Domain_Specific/BlackScholes_nvrtc/Makefile +++ b/Samples/5_Domain_Specific/BlackScholes_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/BlackScholes_nvrtc/README.md b/Samples/5_Domain_Specific/BlackScholes_nvrtc/README.md index 529337e9..d2cb2092 100644 --- a/Samples/5_Domain_Specific/BlackScholes_nvrtc/README.md +++ b/Samples/5_Domain_Specific/BlackScholes_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2017.vcxproj b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2017.vcxproj index a5a33448..d15ecc69 100644 --- a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2019.vcxproj b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2019.vcxproj index b75e953b..382028f6 100644 --- a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2022.vcxproj b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2022.vcxproj index d103afe9..fe1b98ac 100644 --- a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/FDTD3d/Makefile b/Samples/5_Domain_Specific/FDTD3d/Makefile index 588f9bee..6f78c299 100644 --- a/Samples/5_Domain_Specific/FDTD3d/Makefile +++ b/Samples/5_Domain_Specific/FDTD3d/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/FDTD3d/README.md b/Samples/5_Domain_Specific/FDTD3d/README.md index 3e35c2ee..f4cf1037 100644 --- a/Samples/5_Domain_Specific/FDTD3d/README.md +++ b/Samples/5_Domain_Specific/FDTD3d/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaMalloc, cudaFree, cudaFuncGetAttributes, cudaSetDevice, cudaGetD ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2017.vcxproj b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2017.vcxproj index 51709044..c1f10207 100644 --- a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2019.vcxproj b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2019.vcxproj index f550d389..04a0fae9 100644 --- a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2022.vcxproj b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2022.vcxproj index 9b721af5..7d5ce335 100644 --- a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/HSOpticalFlow/Makefile b/Samples/5_Domain_Specific/HSOpticalFlow/Makefile index e532ed87..37cca015 100644 --- a/Samples/5_Domain_Specific/HSOpticalFlow/Makefile +++ b/Samples/5_Domain_Specific/HSOpticalFlow/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/HSOpticalFlow/README.md b/Samples/5_Domain_Specific/HSOpticalFlow/README.md index 6759bc5a..c48b998d 100644 --- a/Samples/5_Domain_Specific/HSOpticalFlow/README.md +++ b/Samples/5_Domain_Specific/HSOpticalFlow/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaMemset, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/Mandelbrot/Makefile b/Samples/5_Domain_Specific/Mandelbrot/Makefile index b03fedea..634131af 100644 --- a/Samples/5_Domain_Specific/Mandelbrot/Makefile +++ b/Samples/5_Domain_Specific/Mandelbrot/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2017.vcxproj b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2017.vcxproj index be20b36d..a65cf809 100644 --- a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -121,6 +121,6 @@ - + diff --git a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2019.vcxproj b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2019.vcxproj index 8f72c782..c8dc7a1a 100644 --- a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2022.vcxproj b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2022.vcxproj index c64d0be5..718dbbb7 100644 --- a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/Mandelbrot/README.md b/Samples/5_Domain_Specific/Mandelbrot/README.md index b41ab2e0..49605ec3 100644 --- a/Samples/5_Domain_Specific/Mandelbrot/README.md +++ b/Samples/5_Domain_Specific/Mandelbrot/README.md @@ -30,7 +30,7 @@ cudaGLUnmapBufferObject, cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaG ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/MonteCarloMultiGPU/Makefile b/Samples/5_Domain_Specific/MonteCarloMultiGPU/Makefile index f608ae9a..ca5f212c 100644 --- a/Samples/5_Domain_Specific/MonteCarloMultiGPU/Makefile +++ b/Samples/5_Domain_Specific/MonteCarloMultiGPU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2017.vcxproj b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2017.vcxproj index cde14137..46f50fa7 100644 --- a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2019.vcxproj b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2019.vcxproj index 73ec1bb4..540e7de2 100644 --- a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2022.vcxproj b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2022.vcxproj index b51147fb..4e9178c4 100644 --- a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/MonteCarloMultiGPU/README.md b/Samples/5_Domain_Specific/MonteCarloMultiGPU/README.md index 0d3c2a43..dc1429ae 100644 --- a/Samples/5_Domain_Specific/MonteCarloMultiGPU/README.md +++ b/Samples/5_Domain_Specific/MonteCarloMultiGPU/README.md @@ -30,7 +30,7 @@ cudaStreamDestroy, cudaMalloc, cudaFree, cudaMallocHost, cudaSetDevice, cudaEven ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/NV12toBGRandResize/Makefile b/Samples/5_Domain_Specific/NV12toBGRandResize/Makefile index 121a70cb..bf4f3e80 100644 --- a/Samples/5_Domain_Specific/NV12toBGRandResize/Makefile +++ b/Samples/5_Domain_Specific/NV12toBGRandResize/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2017.vcxproj b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2017.vcxproj index ad90dbd3..560f7bc2 100644 --- a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2019.vcxproj b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2019.vcxproj index 7ad22653..1620f584 100644 --- a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2022.vcxproj b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2022.vcxproj index 7fca45eb..dd01a974 100644 --- a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/NV12toBGRandResize/README.md b/Samples/5_Domain_Specific/NV12toBGRandResize/README.md index eb153295..f6c3eee6 100644 --- a/Samples/5_Domain_Specific/NV12toBGRandResize/README.md +++ b/Samples/5_Domain_Specific/NV12toBGRandResize/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaStreamDestroy, cudaMalloc, cudaFree, cudaMallocManaged, cudaStre ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/SLID3D10Texture/README.md b/Samples/5_Domain_Specific/SLID3D10Texture/README.md index 41e5e959..9ab9405a 100644 --- a/Samples/5_Domain_Specific/SLID3D10Texture/README.md +++ b/Samples/5_Domain_Specific/SLID3D10Texture/README.md @@ -33,7 +33,7 @@ cudaGraphicsUnmapResources, cudaMalloc, cudaMallocPitch, cudaGetErrorString, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2017.vcxproj b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2017.vcxproj index 5babd818..ded543b6 100644 --- a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2019.vcxproj b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2019.vcxproj index 586dd121..23d32436 100644 --- a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2022.vcxproj b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2022.vcxproj index 77987c27..b56cfdbf 100644 --- a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobelFilter/Makefile b/Samples/5_Domain_Specific/SobelFilter/Makefile index 380500b4..47f7ca4e 100644 --- a/Samples/5_Domain_Specific/SobelFilter/Makefile +++ b/Samples/5_Domain_Specific/SobelFilter/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/SobelFilter/README.md b/Samples/5_Domain_Specific/SobelFilter/README.md index 0b7804d7..7691119e 100644 --- a/Samples/5_Domain_Specific/SobelFilter/README.md +++ b/Samples/5_Domain_Specific/SobelFilter/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2017.vcxproj b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2017.vcxproj index f7e2cd44..cebcac4b 100644 --- a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2019.vcxproj b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2019.vcxproj index 6cefc96e..f8b6ab98 100644 --- a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2022.vcxproj b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2022.vcxproj index bb3fd0ac..b2926d1e 100644 --- a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobolQRNG/Makefile b/Samples/5_Domain_Specific/SobolQRNG/Makefile index 3df0f5bc..c1478305 100644 --- a/Samples/5_Domain_Specific/SobolQRNG/Makefile +++ b/Samples/5_Domain_Specific/SobolQRNG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/SobolQRNG/README.md b/Samples/5_Domain_Specific/SobolQRNG/README.md index 1bb83761..5ead5d1b 100644 --- a/Samples/5_Domain_Specific/SobolQRNG/README.md +++ b/Samples/5_Domain_Specific/SobolQRNG/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaDeviceSynchronize, cudaGetDevice, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2017.vcxproj b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2017.vcxproj index 6446ca35..32bc67a2 100644 --- a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2019.vcxproj b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2019.vcxproj index c4de241a..02abfca6 100644 --- a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2022.vcxproj b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2022.vcxproj index 401bbc1a..e4620fdf 100644 --- a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/VFlockingD3D10/README.md b/Samples/5_Domain_Specific/VFlockingD3D10/README.md index 01ead592..9d6fc067 100644 --- a/Samples/5_Domain_Specific/VFlockingD3D10/README.md +++ b/Samples/5_Domain_Specific/VFlockingD3D10/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGetErrorString, cudaGraphi ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2017.vcxproj b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2017.vcxproj index 6403b0e5..cddedfc6 100644 --- a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2019.vcxproj b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2019.vcxproj index 155b4710..2219cf40 100644 --- a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2022.vcxproj b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2022.vcxproj index 75d5e65e..f5c7f14e 100644 --- a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/bicubicTexture/Makefile b/Samples/5_Domain_Specific/bicubicTexture/Makefile index 1fa1bae8..4d8608ad 100644 --- a/Samples/5_Domain_Specific/bicubicTexture/Makefile +++ b/Samples/5_Domain_Specific/bicubicTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/bicubicTexture/README.md b/Samples/5_Domain_Specific/bicubicTexture/README.md index 860e9065..c3f31ce9 100644 --- a/Samples/5_Domain_Specific/bicubicTexture/README.md +++ b/Samples/5_Domain_Specific/bicubicTexture/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaCreateChannelDesc, cudaMallocArray, cudaFreeArra ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2017.vcxproj b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2017.vcxproj index c0e224eb..cbb89017 100644 --- a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2019.vcxproj b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2019.vcxproj index ce7a4a87..2c35d23d 100644 --- a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2022.vcxproj b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2022.vcxproj index 356db728..6186468b 100644 --- a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/bilateralFilter/Makefile b/Samples/5_Domain_Specific/bilateralFilter/Makefile index 4410ff33..a8519637 100644 --- a/Samples/5_Domain_Specific/bilateralFilter/Makefile +++ b/Samples/5_Domain_Specific/bilateralFilter/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/bilateralFilter/README.md b/Samples/5_Domain_Specific/bilateralFilter/README.md index 1a3e5bb3..12aa41b8 100644 --- a/Samples/5_Domain_Specific/bilateralFilter/README.md +++ b/Samples/5_Domain_Specific/bilateralFilter/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaGraphicsUnmapResources, cudaMallocPitch, cudaFree, cu ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2017.vcxproj b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2017.vcxproj index f8cbcf60..a89ab9a8 100644 --- a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -120,6 +120,6 @@ - + diff --git a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2019.vcxproj b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2019.vcxproj index 76478a1e..0b53fffe 100644 --- a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -116,6 +116,6 @@ - + diff --git a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2022.vcxproj b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2022.vcxproj index 2bbf117c..dc7e01c4 100644 --- a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -116,6 +116,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions/Makefile b/Samples/5_Domain_Specific/binomialOptions/Makefile index 7cd0426f..485f7f0f 100644 --- a/Samples/5_Domain_Specific/binomialOptions/Makefile +++ b/Samples/5_Domain_Specific/binomialOptions/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/binomialOptions/README.md b/Samples/5_Domain_Specific/binomialOptions/README.md index 86723a19..d0da7371 100644 --- a/Samples/5_Domain_Specific/binomialOptions/README.md +++ b/Samples/5_Domain_Specific/binomialOptions/README.md @@ -27,7 +27,7 @@ cudaDeviceSynchronize, cudaMemcpyToSymbol, cudaMemcpyFromSymbol ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2017.vcxproj b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2017.vcxproj index a52532b9..6e7cf9c3 100644 --- a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2019.vcxproj b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2019.vcxproj index cf362e90..3b34983f 100644 --- a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2022.vcxproj b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2022.vcxproj index 1a00dbbd..f6d0f359 100644 --- a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions_nvrtc/Makefile b/Samples/5_Domain_Specific/binomialOptions_nvrtc/Makefile index 1a9eca45..0bca7038 100644 --- a/Samples/5_Domain_Specific/binomialOptions_nvrtc/Makefile +++ b/Samples/5_Domain_Specific/binomialOptions_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/binomialOptions_nvrtc/README.md b/Samples/5_Domain_Specific/binomialOptions_nvrtc/README.md index 15e8c577..6e81d3f4 100644 --- a/Samples/5_Domain_Specific/binomialOptions_nvrtc/README.md +++ b/Samples/5_Domain_Specific/binomialOptions_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2017.vcxproj b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2017.vcxproj index 8c626d62..de2f6617 100644 --- a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2019.vcxproj b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2019.vcxproj index e8a478a5..89c7d6c0 100644 --- a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2022.vcxproj b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2022.vcxproj index efcbad12..730add2b 100644 --- a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/convolutionFFT2D/Makefile b/Samples/5_Domain_Specific/convolutionFFT2D/Makefile index 4297d56c..34442f68 100644 --- a/Samples/5_Domain_Specific/convolutionFFT2D/Makefile +++ b/Samples/5_Domain_Specific/convolutionFFT2D/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/convolutionFFT2D/README.md b/Samples/5_Domain_Specific/convolutionFFT2D/README.md index d1fb5bb9..7a3c3740 100644 --- a/Samples/5_Domain_Specific/convolutionFFT2D/README.md +++ b/Samples/5_Domain_Specific/convolutionFFT2D/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaDestroyTextureObject, cudaDeviceSynchronize, cudaCreat ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2017.vcxproj b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2017.vcxproj index ef5afa1b..d9286bfa 100644 --- a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2019.vcxproj b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2019.vcxproj index 9d4b8d97..62fbfacb 100644 --- a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2022.vcxproj b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2022.vcxproj index 57821761..a74e2da9 100644 --- a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/dwtHaar1D/Makefile b/Samples/5_Domain_Specific/dwtHaar1D/Makefile index 0ee7c65f..f7c8276c 100644 --- a/Samples/5_Domain_Specific/dwtHaar1D/Makefile +++ b/Samples/5_Domain_Specific/dwtHaar1D/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/dwtHaar1D/README.md b/Samples/5_Domain_Specific/dwtHaar1D/README.md index a4ca4ee7..23a55b77 100644 --- a/Samples/5_Domain_Specific/dwtHaar1D/README.md +++ b/Samples/5_Domain_Specific/dwtHaar1D/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2017.vcxproj b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2017.vcxproj index bd039e30..e85d18bf 100644 --- a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2019.vcxproj b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2019.vcxproj index 9bd5ff2e..0aa77dd0 100644 --- a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2022.vcxproj b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2022.vcxproj index d4e82e00..d67b6431 100644 --- a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/dxtc/Makefile b/Samples/5_Domain_Specific/dxtc/Makefile index 1b9e06b1..8e575133 100644 --- a/Samples/5_Domain_Specific/dxtc/Makefile +++ b/Samples/5_Domain_Specific/dxtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/dxtc/README.md b/Samples/5_Domain_Specific/dxtc/README.md index 1023b438..c3ff39eb 100644 --- a/Samples/5_Domain_Specific/dxtc/README.md +++ b/Samples/5_Domain_Specific/dxtc/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaGetDevice, cudaMalloc, cudaGetD ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/dxtc/dxtc_vs2017.vcxproj b/Samples/5_Domain_Specific/dxtc/dxtc_vs2017.vcxproj index a59250ba..0a39fd0d 100644 --- a/Samples/5_Domain_Specific/dxtc/dxtc_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/dxtc/dxtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/dxtc/dxtc_vs2019.vcxproj b/Samples/5_Domain_Specific/dxtc/dxtc_vs2019.vcxproj index db76bb32..269dd0e1 100644 --- a/Samples/5_Domain_Specific/dxtc/dxtc_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/dxtc/dxtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/dxtc/dxtc_vs2022.vcxproj b/Samples/5_Domain_Specific/dxtc/dxtc_vs2022.vcxproj index f08cad42..f0e656ae 100644 --- a/Samples/5_Domain_Specific/dxtc/dxtc_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/dxtc/dxtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/fastWalshTransform/Makefile b/Samples/5_Domain_Specific/fastWalshTransform/Makefile index ca79a87f..b0b08d90 100644 --- a/Samples/5_Domain_Specific/fastWalshTransform/Makefile +++ b/Samples/5_Domain_Specific/fastWalshTransform/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/fastWalshTransform/README.md b/Samples/5_Domain_Specific/fastWalshTransform/README.md index 2e7eb491..46236c1c 100644 --- a/Samples/5_Domain_Specific/fastWalshTransform/README.md +++ b/Samples/5_Domain_Specific/fastWalshTransform/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMemset, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2017.vcxproj b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2017.vcxproj index 387db453..81491b26 100644 --- a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2019.vcxproj b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2019.vcxproj index 9173630a..57900d3d 100644 --- a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2022.vcxproj b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2022.vcxproj index 14b6b8cb..a13af456 100644 --- a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsD3D9/README.md b/Samples/5_Domain_Specific/fluidsD3D9/README.md index 7518ae74..84e45b07 100644 --- a/Samples/5_Domain_Specific/fluidsD3D9/README.md +++ b/Samples/5_Domain_Specific/fluidsD3D9/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2017.vcxproj b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2017.vcxproj index a905deff..13ddf703 100644 --- a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2019.vcxproj b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2019.vcxproj index 82a93317..3d59d6c8 100644 --- a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2022.vcxproj b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2022.vcxproj index 373ab5ad..62924a77 100644 --- a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsGL/Makefile b/Samples/5_Domain_Specific/fluidsGL/Makefile index acccf6a0..f295425a 100644 --- a/Samples/5_Domain_Specific/fluidsGL/Makefile +++ b/Samples/5_Domain_Specific/fluidsGL/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/fluidsGL/README.md b/Samples/5_Domain_Specific/fluidsGL/README.md index e667c270..fa66f2f0 100644 --- a/Samples/5_Domain_Specific/fluidsGL/README.md +++ b/Samples/5_Domain_Specific/fluidsGL/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2017.vcxproj b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2017.vcxproj index 45677537..6fb0c66a 100644 --- a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -120,6 +120,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2019.vcxproj b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2019.vcxproj index faadbe59..0c40d0b1 100644 --- a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -116,6 +116,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2022.vcxproj b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2022.vcxproj index beaf36d5..deee87ab 100644 --- a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -116,6 +116,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsGLES/Makefile b/Samples/5_Domain_Specific/fluidsGLES/Makefile index 8fa4ca3a..b57de511 100644 --- a/Samples/5_Domain_Specific/fluidsGLES/Makefile +++ b/Samples/5_Domain_Specific/fluidsGLES/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/fluidsGLES/README.md b/Samples/5_Domain_Specific/fluidsGLES/README.md index 866dcda4..1abac27e 100644 --- a/Samples/5_Domain_Specific/fluidsGLES/README.md +++ b/Samples/5_Domain_Specific/fluidsGLES/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/marchingCubes/Makefile b/Samples/5_Domain_Specific/marchingCubes/Makefile index 30f40e57..f8274165 100644 --- a/Samples/5_Domain_Specific/marchingCubes/Makefile +++ b/Samples/5_Domain_Specific/marchingCubes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/marchingCubes/README.md b/Samples/5_Domain_Specific/marchingCubes/README.md index db854295..ae1a2f4d 100644 --- a/Samples/5_Domain_Specific/marchingCubes/README.md +++ b/Samples/5_Domain_Specific/marchingCubes/README.md @@ -30,7 +30,7 @@ cudaGLUnmapBufferObject, cudaGraphicsUnmapResources, cudaCreateChannelDesc, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2017.vcxproj b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2017.vcxproj index 59904912..fdf1efa2 100644 --- a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2019.vcxproj b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2019.vcxproj index fa1654b2..52afc39e 100644 --- a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -115,6 +115,6 @@ - + diff --git a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2022.vcxproj b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2022.vcxproj index 2d4ddd62..5f823086 100644 --- a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -115,6 +115,6 @@ - + diff --git a/Samples/5_Domain_Specific/nbody/Makefile b/Samples/5_Domain_Specific/nbody/Makefile index e218084b..b6a10376 100644 --- a/Samples/5_Domain_Specific/nbody/Makefile +++ b/Samples/5_Domain_Specific/nbody/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/nbody/README.md b/Samples/5_Domain_Specific/nbody/README.md index eba10a8d..35a76ed8 100644 --- a/Samples/5_Domain_Specific/nbody/README.md +++ b/Samples/5_Domain_Specific/nbody/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaSetDeviceFlags, cudaGraphicsResourceSetMapFlags, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/nbody/nbody_vs2017.vcxproj b/Samples/5_Domain_Specific/nbody/nbody_vs2017.vcxproj index c20d4808..893f7a23 100644 --- a/Samples/5_Domain_Specific/nbody/nbody_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/nbody/nbody_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -125,6 +125,6 @@ - + diff --git a/Samples/5_Domain_Specific/nbody/nbody_vs2019.vcxproj b/Samples/5_Domain_Specific/nbody/nbody_vs2019.vcxproj index 99874137..84107c17 100644 --- a/Samples/5_Domain_Specific/nbody/nbody_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/nbody/nbody_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -121,6 +121,6 @@ - + diff --git a/Samples/5_Domain_Specific/nbody/nbody_vs2022.vcxproj b/Samples/5_Domain_Specific/nbody/nbody_vs2022.vcxproj index fade7812..be9824bb 100644 --- a/Samples/5_Domain_Specific/nbody/nbody_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/nbody/nbody_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -121,6 +121,6 @@ - + diff --git a/Samples/5_Domain_Specific/nbody_opengles/Makefile b/Samples/5_Domain_Specific/nbody_opengles/Makefile index 1ba63daa..faad2c50 100644 --- a/Samples/5_Domain_Specific/nbody_opengles/Makefile +++ b/Samples/5_Domain_Specific/nbody_opengles/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/nbody_opengles/README.md b/Samples/5_Domain_Specific/nbody_opengles/README.md index 88f2828a..f8c93485 100644 --- a/Samples/5_Domain_Specific/nbody_opengles/README.md +++ b/Samples/5_Domain_Specific/nbody_opengles/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaSetDeviceFlags, cudaGraphicsResourceSetMapFlags, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/nbody_screen/Makefile b/Samples/5_Domain_Specific/nbody_screen/Makefile index c87afabe..74278b08 100644 --- a/Samples/5_Domain_Specific/nbody_screen/Makefile +++ b/Samples/5_Domain_Specific/nbody_screen/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/nbody_screen/README.md b/Samples/5_Domain_Specific/nbody_screen/README.md index 29258334..834bdef8 100644 --- a/Samples/5_Domain_Specific/nbody_screen/README.md +++ b/Samples/5_Domain_Specific/nbody_screen/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaSetDeviceFlags, cudaGraphicsResourceSetMapFlags, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/Makefile b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/Makefile index d48f67ef..48b92ec5 100644 --- a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/Makefile +++ b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/README.md b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/README.md index 629fd64f..d1be7ce9 100644 --- a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/README.md +++ b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/README.md @@ -27,7 +27,7 @@ cudaSetDevice, cudaEventDestroy, cudaOccupancyMaxPotentialBlockSize, cudaCheckEr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2017.vcxproj b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2017.vcxproj index b43284fa..23a18cf0 100644 --- a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2019.vcxproj b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2019.vcxproj index e644f4df..227f77ea 100644 --- a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2022.vcxproj b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2022.vcxproj index 7dec7b3a..54461097 100644 --- a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/postProcessGL/Makefile b/Samples/5_Domain_Specific/postProcessGL/Makefile index d346bc75..2b9ab6e1 100644 --- a/Samples/5_Domain_Specific/postProcessGL/Makefile +++ b/Samples/5_Domain_Specific/postProcessGL/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/postProcessGL/README.md b/Samples/5_Domain_Specific/postProcessGL/README.md index 8639ee80..b89f0349 100644 --- a/Samples/5_Domain_Specific/postProcessGL/README.md +++ b/Samples/5_Domain_Specific/postProcessGL/README.md @@ -30,7 +30,7 @@ cudaHostAlloc, cudaGraphicsUnmapResources, cudaMalloc, cudaFree, cudaGetChannelD ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2017.vcxproj b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2017.vcxproj index 4281022b..ac6901e4 100644 --- a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2019.vcxproj b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2019.vcxproj index c24b3099..2711f5d8 100644 --- a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2022.vcxproj b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2022.vcxproj index 3ce9b99c..3a0d25be 100644 --- a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator/Makefile b/Samples/5_Domain_Specific/quasirandomGenerator/Makefile index 48cc189e..a59c3233 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator/Makefile +++ b/Samples/5_Domain_Specific/quasirandomGenerator/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/quasirandomGenerator/README.md b/Samples/5_Domain_Specific/quasirandomGenerator/README.md index 193be5fd..d2edaea2 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator/README.md +++ b/Samples/5_Domain_Specific/quasirandomGenerator/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMemset, cudaMemcpyToSymbol, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2017.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2017.vcxproj index b666cb59..ce61dc73 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2019.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2019.vcxproj index 669b8b3d..b6339019 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2022.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2022.vcxproj index 330ca71c..3a129871 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/Makefile b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/Makefile index 620f28f6..2c0540af 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/Makefile +++ b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/README.md b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/README.md index e7e9e8c8..9d169869 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/README.md +++ b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/README.md @@ -30,7 +30,7 @@ cuMemcpyDtoH, cuMemAlloc, cuMemFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2017.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2017.vcxproj index a5e455a5..d3dfefe9 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2019.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2019.vcxproj index 01ab89e4..196ed679 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2022.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2022.vcxproj index 028a4f26..1f5b61c2 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/recursiveGaussian/Makefile b/Samples/5_Domain_Specific/recursiveGaussian/Makefile index ae114d95..f2d15106 100644 --- a/Samples/5_Domain_Specific/recursiveGaussian/Makefile +++ b/Samples/5_Domain_Specific/recursiveGaussian/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/recursiveGaussian/README.md b/Samples/5_Domain_Specific/recursiveGaussian/README.md index 884b85c1..090f676f 100644 --- a/Samples/5_Domain_Specific/recursiveGaussian/README.md +++ b/Samples/5_Domain_Specific/recursiveGaussian/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2017.vcxproj b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2017.vcxproj index 621fa9d2..e50cdb89 100644 --- a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2019.vcxproj b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2019.vcxproj index 44420ccc..90818071 100644 --- a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2022.vcxproj b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2022.vcxproj index 5ed86d80..6cd1d059 100644 --- a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10/README.md b/Samples/5_Domain_Specific/simpleD3D10/README.md index 00f0e9c8..b8920771 100644 --- a/Samples/5_Domain_Specific/simpleD3D10/README.md +++ b/Samples/5_Domain_Specific/simpleD3D10/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaGetErrorString, cudaGraphicsResourceGetMappedPoi ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2017.vcxproj index 127a1f5a..c0835d3c 100644 --- a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2019.vcxproj index f32ab0be..9550b91b 100644 --- a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2022.vcxproj index 88dd181c..a2f55214 100644 --- a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/README.md b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/README.md index 47faa204..9847a94c 100644 --- a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/README.md +++ b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMalloc, cudaUnbindTexture, cudaGetEr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2017.vcxproj index ca9222a0..bf6351f2 100644 --- a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2019.vcxproj index 7ae056a1..8e00b3c4 100644 --- a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2022.vcxproj index 38105d26..fa0b58ae 100644 --- a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10Texture/README.md b/Samples/5_Domain_Specific/simpleD3D10Texture/README.md index e0175859..243fe375 100644 --- a/Samples/5_Domain_Specific/simpleD3D10Texture/README.md +++ b/Samples/5_Domain_Specific/simpleD3D10Texture/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMalloc, cudaMallocPitch, cudaGetErrorString, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2017.vcxproj index b07a8b5d..e0cc4b21 100644 --- a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2019.vcxproj index f26d3478..1396403a 100644 --- a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2022.vcxproj index 7e0f43c4..393cd14b 100644 --- a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11/README.md b/Samples/5_Domain_Specific/simpleD3D11/README.md index 15993e1d..8b9f5e01 100644 --- a/Samples/5_Domain_Specific/simpleD3D11/README.md +++ b/Samples/5_Domain_Specific/simpleD3D11/README.md @@ -30,7 +30,7 @@ cudaImportKeyedMutex, cudaExternalMemoryGetMappedBuffer, cudaStreamCreateWithFla ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2017.vcxproj index bee0e798..da17569e 100644 --- a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2019.vcxproj index 1f9ac0dc..d872e58a 100644 --- a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2022.vcxproj index 6ff93290..4d5a1499 100644 --- a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11Texture/README.md b/Samples/5_Domain_Specific/simpleD3D11Texture/README.md index db3facde..19aaf8a5 100644 --- a/Samples/5_Domain_Specific/simpleD3D11Texture/README.md +++ b/Samples/5_Domain_Specific/simpleD3D11Texture/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMalloc, cudaMallocPitch, cudaGetErrorString, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2017.vcxproj index 6954034d..cf5f6ba7 100644 --- a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2019.vcxproj index 0ea910a7..17748bff 100644 --- a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2022.vcxproj index 34972bea..53788508 100644 --- a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D12/README.md b/Samples/5_Domain_Specific/simpleD3D12/README.md index 1d8a77b7..ad39407f 100644 --- a/Samples/5_Domain_Specific/simpleD3D12/README.md +++ b/Samples/5_Domain_Specific/simpleD3D12/README.md @@ -30,7 +30,7 @@ cudaWaitExternalSemaphoresAsync, cudaExternalMemoryGetMappedBuffer, cudaImportEx ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2017.vcxproj index 9496182f..2055ef4c 100644 --- a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2019.vcxproj index ba258150..43e423a1 100644 --- a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2019.vcxproj @@ -39,7 +39,7 @@ - + @@ -120,6 +120,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2022.vcxproj index c2484f17..988cc318 100644 --- a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2022.vcxproj @@ -39,7 +39,7 @@ - + @@ -120,6 +120,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9/README.md b/Samples/5_Domain_Specific/simpleD3D9/README.md index 3e712dd8..c81927c3 100644 --- a/Samples/5_Domain_Specific/simpleD3D9/README.md +++ b/Samples/5_Domain_Specific/simpleD3D9/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaGraphicsResourceGetMappedPointer, cudaGetLastErr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2017.vcxproj index 53ce5f53..79bd8ec1 100644 --- a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2019.vcxproj index 4f2b4979..1b452b3d 100644 --- a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2022.vcxproj index b230029e..480a6384 100644 --- a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9Texture/README.md b/Samples/5_Domain_Specific/simpleD3D9Texture/README.md index eddc8fc6..70af0508 100644 --- a/Samples/5_Domain_Specific/simpleD3D9Texture/README.md +++ b/Samples/5_Domain_Specific/simpleD3D9Texture/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMalloc, cudaMallocPitch, cudaFree, cudaGetLastEr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2017.vcxproj index 8780cd87..82922ed1 100644 --- a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2019.vcxproj index 3603498f..35dbd00e 100644 --- a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2022.vcxproj index 994a725a..a8093424 100644 --- a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleGL/Makefile b/Samples/5_Domain_Specific/simpleGL/Makefile index 17769a6f..caf7fd38 100644 --- a/Samples/5_Domain_Specific/simpleGL/Makefile +++ b/Samples/5_Domain_Specific/simpleGL/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleGL/README.md b/Samples/5_Domain_Specific/simpleGL/README.md index 6144bfa6..2419f043 100644 --- a/Samples/5_Domain_Specific/simpleGL/README.md +++ b/Samples/5_Domain_Specific/simpleGL/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2017.vcxproj index df1ac443..fc775d75 100644 --- a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2019.vcxproj index 4089f3cb..e284230d 100644 --- a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2022.vcxproj index d8138a12..a35bda7e 100644 --- a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleGLES/Makefile b/Samples/5_Domain_Specific/simpleGLES/Makefile index 05424cd0..06902f2a 100644 --- a/Samples/5_Domain_Specific/simpleGLES/Makefile +++ b/Samples/5_Domain_Specific/simpleGLES/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleGLES/README.md b/Samples/5_Domain_Specific/simpleGLES/README.md index b640a766..f22b105f 100644 --- a/Samples/5_Domain_Specific/simpleGLES/README.md +++ b/Samples/5_Domain_Specific/simpleGLES/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleGLES_EGLOutput/Makefile b/Samples/5_Domain_Specific/simpleGLES_EGLOutput/Makefile index 4fdd337b..01de1205 100644 --- a/Samples/5_Domain_Specific/simpleGLES_EGLOutput/Makefile +++ b/Samples/5_Domain_Specific/simpleGLES_EGLOutput/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleGLES_EGLOutput/README.md b/Samples/5_Domain_Specific/simpleGLES_EGLOutput/README.md index 06d80d9e..9af216b4 100644 --- a/Samples/5_Domain_Specific/simpleGLES_EGLOutput/README.md +++ b/Samples/5_Domain_Specific/simpleGLES_EGLOutput/README.md @@ -35,7 +35,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleGLES_screen/Makefile b/Samples/5_Domain_Specific/simpleGLES_screen/Makefile index 4a764a2e..f2672bd8 100644 --- a/Samples/5_Domain_Specific/simpleGLES_screen/Makefile +++ b/Samples/5_Domain_Specific/simpleGLES_screen/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleGLES_screen/README.md b/Samples/5_Domain_Specific/simpleGLES_screen/README.md index f4a89cae..067bdaf4 100644 --- a/Samples/5_Domain_Specific/simpleGLES_screen/README.md +++ b/Samples/5_Domain_Specific/simpleGLES_screen/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleVulkan/Makefile b/Samples/5_Domain_Specific/simpleVulkan/Makefile index 697cb867..098a6d9b 100644 --- a/Samples/5_Domain_Specific/simpleVulkan/Makefile +++ b/Samples/5_Domain_Specific/simpleVulkan/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleVulkan/README.md b/Samples/5_Domain_Specific/simpleVulkan/README.md index baee10f3..6d1a3282 100644 --- a/Samples/5_Domain_Specific/simpleVulkan/README.md +++ b/Samples/5_Domain_Specific/simpleVulkan/README.md @@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaExternalMemoryGetMappedBuffer, cudaSignalSemaphor ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2017.vcxproj index 11419289..ec7cfba6 100644 --- a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -121,6 +121,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2019.vcxproj index 691357fd..8f3965a3 100644 --- a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2022.vcxproj index 46ada277..433f74cc 100644 --- a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleVulkanMMAP/Makefile b/Samples/5_Domain_Specific/simpleVulkanMMAP/Makefile index aace0d8b..420d0307 100644 --- a/Samples/5_Domain_Specific/simpleVulkanMMAP/Makefile +++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleVulkanMMAP/README.md b/Samples/5_Domain_Specific/simpleVulkanMMAP/README.md index b1060db7..ba2bd918 100644 --- a/Samples/5_Domain_Specific/simpleVulkanMMAP/README.md +++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/README.md @@ -33,7 +33,7 @@ cudaWaitExternalSemaphoresAsync, cudaImportExternalSemaphore, cudaDeviceGetAttri ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2017.vcxproj index 630d6c46..d0d825ec 100644 --- a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -123,6 +123,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2019.vcxproj index d4e5a06a..5943395b 100644 --- a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2022.vcxproj index b5487d98..5c47a7d0 100644 --- a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/5_Domain_Specific/smokeParticles/Makefile b/Samples/5_Domain_Specific/smokeParticles/Makefile index 9e127436..83977eaa 100644 --- a/Samples/5_Domain_Specific/smokeParticles/Makefile +++ b/Samples/5_Domain_Specific/smokeParticles/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/smokeParticles/README.md b/Samples/5_Domain_Specific/smokeParticles/README.md index 17d50074..366dea3d 100644 --- a/Samples/5_Domain_Specific/smokeParticles/README.md +++ b/Samples/5_Domain_Specific/smokeParticles/README.md @@ -30,7 +30,7 @@ cudaExtent, cudaPitchedPtr, cudaCreateTextureObject, cudaMemcpyToSymbol ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2017.vcxproj b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2017.vcxproj index b22c13e5..ea3b5093 100644 --- a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -137,6 +137,6 @@ - + diff --git a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2019.vcxproj b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2019.vcxproj index 02d81bdf..11119a14 100644 --- a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -133,6 +133,6 @@ - + diff --git a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2022.vcxproj b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2022.vcxproj index b315bf2c..4dec9439 100644 --- a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -133,6 +133,6 @@ - + diff --git a/Samples/5_Domain_Specific/stereoDisparity/Makefile b/Samples/5_Domain_Specific/stereoDisparity/Makefile index 87dbd9f1..920bd212 100644 --- a/Samples/5_Domain_Specific/stereoDisparity/Makefile +++ b/Samples/5_Domain_Specific/stereoDisparity/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/stereoDisparity/README.md b/Samples/5_Domain_Specific/stereoDisparity/README.md index 62a37a50..182b109c 100644 --- a/Samples/5_Domain_Specific/stereoDisparity/README.md +++ b/Samples/5_Domain_Specific/stereoDisparity/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaEventSynchronize, cudaDeviceSynchronize, cudaCreateTex ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2017.vcxproj b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2017.vcxproj index baa95190..65f05375 100644 --- a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2019.vcxproj b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2019.vcxproj index 96d8377b..efdab434 100644 --- a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2022.vcxproj b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2022.vcxproj index ff27d19b..8f3d040f 100644 --- a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeFiltering/Makefile b/Samples/5_Domain_Specific/volumeFiltering/Makefile index cf8708ca..67d3cae5 100644 --- a/Samples/5_Domain_Specific/volumeFiltering/Makefile +++ b/Samples/5_Domain_Specific/volumeFiltering/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/volumeFiltering/README.md b/Samples/5_Domain_Specific/volumeFiltering/README.md index 3e88c264..f07c7b27 100644 --- a/Samples/5_Domain_Specific/volumeFiltering/README.md +++ b/Samples/5_Domain_Specific/volumeFiltering/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGraphicsMapResources, cudaDestroySurfaceObject, cudaExtent, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2017.vcxproj b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2017.vcxproj index b7244993..5a1b9424 100644 --- a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -122,6 +122,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2019.vcxproj b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2019.vcxproj index bc675ab8..17b3ac6f 100644 --- a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2022.vcxproj b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2022.vcxproj index f863efdc..73849d6e 100644 --- a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeRender/Makefile b/Samples/5_Domain_Specific/volumeRender/Makefile index 5b5d73a3..f6bcf9c5 100644 --- a/Samples/5_Domain_Specific/volumeRender/Makefile +++ b/Samples/5_Domain_Specific/volumeRender/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/volumeRender/README.md b/Samples/5_Domain_Specific/volumeRender/README.md index 322973d8..57e40b0f 100644 --- a/Samples/5_Domain_Specific/volumeRender/README.md +++ b/Samples/5_Domain_Specific/volumeRender/README.md @@ -30,7 +30,7 @@ cudaProfilerStop, cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaF ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2017.vcxproj b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2017.vcxproj index a7e458a2..f70cae03 100644 --- a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2019.vcxproj b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2019.vcxproj index ea181ded..4c63b617 100644 --- a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2022.vcxproj b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2022.vcxproj index 83bba752..efe37a04 100644 --- a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/vulkanImageCUDA/Makefile b/Samples/5_Domain_Specific/vulkanImageCUDA/Makefile index 53c5bc90..d9750da5 100644 --- a/Samples/5_Domain_Specific/vulkanImageCUDA/Makefile +++ b/Samples/5_Domain_Specific/vulkanImageCUDA/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/vulkanImageCUDA/README.md b/Samples/5_Domain_Specific/vulkanImageCUDA/README.md index 76377bda..c0cfa7f8 100644 --- a/Samples/5_Domain_Specific/vulkanImageCUDA/README.md +++ b/Samples/5_Domain_Specific/vulkanImageCUDA/README.md @@ -30,7 +30,7 @@ cudaVkSemaphoreSignal, cudaWaitExternalSemaphoresAsync, cudaMemcpy, cudaVkImport ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2017.vcxproj b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2017.vcxproj index 6ef89f26..4e091726 100644 --- a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2019.vcxproj b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2019.vcxproj index e6d168a0..c7f2af0c 100644 --- a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2022.vcxproj b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2022.vcxproj index eb971331..5bec4cef 100644 --- a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/6_Performance/README.md b/Samples/6_Performance/README.md index 64a4b10a..c44b0ba2 100644 --- a/Samples/6_Performance/README.md +++ b/Samples/6_Performance/README.md @@ -10,3 +10,5 @@ This sample demonstrates Matrix Transpose. Different performance are shown to a ### [UnifiedMemoryPerf](./UnifiedMemoryPerf) This sample demonstrates the performance comparision using matrix multiplication kernel of Unified Memory with/without hints and other types of memory like zero copy buffers, pageable, pagelocked memory performing synchronous and Asynchronous transfers on a single GPU. +### [cudaGraphsPerfScaling](./cudaGraphsPerfScaling) +This sample demonstrates the performance characteristics of cuda graphs. It is focused on how the apis scale with graph size. diff --git a/Samples/6_Performance/UnifiedMemoryPerf/Makefile b/Samples/6_Performance/UnifiedMemoryPerf/Makefile index a7230f13..dfee2cd4 100644 --- a/Samples/6_Performance/UnifiedMemoryPerf/Makefile +++ b/Samples/6_Performance/UnifiedMemoryPerf/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/6_Performance/UnifiedMemoryPerf/README.md b/Samples/6_Performance/UnifiedMemoryPerf/README.md index 99b982ec..dd9a9236 100644 --- a/Samples/6_Performance/UnifiedMemoryPerf/README.md +++ b/Samples/6_Performance/UnifiedMemoryPerf/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaStreamDestroy, cudaMemPrefetchAsync, cudaFree, cudaMallocHost, c ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj index ddcfde4a..439481fe 100644 --- a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj +++ b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj index 231f8e5a..fdc41a74 100644 --- a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj +++ b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2022.vcxproj b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2022.vcxproj index 400137a8..b4e92853 100644 --- a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2022.vcxproj +++ b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/6_Performance/alignedTypes/Makefile b/Samples/6_Performance/alignedTypes/Makefile index 191b3e09..10bcda7e 100644 --- a/Samples/6_Performance/alignedTypes/Makefile +++ b/Samples/6_Performance/alignedTypes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/6_Performance/alignedTypes/README.md b/Samples/6_Performance/alignedTypes/README.md index d9bd0e89..8ac983e6 100644 --- a/Samples/6_Performance/alignedTypes/README.md +++ b/Samples/6_Performance/alignedTypes/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMemset, cudaMalloc, cudaGetDevi ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/6_Performance/alignedTypes/alignedTypes_vs2017.vcxproj b/Samples/6_Performance/alignedTypes/alignedTypes_vs2017.vcxproj index 970929f2..f177e1bc 100644 --- a/Samples/6_Performance/alignedTypes/alignedTypes_vs2017.vcxproj +++ b/Samples/6_Performance/alignedTypes/alignedTypes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/6_Performance/alignedTypes/alignedTypes_vs2019.vcxproj b/Samples/6_Performance/alignedTypes/alignedTypes_vs2019.vcxproj index c0110508..fcf174ec 100644 --- a/Samples/6_Performance/alignedTypes/alignedTypes_vs2019.vcxproj +++ b/Samples/6_Performance/alignedTypes/alignedTypes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/6_Performance/alignedTypes/alignedTypes_vs2022.vcxproj b/Samples/6_Performance/alignedTypes/alignedTypes_vs2022.vcxproj index fcc2c9e7..bb200e26 100644 --- a/Samples/6_Performance/alignedTypes/alignedTypes_vs2022.vcxproj +++ b/Samples/6_Performance/alignedTypes/alignedTypes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/c_cpp_properties.json b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/c_cpp_properties.json new file mode 100644 index 00000000..f0066b0f --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/c_cpp_properties.json @@ -0,0 +1,18 @@ +{ + "configurations": [ + { + "name": "Linux", + "includePath": [ + "${workspaceFolder}/**", + "${workspaceFolder}/../../../Common" + ], + "defines": [], + "compilerPath": "/usr/local/cuda/bin/nvcc", + "cStandard": "gnu17", + "cppStandard": "gnu++14", + "intelliSenseMode": "linux-gcc-x64", + "configurationProvider": "ms-vscode.makefile-tools" + } + ], + "version": 4 +} diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/extensions.json b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/extensions.json new file mode 100644 index 00000000..c7eb54dc --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/extensions.json @@ -0,0 +1,7 @@ +{ + "recommendations": [ + "nvidia.nsight-vscode-edition", + "ms-vscode.cpptools", + "ms-vscode.makefile-tools" + ] +} diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/launch.json b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/launch.json new file mode 100644 index 00000000..c7dfe643 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/launch.json @@ -0,0 +1,10 @@ +{ + "configurations": [ + { + "name": "CUDA C++: Launch", + "type": "cuda-gdb", + "request": "launch", + "program": "${workspaceFolder}/cudaGraphsPerfScaling" + } + ] +} diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/tasks.json b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/tasks.json new file mode 100644 index 00000000..4509aeb1 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/tasks.json @@ -0,0 +1,15 @@ +{ + "version": "2.0.0", + "tasks": [ + { + "label": "sample", + "type": "shell", + "command": "make dbg=1", + "problemMatcher": ["$nvcc"], + "group": { + "kind": "build", + "isDefault": true + } + } + ] +} diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/Makefile b/Samples/6_Performance/cudaGraphsPerfScaling/Makefile new file mode 100644 index 00000000..4bc85985 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/Makefile @@ -0,0 +1,363 @@ +################################################################################ +# Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions +# are met: +# * Redistributions of source code must retain the above copyright +# notice, this list of conditions and the following disclaimer. +# * Redistributions in binary form must reproduce the above copyright +# notice, this list of conditions and the following disclaimer in the +# documentation and/or other materials provided with the distribution. +# * Neither the name of NVIDIA CORPORATION nor the names of its +# contributors may be used to endorse or promote products derived +# from this software without specific prior written permission. +# +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY +# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR +# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, +# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, +# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY +# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +# +################################################################################ +# +# Makefile project only supported on Mac OS X and Linux Platforms) +# +################################################################################ + +# Location of the CUDA Toolkit +CUDA_PATH ?= /usr/local/cuda + +############################## +# start deprecated interface # +############################## +ifeq ($(x86_64),1) + $(info WARNING - x86_64 variable has been deprecated) + $(info WARNING - please use TARGET_ARCH=x86_64 instead) + TARGET_ARCH ?= x86_64 +endif +ifeq ($(ARMv7),1) + $(info WARNING - ARMv7 variable has been deprecated) + $(info WARNING - please use TARGET_ARCH=armv7l instead) + TARGET_ARCH ?= armv7l +endif +ifeq ($(aarch64),1) + $(info WARNING - aarch64 variable has been deprecated) + $(info WARNING - please use TARGET_ARCH=aarch64 instead) + TARGET_ARCH ?= aarch64 +endif +ifeq ($(ppc64le),1) + $(info WARNING - ppc64le variable has been deprecated) + $(info WARNING - please use TARGET_ARCH=ppc64le instead) + TARGET_ARCH ?= ppc64le +endif +ifneq ($(GCC),) + $(info WARNING - GCC variable has been deprecated) + $(info WARNING - please use HOST_COMPILER=$(GCC) instead) + HOST_COMPILER ?= $(GCC) +endif +ifneq ($(abi),) + $(error ERROR - abi variable has been removed) +endif +############################ +# end deprecated interface # +############################ + +# architecture +HOST_ARCH := $(shell uname -m) +TARGET_ARCH ?= $(HOST_ARCH) +ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le armv7l)) + ifneq ($(TARGET_ARCH),$(HOST_ARCH)) + ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le)) + TARGET_SIZE := 64 + else ifneq (,$(filter $(TARGET_ARCH),armv7l)) + TARGET_SIZE := 32 + endif + else + TARGET_SIZE := $(shell getconf LONG_BIT) + endif +else + $(error ERROR - unsupported value $(TARGET_ARCH) for TARGET_ARCH!) +endif + +# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now. +ifeq ($(HOST_ARCH),aarch64) + ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null)) + HOST_ARCH := sbsa + TARGET_ARCH := sbsa + endif +endif + +ifneq ($(TARGET_ARCH),$(HOST_ARCH)) + ifeq (,$(filter $(HOST_ARCH)-$(TARGET_ARCH),aarch64-armv7l x86_64-armv7l x86_64-aarch64 x86_64-sbsa x86_64-ppc64le)) + $(error ERROR - cross compiling from $(HOST_ARCH) to $(TARGET_ARCH) is not supported!) + endif +endif + +# When on native aarch64 system with userspace of 32-bit, change TARGET_ARCH to armv7l +ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_SIZE),aarch64-aarch64-32) + TARGET_ARCH = armv7l +endif + +# operating system +HOST_OS := $(shell uname -s 2>/dev/null | tr "[:upper:]" "[:lower:]") +TARGET_OS ?= $(HOST_OS) +ifeq (,$(filter $(TARGET_OS),linux darwin qnx android)) + $(error ERROR - unsupported value $(TARGET_OS) for TARGET_OS!) +endif + +# host compiler +ifdef HOST_COMPILER + CUSTOM_HOST_COMPILER = 1 +endif + +ifeq ($(TARGET_OS),darwin) + ifeq ($(shell expr `xcodebuild -version | grep -i xcode | awk '{print $$2}' | cut -d'.' -f1` \>= 5),1) + HOST_COMPILER ?= clang++ + endif +else ifneq ($(TARGET_ARCH),$(HOST_ARCH)) + ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-armv7l) + ifeq ($(TARGET_OS),linux) + HOST_COMPILER ?= arm-linux-gnueabihf-g++ + else ifeq ($(TARGET_OS),qnx) + ifeq ($(QNX_HOST),) + $(error ERROR - QNX_HOST must be passed to the QNX host toolchain) + endif + ifeq ($(QNX_TARGET),) + $(error ERROR - QNX_TARGET must be passed to the QNX target toolchain) + endif + export QNX_HOST + export QNX_TARGET + HOST_COMPILER ?= $(QNX_HOST)/usr/bin/arm-unknown-nto-qnx6.6.0eabi-g++ + else ifeq ($(TARGET_OS),android) + HOST_COMPILER ?= arm-linux-androideabi-g++ + endif + else ifeq ($(TARGET_ARCH),aarch64) + ifeq ($(TARGET_OS), linux) + HOST_COMPILER ?= aarch64-linux-gnu-g++ + else ifeq ($(TARGET_OS),qnx) + ifeq ($(QNX_HOST),) + $(error ERROR - QNX_HOST must be passed to the QNX host toolchain) + endif + ifeq ($(QNX_TARGET),) + $(error ERROR - QNX_TARGET must be passed to the QNX target toolchain) + endif + export QNX_HOST + export QNX_TARGET + HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++ + else ifeq ($(TARGET_OS), android) + HOST_COMPILER ?= aarch64-linux-android-clang++ + endif + else ifeq ($(TARGET_ARCH),sbsa) + HOST_COMPILER ?= aarch64-linux-gnu-g++ + else ifeq ($(TARGET_ARCH),ppc64le) + HOST_COMPILER ?= powerpc64le-linux-gnu-g++ + endif +endif +HOST_COMPILER ?= g++ +NVCC := $(CUDA_PATH)/bin/nvcc -ccbin $(HOST_COMPILER) + +# internal flags +NVCCFLAGS := -m${TARGET_SIZE} +CCFLAGS := +LDFLAGS := + +# build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + +ifeq ($(TARGET_OS),darwin) + LDFLAGS += -rpath $(CUDA_PATH)/lib + CCFLAGS += -arch $(HOST_ARCH) +else ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-armv7l-linux) + LDFLAGS += --dynamic-linker=/lib/ld-linux-armhf.so.3 + CCFLAGS += -mfloat-abi=hard +else ifeq ($(TARGET_OS),android) + LDFLAGS += -pie + CCFLAGS += -fpie -fpic -fexceptions +endif + +ifneq ($(TARGET_ARCH),$(HOST_ARCH)) + ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) + ifneq ($(TARGET_FS),) + GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6) + ifeq ($(GCCVERSIONLTEQ46),1) + CCFLAGS += --sysroot=$(TARGET_FS) + endif + LDFLAGS += --sysroot=$(TARGET_FS) + LDFLAGS += -rpath-link=$(TARGET_FS)/lib + LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib + LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/arm-linux-gnueabihf + endif + endif + ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux) + ifneq ($(TARGET_FS),) + GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6) + ifeq ($(GCCVERSIONLTEQ46),1) + CCFLAGS += --sysroot=$(TARGET_FS) + endif + LDFLAGS += --sysroot=$(TARGET_FS) + LDFLAGS += -rpath-link=$(TARGET_FS)/lib -L$(TARGET_FS)/lib + LDFLAGS += -rpath-link=$(TARGET_FS)/lib/aarch64-linux-gnu -L$(TARGET_FS)/lib/aarch64-linux-gnu + LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib + LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu + LDFLAGS += --unresolved-symbols=ignore-in-shared-libs + CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm + CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu + endif + endif + ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) + NVCCFLAGS += -D_QNX_SOURCE + NVCCFLAGS += --qpp-config 8.3.0,gcc_ntoaarch64le + CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu + LDFLAGS += -lsocket + LDFLAGS += -L/usr/lib/aarch64-qnx-gnu + CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu" + ifdef TARGET_OVERRIDE + LDFLAGS += -lslog2 + endif + + ifneq ($(TARGET_FS),) + LDFLAGS += -L$(TARGET_FS)/usr/lib + CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib" + LDFLAGS += -L$(TARGET_FS)/usr/libnvidia + CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia" + CCFLAGS += -I$(TARGET_FS)/../include + endif + endif +endif + +ifdef TARGET_OVERRIDE # cuda toolkit targets override + NVCCFLAGS += -target-dir $(TARGET_OVERRIDE) +endif + +# Install directory of different arch +CUDA_INSTALL_TARGET_DIR := +ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) + CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-gnueabihf/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux) + CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),sbsa-linux) + CUDA_INSTALL_TARGET_DIR = targets/sbsa-linux/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-android) + CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-androideabi/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-android) + CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux-androideabi/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-qnx) + CUDA_INSTALL_TARGET_DIR = targets/ARMv7-linux-QNX/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) + CUDA_INSTALL_TARGET_DIR = targets/aarch64-qnx/ +else ifeq ($(TARGET_ARCH),ppc64le) + CUDA_INSTALL_TARGET_DIR = targets/ppc64le-linux/ +endif + +# Debug build flags +ifeq ($(dbg),1) + NVCCFLAGS += -g -G + BUILD_TYPE := debug +else + BUILD_TYPE := release +endif + +ALL_CCFLAGS := +ALL_CCFLAGS += $(NVCCFLAGS) +ALL_CCFLAGS += $(EXTRA_NVCCFLAGS) +ALL_CCFLAGS += $(addprefix -Xcompiler ,$(CCFLAGS)) +ALL_CCFLAGS += $(addprefix -Xcompiler ,$(EXTRA_CCFLAGS)) + +SAMPLE_ENABLED := 1 + +# This sample is not supported on Mac OSX +ifeq ($(TARGET_OS),darwin) + $(info >>> WARNING - cudaGraphsPerfScaling is not supported on Mac OSX - waiving sample <<<) + SAMPLE_ENABLED := 0 +endif + +ALL_LDFLAGS := +ALL_LDFLAGS += $(ALL_CCFLAGS) +ALL_LDFLAGS += $(addprefix -Xlinker ,$(LDFLAGS)) +ALL_LDFLAGS += $(addprefix -Xlinker ,$(EXTRA_LDFLAGS)) + +# Common includes and paths for CUDA +INCLUDES := -I../../../Common +LIBRARIES := + +################################################################################ + +# Gencode arguments +ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa)) +SMS ?= 53 61 70 72 75 80 86 87 90 +else +SMS ?= 50 52 60 61 70 75 80 86 89 90 +endif + +ifeq ($(SMS),) +$(info >>> WARNING - no SM architectures have been specified - waiving sample <<<) +SAMPLE_ENABLED := 0 +endif + +ifeq ($(GENCODE_FLAGS),) +# Generate SASS code for each SM architecture listed in $(SMS) +$(foreach sm,$(SMS),$(eval GENCODE_FLAGS += -gencode arch=compute_$(sm),code=sm_$(sm))) + +# Generate PTX code from the highest SM architecture in $(SMS) to guarantee forward-compatibility +HIGHEST_SM := $(lastword $(sort $(SMS))) +ifneq ($(HIGHEST_SM),) +GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM) +endif +endif + +ALL_CCFLAGS += --std=c++11 --threads 0 + +ifeq ($(SAMPLE_ENABLED),0) +EXEC ?= @echo "[@]" +endif + +################################################################################ + +# Target rules +all: build + +build: cudaGraphsPerfScaling + +check.deps: +ifeq ($(SAMPLE_ENABLED),0) + @echo "Sample will be waived due to the above missing dependencies" +else + @echo "Sample is ready - all dependencies have been met" +endif + +cudaGraphPerfScaling.o:cudaGraphPerfScaling.cu + $(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $< + +cudaGraphsPerfScaling: cudaGraphPerfScaling.o + $(EXEC) $(NVCC) $(ALL_LDFLAGS) $(GENCODE_FLAGS) -o $@ $+ $(LIBRARIES) + $(EXEC) mkdir -p ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE) + $(EXEC) cp $@ ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE) + +run: build + $(EXEC) ./cudaGraphsPerfScaling + +testrun: build + +clean: + rm -f cudaGraphsPerfScaling cudaGraphPerfScaling.o + rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/cudaGraphsPerfScaling + +clobber: clean diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/README.md b/Samples/6_Performance/cudaGraphsPerfScaling/README.md new file mode 100644 index 00000000..dce334be --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/README.md @@ -0,0 +1,70 @@ +# cudaGraphsPerfScaling - Cuda Graphs Perf Scaling + +## Description + +A simple program for characterizing cuda graph api performance with different sized graphs. + +## Key Concepts + +Performance Strategies + +## Supported SM Architectures + +[SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 5.3 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus) [SM 8.9 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus) + +## Supported OSes + +Linux, Windows + +## Supported CPU Architecture + +x86_64, armv7l + +## CUDA APIs involved + +### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html) +cudaStreamBeginCapture, cudaGraphInstantiate, cudaGraphLaunch, cudaGraphUpload + +## Prerequisites + +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. + +## Build and Run + +### Windows +The Windows samples are built using the Visual Studio IDE. Solution files (.sln) are provided for each supported version of Visual Studio, using the format: +``` +*_vs.sln - for Visual Studio +``` +Each individual sample has its own set of solution files in its directory: + +To build/examine all the samples at once, the complete solution files should be used. To build/examine a single sample, the individual sample solution files should be used. +> **Note:** Some samples require that the Microsoft DirectX SDK (June 2010 or newer) be installed and that the VC++ directory paths are properly set up (**Tools > Options...**). Check DirectX Dependencies section for details." + +### Linux +The Linux samples are built using makefiles. To use the makefiles, change the current directory to the sample directory you wish to build, and run make: +``` +$ cd +$ make +``` +The samples makefiles can take advantage of certain options: +* **TARGET_ARCH=** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, armv7l. + By default, TARGET_ARCH is set to HOST_ARCH. On a x86_64 machine, not setting TARGET_ARCH is the equivalent of setting TARGET_ARCH=x86_64.
+`$ make TARGET_ARCH=x86_64`
`$ make TARGET_ARCH=armv7l`
+ See [here](http://docs.nvidia.com/cuda/cuda-samples/index.html#cross-samples) for more details. +* **dbg=1** - build with debug symbols + ``` + $ make dbg=1 + ``` +* **SMS="A B ..."** - override the SM architectures for which the sample will be built, where `"A B ..."` is a space-delimited list of SM architectures. For example, to generate SASS for SM 50 and SM 60, use `SMS="50 60"`. + ``` + $ make SMS="50 60" + ``` + +* **HOST_COMPILER=** - override the default g++ host compiler. See the [Linux Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#system-requirements) for a list of supported host compilers. +``` + $ make HOST_COMPILER=g++ +``` + +## References (for more details) + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphPerfScaling.cu b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphPerfScaling.cu new file mode 100644 index 00000000..0e811744 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphPerfScaling.cu @@ -0,0 +1,434 @@ +/* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of NVIDIA CORPORATION nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR + * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, + * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, + * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR + * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY + * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/* + * This is a simple application showing the performance characteristics of cudaGraphs. + */ + +#define USE_NVTX + +#include +#include +#include +#include + +typedef volatile int LatchType; + +std::chrono::time_point getCpuTime() +{ + return std::chrono::high_resolution_clock::now(); +} + +template +float getMicroSecondDuration(T start, T end) +{ + return std::chrono::duration_cast(end-start).count() *.001f; +} + +float getAsyncMicroSecondDuration(cudaEvent_t start, cudaEvent_t end) +{ + float ms; + cudaEventElapsedTime(&ms, start, end); + return ms*1000; +} + +#ifdef USE_NVTX +#include + +class Tracer { +public: + Tracer(const char* name) { + nvtxRangePushA(name); + } + ~Tracer() { + nvtxRangePop(); + } +}; +#define RANGE(name) Tracer uniq_name_using_macros(name); +#define RANGE_PUSH(name) nvtxRangePushA(name) +#define RANGE_POP() nvtxRangePop(); +#else +#define RANGE(name) +#endif + +std::vector stream; +cudaEvent_t event[1]; +cudaEvent_t timingEvent[2]; + +struct hostData { + long long timeElapsed; + bool timeoutDetected; + long long timeElapsed2; + bool timeoutDetected2; + LatchType latch; + LatchType latch2; +}; + +struct hostData *hostData; + +__global__ void empty() +{ +} + +// Function to read the GPU nanosecond timer in a kernel +__device__ __forceinline__ unsigned long long __globaltimer() { + unsigned long long globaltimer; + asm volatile ("mov.u64 %0, %globaltimer;" : "=l"(globaltimer)); + return globaltimer; +} + +__global__ void delay(long long ticks) +{ + long long endTime = clock64() + ticks; + while (clock64() < endTime); +} + +__global__ void waitWithTimeout(long long nanoseconds, bool* timeoutDetected, long long *timeElapsed, LatchType* latch) +{ + long long startTime = __globaltimer(); + long long endTime = startTime + nanoseconds; + long long time = 0; + do { + time = __globaltimer(); + } while (time < endTime && (latch == NULL || *latch == 0)); + if (timeElapsed != NULL) { + *timeElapsed = time - startTime; + } + if (timeoutDetected) { + // report timeout if latch not detected + *timeoutDetected = (latch == NULL || *latch == 0); + } +} + +__global__ void preUploadAnnotation() +{ +} + +__global__ void postUploadAnnotation() +{ +} + +cudaGraph_t createParallelChain(int length, int width, bool singleEntry = false) +{ + RANGE_PUSH(__func__); + RANGE("capture"); + cudaGraph_t graph; + cudaStreamBeginCapture(stream[0], cudaStreamCaptureModeGlobal); + int streamIdx = 0; + if (singleEntry) { + empty<<<1,1,0,stream[streamIdx]>>>(); + } + + cudaEventRecord(event[0], stream[0]); + for (int i = 1; i < width; i++) { + cudaStreamWaitEvent(stream[i], event[0]); + } + + for (int i = 0; i < width; i++) { + streamIdx = i; + for (int j = 0; j < length; j++) { + empty<<<1,1,0,stream[streamIdx]>>>(); + } + } + + for (int i = 1; i < width; i++) { + cudaEventRecord(event[0], stream[i]); + cudaStreamWaitEvent(stream[0], event[0]); + } + + cudaStreamEndCapture(stream[0], &graph); + return graph; +} + +std::vector metricName; +std::vector metricValue; + +int counter2 = 0; +void runDemo(cudaGraph_t graph, int length, int width) +{ + cudaGraphExec_t graphExec; + { + auto start = getCpuTime(); + cudaGraphInstantiateWithFlags(&graphExec, graph, 0); + auto end = getCpuTime(); + metricName.push_back("instantiation"); + metricValue.push_back(getMicroSecondDuration(start, end)); + } + { + RANGE("launch including upload"); + auto start = getCpuTime(); + cudaGraphLaunch(graphExec, stream[0]); + auto apiReturn = getCpuTime(); + cudaStreamSynchronize(stream[0]); + auto streamSync = getCpuTime(); + metricName.push_back("first_launch_api"); + metricValue.push_back(getMicroSecondDuration(start, apiReturn)); + metricName.push_back("first_launch_total"); + metricValue.push_back(getMicroSecondDuration(start, streamSync)); + } + { + RANGE("repeat lauch in empty stream"); + auto start = getCpuTime(); + cudaGraphLaunch(graphExec, stream[0]); + auto apiReturn = getCpuTime(); + cudaStreamSynchronize(stream[0]); + auto streamSync = getCpuTime(); + metricName.push_back("repeat_launch_api"); + metricValue.push_back(getMicroSecondDuration(start, apiReturn)); + metricName.push_back("repeat_launch_total"); + metricValue.push_back(getMicroSecondDuration(start, streamSync)); + } + { + // re-instantiating the exec to simulate first launch into a busy stream. + cudaGraphExecDestroy(graphExec); + cudaGraphInstantiateWithFlags(&graphExec, graph, 0); + + long long maxTimeoutNanoSeconds = 4000 + 500*length*width; + waitWithTimeout<<<1,1,0,stream[0]>>>(maxTimeoutNanoSeconds, &hostData->timeoutDetected, &hostData->timeElapsed, &hostData->latch); + + RANGE("launch including upload in busy stream"); + cudaEventRecord(timingEvent[0], stream[0]); + cudaGraphLaunch(graphExec, stream[0]); + cudaEventRecord(timingEvent[1], stream[0]); + + hostData->latch = 1; + cudaStreamSynchronize(stream[0]); + + metricName.push_back("first_launch_device"); + metricValue.push_back(getAsyncMicroSecondDuration(timingEvent[0], timingEvent[1])); + metricName.push_back("blockingKernelTimeoutDetected"); + metricValue.push_back(hostData->timeoutDetected); + hostData->latch = 0; + hostData->timeoutDetected = 0; + } + { + RANGE("repeat lauch in busy stream"); + long long maxTimeoutNanoSeconds = 4000 + 500*length*width; + waitWithTimeout<<<1,1,0,stream[0]>>>(maxTimeoutNanoSeconds, &hostData->timeoutDetected, &hostData->timeElapsed, &hostData->latch); + cudaEventRecord(timingEvent[0], stream[0]); + cudaGraphLaunch(graphExec, stream[0]); + cudaEventRecord(timingEvent[1], stream[0]); + + hostData->latch = 1; + cudaStreamSynchronize(stream[0]); + + metricName.push_back("repeat_launch_device"); + metricValue.push_back(getAsyncMicroSecondDuration(timingEvent[0], timingEvent[1])); + metricName.push_back("blockingKernelTimeoutDetected"); + metricValue.push_back(hostData->timeoutDetected); + hostData->latch = 0; + hostData->timeoutDetected = 0; + } + { + // re-instantiating the exec to provide upload with work to do. + cudaGraphExecDestroy(graphExec); + cudaGraphInstantiateWithFlags(&graphExec, graph, 0); + long long maxTimeoutNanoSeconds = 4000 + 1000*length*width; + waitWithTimeout<<<1,1,0,stream[0]>>>(maxTimeoutNanoSeconds, &hostData->timeoutDetected2, &hostData->timeElapsed2, &hostData->latch2); + maxTimeoutNanoSeconds = 2000 + 500*length*width; + waitWithTimeout<<<1,1,0,stream[1]>>>(maxTimeoutNanoSeconds, &hostData->timeoutDetected, &hostData->timeElapsed, &hostData->latch); + + RANGE("uploading a graph off of the critical path"); + preUploadAnnotation<<<1,1,0,stream[1]>>>(); + cudaEventRecord(timingEvent[0], stream[0]); + auto start = getCpuTime(); + cudaGraphUpload(graphExec, stream[1]); + auto apiReturn = getCpuTime(); + cudaEventRecord(event[0],stream[1]); + cudaEventRecord(timingEvent[1], stream[0]); + postUploadAnnotation<<<1,1,0,stream[1]>>>(); + + hostData->latch = 1; // release the blocking kernel for the upload + cudaStreamWaitEvent(stream[0],event[0]); + cudaGraphLaunch(graphExec, stream[0]); + cudaEventSynchronize(event[0]); // upload done, similuate critical path being ready for the graph to run by the release of the second latch + + hostData->latch2 = 1; // release the work + cudaStreamSynchronize(stream[0]); + + metricName.push_back("upload_api_time"); + metricValue.push_back(getMicroSecondDuration(start, apiReturn)); + metricName.push_back("updoad_device_time"); + metricValue.push_back(getAsyncMicroSecondDuration(timingEvent[0], timingEvent[1])); + metricName.push_back("blockingKernelTimeoutDetected"); + metricValue.push_back(hostData->timeoutDetected); + + hostData->latch = 0; + hostData->latch2 = 0; + hostData->timeoutDetected = 0; + hostData->timeoutDetected2 = 0; + } + cudaGraphExecDestroy(graphExec); + cudaGraphDestroy(graph); + RANGE_POP(); +} + +void usage() { + printf("programName [outputFmt] [numTrials] [length] [width] [pattern] [stride] [maxLength] \n"); + printf("\toutputFmt - program output, default=3 (see below)\n"); + printf("\tnumTrials (per length)\n"); + printf("\tstarting length of the topology\n"); + printf("\twidth - width of the graph topology\n"); + printf("\tpattern - Structure of graph, default=0 (see below)\n"); + printf("\tstride - how to grow the length between each set of trials \n"); + printf("\tmaxLength - maximum lenght to try \n"); + printf("\n"); + printf("outputFmt can be:\n"); + printf("\t0: this help message\n"); + printf("\t1: csv data headers\n"); + printf("\t2: per trial csv data\n"); + printf("\t3: csv data & headers\n"); + printf("\t4: csv data is printed and trials are averaged for each length\n"); + printf("\t5: csv data is printed and trials are averaged for each length and headers are printed\n"); + printf("\n"); + printf("Pattern can be:\n"); + printf("\t0: No interconnect between branches\n"); + printf("\t1: Adds an extra root node before the initial fork\n"); +} + +int main(int argc, char **argv) +{ + if(argc < 1) { + usage(); + return 0; + } + + int numTrials=1, length=20, width=1, outputFmt=3, pattern=0, stride = 1; + if(argc > 1) outputFmt = atoi(argv[1]); + if(argc > 2) numTrials = atoi(argv[2]); + if(argc > 3) length= atoi(argv[3]); + if(argc > 4) width= atoi(argv[4]); + if(argc > 5) pattern = atoi(argv[5]); + if(argc > 6) stride = atoi(argv[6]); + int maxLength = length; + if(argc > 7) maxLength = atoi(argv[7]); + if (maxLength < length) { + maxLength = length; + } + + if((outputFmt & 4) && (outputFmt & 2)) { + printf("printing average and all samples doesn't make sense\n"); + } + + if(length == 0 || + width == 0 || + outputFmt == 0 || + outputFmt > 5 || + pattern > 1) + { + usage(); + return 0; + } + + bool singleEntry = (pattern == 1); + + cudaGraph_t graph; + + cudaFree(0); + cudaMallocHost(&hostData, sizeof(*hostData)); + stream.resize(width); + for (int i = 0; i < width; i++) + { + cudaStreamCreate(&stream[i]); + } + + cudaEventCreate(&event[0], cudaEventDisableTiming); + cudaEventCreate(&timingEvent[0], 0); + cudaEventCreate(&timingEvent[1], 0); + + { + RANGE("warmup"); + for (int i = 0; i < width; i++) + { + empty<<<1,1,0,stream[i]>>>(); + } + cudaStreamSynchronize(stream[0]); + + auto start = getCpuTime(); + graph = createParallelChain(length, width, singleEntry); + auto end = getCpuTime(); + metricValue.push_back(getMicroSecondDuration(start, end)); + metricName.push_back("capture"); + runDemo(graph, length, width); + } + + if (outputFmt & 1) { + printf("length, width, pattern, "); + for (int i = 0; i < metricName.size(); i++) { + printf("%s, ", metricName[i]); + } + printf("\r\n"); + } + + if (!(outputFmt & 6)) { + printf("skipping trials since no output is expected\n"); + return; + } + + std::vector metricTotal; + metricTotal.resize(metricValue.size()); + + while (length <= maxLength) { + for (int i = 0; i < numTrials; i++) { + metricName.clear(); + metricValue.clear(); + auto start = getCpuTime(); + graph = createParallelChain(length, width, singleEntry); + auto end = getCpuTime(); + metricValue.push_back(getMicroSecondDuration(start, end)); + + runDemo(graph, length, width); + + if (outputFmt & 2) { + printf("%d, %d, %d, ",length, width, pattern); + for (int i = 0; i < metricValue.size(); i++) { + printf("%0.3f, ", metricValue[i]); + } + printf("\r\n"); + } + if (outputFmt & 4) { + for (int i = 0; i < metricTotal.size(); i++) { + metricTotal[i] += metricValue[i]; + } + } + } + + if (outputFmt & 4) { + printf("%d, %d, %d, ",length, width, pattern); + for (int i = 0; i < metricTotal.size(); i++) { + printf("%0.3f, ", metricTotal[i]/numTrials); + metricTotal[i] = 0; + } + printf("\r\n"); + } + + length += stride; + } + + printf("\n"); +} + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.sln b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.sln new file mode 100644 index 00000000..9a8b80cd --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.sln @@ -0,0 +1,20 @@ + +Microsoft Visual Studio Solution File, Format Version 12.00 +# Visual Studio 2017 +Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cudaGraphsPerfScaling", "cudaGraphsPerfScaling_vs2017.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}" +EndProject +Global + GlobalSection(SolutionConfigurationPlatforms) = preSolution + Debug|x64 = Debug|x64 + Release|x64 = Release|x64 + EndGlobalSection + GlobalSection(ProjectConfigurationPlatforms) = postSolution + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64 + EndGlobalSection + GlobalSection(SolutionProperties) = preSolution + HideSolutionNode = FALSE + EndGlobalSection +EndGlobal diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.vcxproj b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.vcxproj new file mode 100644 index 00000000..88bfe7f1 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.vcxproj @@ -0,0 +1,112 @@ + + + + $(VCTargetsPath)\BuildCustomizations + + + + Debug + x64 + + + Release + x64 + + + + {997E0757-EA74-4A4E-A0FC-47D8C8831A15} + cudaGraphsPerfScaling_vs2017 + cudaGraphsPerfScaling + + + + $([Microsoft.Build.Utilities.ToolLocationHelper]::GetLatestSDKTargetPlatformVersion('Windows', '10.0')) + $(LatestTargetPlatformVersion) + $(WindowsTargetPlatformVersion) + + + + Application + MultiByte + v141 + + + true + + + true + + + + + + + + + + + $(Platform)/$(Configuration)/ + $(IncludePath) + AllRules.ruleset + + + + + ../../../bin/win64/$(Configuration)/ + + + + Level3 + WIN32;_MBCS;%(PreprocessorDefinitions) + ./;$(CudaToolkitDir)/include;../../../Common; + + + Console + cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies) + $(CudaToolkitLibDir); + $(OutDir)/cudaGraphsPerfScaling.exe + + + compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_89,sm_89;compute_90,sm_90; + -Xcompiler "/wd 4819" --threads 0 + ./;../../../Common + WIN32 + + + + + Disabled + MultiThreadedDebug + + + true + Default + + + MTd + 64 + + + + + MaxSpeed + MultiThreaded + + + false + UseLinkTimeCodeGeneration + + + MT + 64 + + + + + + + + + + + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.sln b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.sln new file mode 100644 index 00000000..5c443345 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.sln @@ -0,0 +1,20 @@ + +Microsoft Visual Studio Solution File, Format Version 12.00 +# Visual Studio 2019 +Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cudaGraphsPerfScaling", "cudaGraphsPerfScaling_vs2019.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}" +EndProject +Global + GlobalSection(SolutionConfigurationPlatforms) = preSolution + Debug|x64 = Debug|x64 + Release|x64 = Release|x64 + EndGlobalSection + GlobalSection(ProjectConfigurationPlatforms) = postSolution + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64 + EndGlobalSection + GlobalSection(SolutionProperties) = preSolution + HideSolutionNode = FALSE + EndGlobalSection +EndGlobal diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.vcxproj b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.vcxproj new file mode 100644 index 00000000..f2d60343 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.vcxproj @@ -0,0 +1,108 @@ + + + + $(VCTargetsPath)\BuildCustomizations + + + + Debug + x64 + + + Release + x64 + + + + {997E0757-EA74-4A4E-A0FC-47D8C8831A15} + cudaGraphsPerfScaling_vs2019 + cudaGraphsPerfScaling + + + + + Application + MultiByte + v142 + 10.0 + + + true + + + true + + + + + + + + + + + $(Platform)/$(Configuration)/ + $(IncludePath) + AllRules.ruleset + + + + + ../../../bin/win64/$(Configuration)/ + + + + Level3 + WIN32;_MBCS;%(PreprocessorDefinitions) + ./;$(CudaToolkitDir)/include;../../../Common; + + + Console + cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies) + $(CudaToolkitLibDir); + $(OutDir)/cudaGraphsPerfScaling.exe + + + compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_89,sm_89;compute_90,sm_90; + -Xcompiler "/wd 4819" --threads 0 + ./;../../../Common + WIN32 + + + + + Disabled + MultiThreadedDebug + + + true + Default + + + MTd + 64 + + + + + MaxSpeed + MultiThreaded + + + false + UseLinkTimeCodeGeneration + + + MT + 64 + + + + + + + + + + + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.sln b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.sln new file mode 100644 index 00000000..76280160 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.sln @@ -0,0 +1,20 @@ + +Microsoft Visual Studio Solution File, Format Version 12.00 +# Visual Studio 2022 +Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cudaGraphsPerfScaling", "cudaGraphsPerfScaling_vs2022.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}" +EndProject +Global + GlobalSection(SolutionConfigurationPlatforms) = preSolution + Debug|x64 = Debug|x64 + Release|x64 = Release|x64 + EndGlobalSection + GlobalSection(ProjectConfigurationPlatforms) = postSolution + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64 + EndGlobalSection + GlobalSection(SolutionProperties) = preSolution + HideSolutionNode = FALSE + EndGlobalSection +EndGlobal diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.vcxproj b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.vcxproj new file mode 100644 index 00000000..30384f07 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.vcxproj @@ -0,0 +1,108 @@ + + + + $(VCTargetsPath)\BuildCustomizations + + + + Debug + x64 + + + Release + x64 + + + + {997E0757-EA74-4A4E-A0FC-47D8C8831A15} + cudaGraphsPerfScaling_vs2022 + cudaGraphsPerfScaling + + + + + Application + MultiByte + v143 + 10.0 + + + true + + + true + + + + + + + + + + + $(Platform)/$(Configuration)/ + $(IncludePath) + AllRules.ruleset + + + + + ../../../bin/win64/$(Configuration)/ + + + + Level3 + WIN32;_MBCS;%(PreprocessorDefinitions) + ./;$(CudaToolkitDir)/include;../../../Common; + + + Console + cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies) + $(CudaToolkitLibDir); + $(OutDir)/cudaGraphsPerfScaling.exe + + + compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_89,sm_89;compute_90,sm_90; + -Xcompiler "/wd 4819" --threads 0 + ./;../../../Common + WIN32 + + + + + Disabled + MultiThreadedDebug + + + true + Default + + + MTd + 64 + + + + + MaxSpeed + MultiThreaded + + + false + UseLinkTimeCodeGeneration + + + MT + 64 + + + + + + + + + + + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/dataCollection.bash b/Samples/6_Performance/cudaGraphsPerfScaling/dataCollection.bash new file mode 100644 index 00000000..a382be10 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/dataCollection.bash @@ -0,0 +1,17 @@ +GPU=$1 +DRIVER_VERSION=$2 +BINARY=./cudaGraphsPerfScaling +datadir=PERF_DATA + +suffix=$DRIVER_VERSION +prefix=$GPU +mkdir -p $datadir + +trials=600 + +width=1 +nvidia-smi > $datadir/${prefix}_info_${suffix}.txt +$BINARY 5 $trials 1 $width 0 1 256 > $datadir/${prefix}_${width}_small_${suffix}.csv +$BINARY 5 $trials 1 $width 0 32 2048 > $datadir/${prefix}_${width}_large_${suffix}.csv +width=4 +$BINARY 5 $trials 1 $width 0 1 256 > $datadir/${prefix}_${width}_small_${suffix}.csv diff --git a/Samples/6_Performance/transpose/Makefile b/Samples/6_Performance/transpose/Makefile index 1f6d156e..6885a8d0 100644 --- a/Samples/6_Performance/transpose/Makefile +++ b/Samples/6_Performance/transpose/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/6_Performance/transpose/README.md b/Samples/6_Performance/transpose/README.md index e069e1c6..32c10bb1 100644 --- a/Samples/6_Performance/transpose/README.md +++ b/Samples/6_Performance/transpose/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaMalloc, cudaFree, cudaGetLastError, cudaEventSynchronize, cudaEv ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/6_Performance/transpose/transpose_vs2017.vcxproj b/Samples/6_Performance/transpose/transpose_vs2017.vcxproj index 22e928a7..195a6ce3 100644 --- a/Samples/6_Performance/transpose/transpose_vs2017.vcxproj +++ b/Samples/6_Performance/transpose/transpose_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/6_Performance/transpose/transpose_vs2019.vcxproj b/Samples/6_Performance/transpose/transpose_vs2019.vcxproj index 6993e848..7a901a8d 100644 --- a/Samples/6_Performance/transpose/transpose_vs2019.vcxproj +++ b/Samples/6_Performance/transpose/transpose_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/6_Performance/transpose/transpose_vs2022.vcxproj b/Samples/6_Performance/transpose/transpose_vs2022.vcxproj index 28938d90..56ce0896 100644 --- a/Samples/6_Performance/transpose/transpose_vs2022.vcxproj +++ b/Samples/6_Performance/transpose/transpose_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - +