Updating samples for CUDA 12.5

Fix cudaExtent.width set error.

.gitignore

@@ -0,0 +1 @@
+.vscode/*

CHANGELOG.md

@@ -1,5 +1,31 @@
 ## Changelog
 
+### CUDA 12.5
+
+### CUDA 12.4
+* Added graphConditionalNodes Sample
+
+### CUDA 12.3
+* Added cuDLA samples
+* Fixed jitLto regression
+
+### CUDA 12.2
+* libNVVM samples received updates
+* Fixed jitLto Case issues
+* Enabled HOST_COMPILER flag to the makefiles for GCC which is untested but may still work.
+
+### CUDA 12.1
+* Added new sample for Large Kernels
+
+### CUDA 12.0
+* Added new flags for JIT compiling 
+* Removed deprecated APIs in Hopper Architecture
+
+### CUDA 11.6
+* Added new folder structure for samples
+* Added support of Visual Studio 2022 to all samples supported on [Windows](#windows-1).
+* All CUDA samples are now only available on [GitHub](https://github.com/nvidia/cuda-samples). They are no longer available via CUDA toolkit.
+
 ### CUDA 11.5
 * Added `cuDLAHybridMode`. Demonstrate usage of cuDLA in hybrid mode.
 * Added `cuDLAStandaloneMode`. Demonstrate usage of cuDLA in standalone mode.
@@ -114,4 +140,4 @@ This is the first release of CUDA Samples on GitHub:
 *  Added `conjugateGradientMultiBlockCG`. Demonstrates a conjugate gradient solver on GPU using Multi Block Cooperative Groups.
 *  Added `conjugateGradientMultiDeviceCG`. Demonstrates a conjugate gradient solver on multiple GPUs using Multi Device Cooperative Groups, also uses unified memory prefetching and usage hints APIs.
 *  Added `simpleCUBLAS`. Demonstrates how perform GEMM operations using CUBLAS library.
-*  Added `simpleCUFFT`. Demonstrates how perform FFT operations using CUFFT library.
+*  Added `simpleCUFFT`. Demonstrates how perform FFT operations using CUFFT library.

Common/helper_cuda.h

@@ -666,6 +666,8 @@ inline int _ConvertSMVer2Cores(int major, int minor) {
       {0x80,  64},
       {0x86, 128},
       {0x87, 128},
+      {0x89, 128},
+      {0x90, 128},
       {-1, -1}};
 
   int index = 0;
@@ -712,6 +714,9 @@ inline const char* _ConvertSMVer2ArchName(int major, int minor) {
       {0x75, "Turing"},
       {0x80, "Ampere"},
       {0x86, "Ampere"},
+      {0x87, "Ampere"},
+      {0x89, "Ada"},
+      {0x90, "Hopper"},
       {-1, "Graphics Device"}};
 
   int index = 0;

Common/helper_cuda_drvapi.h

@@ -114,6 +114,8 @@ inline int _ConvertSMVer2CoresDRV(int major, int minor) {
       {0x80,  64},
       {0x86, 128},
       {0x87, 128},
+      {0x89, 128},
+      {0x90, 128},
       {-1, -1}};
 
   int index = 0;

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<Process> &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;
 }
 

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;

Common/helper_string.h

@@ -421,6 +421,7 @@ inline char *sdkFindFilePath(const char *filename,
   }
 
   // File not found
+  printf("\nerror: sdkFindFilePath: file <%s> not found!\n", filename);
   return 0;
 }
 

Common/nvrtc_helper.h

@@ -49,6 +49,11 @@
 
 void compileFileToCUBIN(char *filename, int argc, char **argv, char **cubinResult,
                       size_t *cubinResultSize, int requiresCGheaders) {
+  if (!filename) {
+    std::cerr << "\nerror: filename is empty for compileFileToCUBIN()!\n";
+    exit(1);
+  }
+
   std::ifstream inputFile(filename,
                           std::ios::in | std::ios::binary | std::ios::ate);
 
@@ -111,7 +116,12 @@ void compileFileToCUBIN(char *filename, int argc, char **argv, char **cubinResul
 
     compileOptions = "--include-path=";
 
-    std::string path = sdkFindFilePath(HeaderNames, argv[0]);
+    char *strPath = sdkFindFilePath(HeaderNames, argv[0]);
+    if (!strPath) {
+      std::cerr << "\nerror: header file " << HeaderNames << " not found!\n";
+      exit(1);
+    }
+    std::string path = strPath;
     if (!path.empty()) {
       std::size_t found = path.find(HeaderNames);
       path.erase(found);
@@ -120,6 +130,7 @@ void compileFileToCUBIN(char *filename, int argc, char **argv, char **cubinResul
           "\nCooperativeGroups headers not found, please install it in %s "
           "sample directory..\n Exiting..\n",
           argv[0]);
+      exit(1);
     }
     compileOptions += path.c_str();
     compileParams[numCompileOptions] = reinterpret_cast<char *>(

README.md

@@ -1,15 +1,12 @@
 # CUDA Samples
 
-Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 11.6](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 11.6
-* Added new folder structure for samples
-* Added support of Visual Studio 2022 to all samples supported on [Windows](#windows-1).
-* All CUDA samples are now only available on [GitHub](https://github.com/nvidia/cuda-samples). They are no longer available via CUDA toolkit.
+### CUDA 12.5
 
 ### [older versions...](./CHANGELOG.md)
 
@@ -17,7 +14,7 @@ This section describes the release notes for the CUDA Samples on GitHub only.
 
 ### Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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
@@ -92,6 +89,9 @@ Samples that are specific to domain (Graphics, Finance, Image Processing).
 ### [6. Performance](./Samples/6_Performance/README.md)
 Samples that demonstrate performance optimization.
 
+### [7. libNVVM](./Samples/7_libNVVM/README.md)
+Samples that demonstrate the use of libNVVVM and NVVM IR.
+
 ## Dependencies
 
 Some CUDA Samples rely on third-party applications and/or libraries, or features provided by the CUDA Toolkit and Driver, to either build or execute. These dependencies are listed below.
@@ -246,6 +246,10 @@ FP16 is a 16-bit floating-point format. One bit is used for the sign, five bits
 
 NVCC support of [C++11 features](https://en.wikipedia.org/wiki/C++11).
 
+#### CMake
+
+The libNVVM samples are built using [CMake](https://cmake.org/) 3.10 or later.
+
 ## Contributors Guide
 
 We welcome your input on issues and suggestions for samples. At this time we are not accepting contributions from the public, check back here as we evolve our contribution model.
@@ -263,4 +267,4 @@ Answers to frequently asked questions about CUDA can be found at http://develope
 
 ## Attributions
 
-*   Teapot image is obtained from [Wikimedia](https://en.wikipedia.org/wiki/File:Original_Utah_Teapot.jpg) and is licensed under the Creative Commons [Attribution-Share Alike 2.0](https://creativecommons.org/licenses/by-sa/2.0/deed.en) Generic license. The image is modified for samples use cases.
+*   Teapot image is obtained from [Wikimedia](https://en.wikipedia.org/wiki/File:Original_Utah_Teapot.jpg) and is licensed under the Creative Commons [Attribution-Share Alike 2.0](https://creativecommons.org/licenses/by-sa/2.0/deed.en) Generic license. The image is modified for samples use cases.

Samples/0_Introduction/UnifiedMemoryStreams/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)
@@ -318,9 +335,9 @@ endif
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/UnifiedMemoryStreams/NsightEclipse.xml

@@ -6,11 +6,11 @@
     <toolkit>cudaStreamDestroy</toolkit>
     <toolkit>cudaFree</toolkit>
     <toolkit>cudaMallocManaged</toolkit>
-    <toolkit>cudaStreamCreate</toolkit>
-    <toolkit>cudaDeviceSynchronize</toolkit>
     <toolkit>cudaStreamAttachMemAsync</toolkit>
     <toolkit>cudaSetDevice</toolkit>
+    <toolkit>cudaDeviceSynchronize</toolkit>
     <toolkit>cudaStreamSynchronize</toolkit>
+    <toolkit>cudaStreamCreate</toolkit>
     <toolkit>cudaGetDeviceProperties</toolkit>
   </cuda_api_list>
   <description><![CDATA[This sample demonstrates the use of OpenMP and streams with Unified Memory on a single GPU.]]></description>
@@ -57,19 +57,6 @@
     <scope>1:CUDA Systems Integration</scope>
     <scope>1:Unified Memory</scope>
   </scopes>
-  <sm-arch>sm35</sm-arch>
-  <sm-arch>sm37</sm-arch>
-  <sm-arch>sm50</sm-arch>
-  <sm-arch>sm52</sm-arch>
-  <sm-arch>sm53</sm-arch>
-  <sm-arch>sm60</sm-arch>
-  <sm-arch>sm61</sm-arch>
-  <sm-arch>sm70</sm-arch>
-  <sm-arch>sm72</sm-arch>
-  <sm-arch>sm75</sm-arch>
-  <sm-arch>sm80</sm-arch>
-  <sm-arch>sm86</sm-arch>
-  <sm-arch>sm87</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/0_Introduction/UnifiedMemoryStreams/README.md

@@ -10,8 +10,6 @@ CUDA Systems Integration, OpenMP, CUBLAS, Multithreading, Unified Memory, CUDA S
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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)
-
 ## Supported OSes
 
 Linux, Windows
@@ -23,14 +21,14 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaStreamDestroy, cudaFree, cudaMallocManaged, cudaStreamCreate, cudaDeviceSynchronize, cudaStreamAttachMemAsync, cudaSetDevice, cudaStreamSynchronize, cudaGetDeviceProperties
+cudaStreamDestroy, cudaFree, cudaMallocManaged, cudaStreamAttachMemAsync, cudaSetDevice, cudaDeviceSynchronize, cudaStreamSynchronize, cudaStreamCreate, cudaGetDeviceProperties
 
 ## Dependencies needed to build/run
-[OpenMP](../../README.md#openmp), [UVM](../../README.md#uvm), [CUBLAS](../../README.md#cublas)
+[OpenMP](../../../README.md#openmp), [UVM](../../../README.md#uvm), [CUBLAS](../../../README.md#cublas)
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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

Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/UnifiedMemoryStreams.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/UnifiedMemoryStreams.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/UnifiedMemoryStreams.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/asyncAPI/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)
@@ -279,9 +296,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/asyncAPI/NsightEclipse.xml

@@ -3,21 +3,21 @@
 <entry>
   <name>asyncAPI</name>
   <cuda_api_list>
-    <toolkit>cudaMemset</toolkit>
+    <toolkit>cudaProfilerStop</toolkit>
+    <toolkit>cudaMalloc</toolkit>
+    <toolkit>cudaMemcpyAsync</toolkit>
     <toolkit>cudaFree</toolkit>
-    <toolkit>cudaEventRecord</toolkit>
     <toolkit>cudaMallocHost</toolkit>
     <toolkit>cudaProfilerStart</toolkit>
-    <toolkit>cudaEventCreate</toolkit>
-    <toolkit>cudaEventElapsedTime</toolkit>
     <toolkit>cudaDeviceSynchronize</toolkit>
+    <toolkit>cudaEventRecord</toolkit>
     <toolkit>cudaFreeHost</toolkit>
-    <toolkit>cudaMalloc</toolkit>
-    <toolkit>cudaEventQuery</toolkit>
-    <toolkit>cudaProfilerStop</toolkit>
+    <toolkit>cudaMemset</toolkit>
     <toolkit>cudaEventDestroy</toolkit>
-    <toolkit>cudaMemcpyAsync</toolkit>
+    <toolkit>cudaEventQuery</toolkit>
+    <toolkit>cudaEventElapsedTime</toolkit>
     <toolkit>cudaGetDeviceProperties</toolkit>
+    <toolkit>cudaEventCreate</toolkit>
   </cuda_api_list>
   <description><![CDATA[This sample illustrates the usage of CUDA events for both GPU timing and overlapping CPU and GPU execution. Events are inserted into a stream of CUDA calls. Since CUDA stream calls are asynchronous, the CPU can perform computations while GPU is executing (including DMA memcopies between the host and device). CPU can query CUDA events to determine whether GPU has completed tasks.]]></description>
   <devicecompilation>whole</devicecompilation>
@@ -46,8 +46,6 @@
     <scope>1:CUDA Basic Topics</scope>
     <scope>1:Performance Strategies</scope>
   </scopes>
-  <sm-arch>sm35</sm-arch>
-  <sm-arch>sm37</sm-arch>
   <sm-arch>sm50</sm-arch>
   <sm-arch>sm52</sm-arch>
   <sm-arch>sm53</sm-arch>
@@ -59,6 +57,8 @@
   <sm-arch>sm80</sm-arch>
   <sm-arch>sm86</sm-arch>
   <sm-arch>sm87</sm-arch>
+  <sm-arch>sm89</sm-arch>
+  <sm-arch>sm90</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/0_Introduction/asyncAPI/README.md

@@ -10,7 +10,7 @@ Asynchronous Data Transfers, CUDA Streams and Events
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaMemset, cudaFree, cudaEventRecord, cudaMallocHost, cudaProfilerStart, cudaEventCreate, cudaEventElapsedTime, cudaDeviceSynchronize, cudaFreeHost, cudaMalloc, cudaEventQuery, cudaProfilerStop, cudaEventDestroy, cudaMemcpyAsync, cudaGetDeviceProperties
+cudaProfilerStop, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaMallocHost, cudaProfilerStart, cudaDeviceSynchronize, cudaEventRecord, cudaFreeHost, cudaMemset, cudaEventDestroy, cudaEventQuery, cudaEventElapsedTime, cudaGetDeviceProperties, cudaEventCreate
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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
 

Samples/0_Introduction/asyncAPI/asyncAPI_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/asyncAPI.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/asyncAPI/asyncAPI_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/asyncAPI.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/asyncAPI/asyncAPI_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/asyncAPI.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/c++11_cuda/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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 $(HOST_ARCH)
@@ -299,20 +316,23 @@ ifeq ($(TARGET_OS),linux)
 #$(warning $(GCCVERSION))
 
     IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 47000)
-
+ ifneq ($(CUSTOM_HOST_COMPILER), 1)
     ifeq ($(IS_MIN_VERSION), 1)
         $(info >>> GCC Version is greater or equal to 4.7.0 <<<)
     else
         $(info >>> Waiving build. Minimum GCC version required is 4.7.0<<<)
         SAMPLE_ENABLED := 0
     endif
+ else
+    $(warning >>> Custom HOST_COMPILER set; skipping GCC version check. This may lead to unintended behavior. Please note the minimum equivalent GCC version is 4.7.0 <<<)
+ endif
 endif
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)
@@ -363,7 +383,6 @@ run: build
 	$(EXEC) ./c++11_cuda
 
 testrun: build
-	$(EXEC) ./c++11_cuda --dummy-test-param
 
 clean:
 	rm -f c++11_cuda c++11_cuda.o

Samples/0_Introduction/c++11_cuda/NsightEclipse.xml

@@ -7,9 +7,9 @@
   </cflags>
   <cuda_api_list>
     <toolkit>cudaMalloc</toolkit>
+    <toolkit>cudaMemcpy</toolkit>
     <toolkit>cudaMemset</toolkit>
     <toolkit>cudaFree</toolkit>
-    <toolkit>cudaMemcpy</toolkit>
   </cuda_api_list>
   <description><![CDATA[This sample demonstrates C++11 feature support in CUDA. It scans a input text file and prints no. of occurrences of x, y, z, w characters. ]]></description>
   <devicecompilation>whole</devicecompilation>
@@ -31,9 +31,6 @@
   </librarypaths>
   <nsight_eclipse>true</nsight_eclipse>
   <primary_file>c++11_cuda.cu</primary_file>
-  <qatests>
-    <qatest>--dummy-test-param</qatest>
-  </qatests>
   <required_dependencies>
     <dependency>CPP11</dependency>
   </required_dependencies>
@@ -41,8 +38,6 @@
     <scope>1:CUDA Advanced Topics</scope>
     <scope>1:C++11 CUDA</scope>
   </scopes>
-  <sm-arch>sm35</sm-arch>
-  <sm-arch>sm37</sm-arch>
   <sm-arch>sm50</sm-arch>
   <sm-arch>sm52</sm-arch>
   <sm-arch>sm53</sm-arch>
@@ -54,6 +49,8 @@
   <sm-arch>sm80</sm-arch>
   <sm-arch>sm86</sm-arch>
   <sm-arch>sm87</sm-arch>
+  <sm-arch>sm89</sm-arch>
+  <sm-arch>sm90</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/0_Introduction/c++11_cuda/README.md

@@ -10,7 +10,7 @@ CPP11 CUDA
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaMalloc, cudaMemset, cudaFree, cudaMemcpy
+cudaMalloc, cudaMemcpy, cudaMemset, cudaFree
 
 ## Dependencies needed to build/run
-[CPP11](../../README.md#cpp11)
+[CPP11](../../../README.md#cpp11)
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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

Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/c++11_cuda.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/c++11_cuda.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/c++11_cuda.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/clock/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)
@@ -279,9 +296,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/clock/NsightEclipse.xml

@@ -4,8 +4,8 @@
   <name>clock</name>
   <cuda_api_list>
     <toolkit>cudaMalloc</toolkit>
-    <toolkit>cudaFree</toolkit>
     <toolkit>cudaMemcpy</toolkit>
+    <toolkit>cudaFree</toolkit>
   </cuda_api_list>
   <description><![CDATA[This example shows how to use the clock function to measure the performance of block of threads of a kernel accurately.]]></description>
   <devicecompilation>whole</devicecompilation>
@@ -34,8 +34,6 @@
     <scope>1:CUDA Basic Topics</scope>
     <scope>1:Performance Strategies</scope>
   </scopes>
-  <sm-arch>sm35</sm-arch>
-  <sm-arch>sm37</sm-arch>
   <sm-arch>sm50</sm-arch>
   <sm-arch>sm52</sm-arch>
   <sm-arch>sm53</sm-arch>
@@ -47,6 +45,8 @@
   <sm-arch>sm80</sm-arch>
   <sm-arch>sm86</sm-arch>
   <sm-arch>sm87</sm-arch>
+  <sm-arch>sm89</sm-arch>
+  <sm-arch>sm90</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/0_Introduction/clock/README.md

@@ -10,7 +10,7 @@ Performance Strategies
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaMalloc, cudaFree, cudaMemcpy
+cudaMalloc, cudaMemcpy, cudaFree
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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
 

Samples/0_Introduction/clock/clock_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/clock.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/clock/clock_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/clock.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/clock/clock_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/clock.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/clock_nvrtc/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)

Samples/0_Introduction/clock_nvrtc/README.md

@@ -10,7 +10,7 @@ Performance Strategies, Runtime Compilation
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,17 +23,17 @@ x86_64, ppc64le, aarch64
 ## CUDA APIs involved
 
 ### [CUDA Driver API](http://docs.nvidia.com/cuda/cuda-driver-api/index.html)
-cuModuleGetFunction, cuMemAlloc, cuLaunchKernel, cuCtxSynchronize, cuMemFree, cuMemcpyDtoH, cuMemcpyHtoD
+cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuCtxSynchronize, cuMemAlloc, cuMemFree, cuModuleGetFunction
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
 cudaBlockSize, cudaGridSize
 
 ## Dependencies needed to build/run
-[NVRTC](../../README.md#nvrtc)
+[NVRTC](../../../README.md#nvrtc)
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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

Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/concurrentKernels/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)
@@ -279,9 +296,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/concurrentKernels/NsightEclipse.xml

@@ -3,22 +3,22 @@
 <entry>
   <name>concurrentKernels</name>
   <cuda_api_list>
-    <toolkit>cudaStreamWaitEvent</toolkit>
     <toolkit>cudaStreamDestroy</toolkit>
-    <toolkit>cudaFree</toolkit>
-    <toolkit>cudaEventRecord</toolkit>
-    <toolkit>cudaMallocHost</toolkit>
-    <toolkit>cudaStreamCreate</toolkit>
-    <toolkit>cudaEventCreate</toolkit>
-    <toolkit>cudaEventElapsedTime</toolkit>
-    <toolkit>cudaEventSynchronize</toolkit>
-    <toolkit>cudaFreeHost</toolkit>
     <toolkit>cudaMalloc</toolkit>
-    <toolkit>cudaEventCreateWithFlags</toolkit>
-    <toolkit>cudaEventDestroy</toolkit>
     <toolkit>cudaMemcpyAsync</toolkit>
-    <toolkit>cudaGetDeviceProperties</toolkit>
+    <toolkit>cudaFree</toolkit>
+    <toolkit>cudaMallocHost</toolkit>
+    <toolkit>cudaEventCreateWithFlags</toolkit>
+    <toolkit>cudaEventSynchronize</toolkit>
+    <toolkit>cudaEventRecord</toolkit>
+    <toolkit>cudaFreeHost</toolkit>
     <toolkit>cudaGetDevice</toolkit>
+    <toolkit>cudaStreamWaitEvent</toolkit>
+    <toolkit>cudaEventDestroy</toolkit>
+    <toolkit>cudaEventElapsedTime</toolkit>
+    <toolkit>cudaStreamCreate</toolkit>
+    <toolkit>cudaGetDeviceProperties</toolkit>
+    <toolkit>cudaEventCreate</toolkit>
   </cuda_api_list>
   <description><![CDATA[This sample demonstrates the use of CUDA streams for concurrent execution of several kernels on GPU device. It also illustrates how to introduce dependencies between CUDA streams with the new cudaStreamWaitEvent function.]]></description>
   <devicecompilation>whole</devicecompilation>
@@ -44,8 +44,6 @@
     <scope>1:CUDA Advanced Topics</scope>
     <scope>1:Performance Strategies</scope>
   </scopes>
-  <sm-arch>sm35</sm-arch>
-  <sm-arch>sm37</sm-arch>
   <sm-arch>sm50</sm-arch>
   <sm-arch>sm52</sm-arch>
   <sm-arch>sm53</sm-arch>
@@ -57,6 +55,8 @@
   <sm-arch>sm80</sm-arch>
   <sm-arch>sm86</sm-arch>
   <sm-arch>sm87</sm-arch>
+  <sm-arch>sm89</sm-arch>
+  <sm-arch>sm90</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/0_Introduction/concurrentKernels/README.md

@@ -10,7 +10,7 @@ Performance Strategies
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaStreamWaitEvent, cudaStreamDestroy, cudaFree, cudaEventRecord, cudaMallocHost, cudaStreamCreate, cudaEventCreate, cudaEventElapsedTime, cudaEventSynchronize, cudaFreeHost, cudaMalloc, cudaEventCreateWithFlags, cudaEventDestroy, cudaMemcpyAsync, cudaGetDeviceProperties, cudaGetDevice
+cudaStreamDestroy, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaMallocHost, cudaEventCreateWithFlags, cudaEventSynchronize, cudaEventRecord, cudaFreeHost, cudaGetDevice, cudaStreamWaitEvent, cudaEventDestroy, cudaEventElapsedTime, cudaStreamCreate, cudaGetDeviceProperties, cudaEventCreate
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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
 

Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/concurrentKernels.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/concurrentKernels.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/concurrentKernels.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/cppIntegration/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)
@@ -279,9 +296,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/cppIntegration/NsightEclipse.xml

@@ -4,8 +4,8 @@
   <name>cppIntegration</name>
   <cuda_api_list>
     <toolkit>cudaMalloc</toolkit>
-    <toolkit>cudaFree</toolkit>
     <toolkit>cudaMemcpy</toolkit>
+    <toolkit>cudaFree</toolkit>
   </cuda_api_list>
   <description><![CDATA[This example demonstrates how to integrate CUDA into an existing C++ application, i.e. the CUDA entry point on host side is only a function which is called from C++ code and only the file containing this function is compiled with nvcc. It also demonstrates that vector types can be used from cpp.]]></description>
   <devicecompilation>whole</devicecompilation>
@@ -28,8 +28,6 @@
   <scopes>
     <scope>1:CUDA Basic Topics</scope>
   </scopes>
-  <sm-arch>sm35</sm-arch>
-  <sm-arch>sm37</sm-arch>
   <sm-arch>sm50</sm-arch>
   <sm-arch>sm52</sm-arch>
   <sm-arch>sm53</sm-arch>
@@ -41,6 +39,8 @@
   <sm-arch>sm80</sm-arch>
   <sm-arch>sm86</sm-arch>
   <sm-arch>sm87</sm-arch>
+  <sm-arch>sm89</sm-arch>
+  <sm-arch>sm90</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/0_Introduction/cppIntegration/README.md

@@ -10,7 +10,7 @@ CPP-CUDA Integration
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaMalloc, cudaFree, cudaMemcpy
+cudaMalloc, cudaMemcpy, cudaFree
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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
 

Samples/0_Introduction/cppIntegration/cppIntegration_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/cppIntegration.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -109,6 +109,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/cppIntegration/cppIntegration_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/cppIntegration.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -105,6 +105,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/cppIntegration/cppIntegration_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/cppIntegration.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -105,6 +105,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/cppOverload/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)
@@ -279,9 +296,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/cppOverload/NsightEclipse.xml

@@ -3,17 +3,17 @@
 <entry>
   <name>cppOverload</name>
   <cuda_api_list>
-    <toolkit>cudaFree</toolkit>
+    <toolkit>cudaMemcpy</toolkit>
     <toolkit>cudaFuncSetCacheConfig</toolkit>
+    <toolkit>cudaFree</toolkit>
     <toolkit>cudaMallocHost</toolkit>
-    <toolkit>cudaFuncGetAttributes</toolkit>
-    <toolkit>cudaGetDeviceCount</toolkit>
+    <toolkit>cudaSetDevice</toolkit>
+    <toolkit>cudaGetDeviceProperties</toolkit>
     <toolkit>cudaDeviceSynchronize</toolkit>
     <toolkit>cudaFreeHost</toolkit>
     <toolkit>cudaMalloc</toolkit>
-    <toolkit>cudaSetDevice</toolkit>
-    <toolkit>cudaMemcpy</toolkit>
-    <toolkit>cudaGetDeviceProperties</toolkit>
+    <toolkit>cudaFuncGetAttributes</toolkit>
+    <toolkit>cudaGetDeviceCount</toolkit>
   </cuda_api_list>
   <description><![CDATA[This sample demonstrates how to use C++ function overloading on the GPU.]]></description>
   <devicecompilation>whole</devicecompilation>
@@ -39,8 +39,6 @@
     <scope>1:CUDA Basic Topics</scope>
     <scope>1:Performance Strategies</scope>
   </scopes>
-  <sm-arch>sm35</sm-arch>
-  <sm-arch>sm37</sm-arch>
   <sm-arch>sm50</sm-arch>
   <sm-arch>sm52</sm-arch>
   <sm-arch>sm53</sm-arch>
@@ -52,6 +50,8 @@
   <sm-arch>sm80</sm-arch>
   <sm-arch>sm86</sm-arch>
   <sm-arch>sm87</sm-arch>
+  <sm-arch>sm89</sm-arch>
+  <sm-arch>sm90</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/0_Introduction/cppOverload/README.md

@@ -10,7 +10,7 @@ C++ Function Overloading, CUDA Streams and Events
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaFree, cudaFuncSetCacheConfig, cudaMallocHost, cudaFuncGetAttributes, cudaGetDeviceCount, cudaDeviceSynchronize, cudaFreeHost, cudaMalloc, cudaSetDevice, cudaMemcpy, cudaGetDeviceProperties
+cudaMemcpy, cudaFuncSetCacheConfig, cudaFree, cudaMallocHost, cudaSetDevice, cudaGetDeviceProperties, cudaDeviceSynchronize, cudaFreeHost, cudaMalloc, cudaFuncGetAttributes, cudaGetDeviceCount
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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
 

Samples/0_Introduction/cppOverload/cppOverload_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/cppOverload.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/cppOverload/cppOverload_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/cppOverload.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/cppOverload/cppOverload_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/cppOverload.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/cudaOpenMP/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)
@@ -321,9 +338,9 @@ endif
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/cudaOpenMP/README.md

@@ -10,7 +10,7 @@ CUDA Systems Integration, OpenMP, Multithreading
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaMemset, cudaFree, cudaGetDeviceCount, cudaSetDevice, cudaMalloc, cudaGetLastError, cudaMemcpy, cudaGetErrorString, cudaGetDeviceProperties, cudaGetDevice
+cudaMemcpy, cudaGetErrorString, cudaFree, cudaGetLastError, cudaSetDevice, cudaGetDeviceCount, cudaGetDevice, cudaMemset, cudaMalloc, cudaGetDeviceProperties
 
 ## Dependencies needed to build/run
-[OpenMP](../../README.md#openmp)
+[OpenMP](../../../README.md#openmp)
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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

Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/cudaOpenMP.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/cudaOpenMP.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/cudaOpenMP.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/fp16ScalarProduct/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)
@@ -285,9 +302,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 60 61 70 75 80 86
+SMS ?= 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/fp16ScalarProduct/NsightEclipse.xml

@@ -3,11 +3,11 @@
 <entry>
   <name>fp16ScalarProduct</name>
   <cuda_api_list>
+    <toolkit>cudaMemcpy</toolkit>
     <toolkit>cudaFree</toolkit>
     <toolkit>cudaMallocHost</toolkit>
     <toolkit>cudaFreeHost</toolkit>
     <toolkit>cudaMalloc</toolkit>
-    <toolkit>cudaMemcpy</toolkit>
     <toolkit>cudaGetDeviceProperties</toolkit>
   </cuda_api_list>
   <description><![CDATA[Calculates scalar product of two vectors of FP16 numbers.]]></description>
@@ -44,6 +44,8 @@
   <sm-arch>sm80</sm-arch>
   <sm-arch>sm86</sm-arch>
   <sm-arch>sm87</sm-arch>
+  <sm-arch>sm89</sm-arch>
+  <sm-arch>sm90</sm-arch>
   <supported_envs>
     <env>
       <arch>arm</arch>

Samples/0_Introduction/fp16ScalarProduct/README.md

@@ -10,7 +10,7 @@ CUDA Runtime API
 
 ## Supported SM Architectures
 
-[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 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
 
@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaFree, cudaMallocHost, cudaFreeHost, cudaMalloc, cudaMemcpy, cudaGetDeviceProperties
+cudaMemcpy, cudaFree, cudaMallocHost, cudaFreeHost, cudaMalloc, cudaGetDeviceProperties
 
 ## Dependencies needed to build/run
-[FP16](../../README.md#fp16)
+[FP16](../../../README.md#fp16)
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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

Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/fp16ScalarProduct.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/fp16ScalarProduct.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/fp16ScalarProduct.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMul/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)
@@ -279,9 +296,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/matrixMul/NsightEclipse.xml

@@ -3,20 +3,20 @@
 <entry>
   <name>matrixMul</name>
   <cuda_api_list>
+    <toolkit>cudaStreamCreateWithFlags</toolkit>
+    <toolkit>cudaProfilerStop</toolkit>
+    <toolkit>cudaMalloc</toolkit>
     <toolkit>cudaFree</toolkit>
-    <toolkit>cudaEventRecord</toolkit>
     <toolkit>cudaMallocHost</toolkit>
     <toolkit>cudaProfilerStart</toolkit>
-    <toolkit>cudaEventCreate</toolkit>
-    <toolkit>cudaEventElapsedTime</toolkit>
     <toolkit>cudaEventSynchronize</toolkit>
+    <toolkit>cudaEventRecord</toolkit>
     <toolkit>cudaFreeHost</toolkit>
-    <toolkit>cudaMalloc</toolkit>
-    <toolkit>cudaProfilerStop</toolkit>
-    <toolkit>cudaStreamCreateWithFlags</toolkit>
-    <toolkit>cudaEventDestroy</toolkit>
     <toolkit>cudaStreamSynchronize</toolkit>
+    <toolkit>cudaEventDestroy</toolkit>
+    <toolkit>cudaEventElapsedTime</toolkit>
     <toolkit>cudaMemcpyAsync</toolkit>
+    <toolkit>cudaEventCreate</toolkit>
   </cuda_api_list>
   <description><![CDATA[This sample implements matrix multiplication and is exactly the same as Chapter 6 of the programming guide. It has been written for clarity of exposition to illustrate various CUDA programming principles, not with the goal of providing the most performant generic kernel for matrix multiplication.  To illustrate GPU performance for matrix multiply, this sample also shows how to use the new CUDA 4.0 interface for CUBLAS to demonstrate high-performance performance for matrix multiplication.]]></description>
   <devicecompilation>whole</devicecompilation>
@@ -43,8 +43,6 @@
     <scope>1:CUDA Basic Topics</scope>
     <scope>3:Linear Algebra</scope>
   </scopes>
-  <sm-arch>sm35</sm-arch>
-  <sm-arch>sm37</sm-arch>
   <sm-arch>sm50</sm-arch>
   <sm-arch>sm52</sm-arch>
   <sm-arch>sm53</sm-arch>
@@ -56,6 +54,8 @@
   <sm-arch>sm80</sm-arch>
   <sm-arch>sm86</sm-arch>
   <sm-arch>sm87</sm-arch>
+  <sm-arch>sm89</sm-arch>
+  <sm-arch>sm90</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/0_Introduction/matrixMul/README.md

@@ -10,7 +10,7 @@ CUDA Runtime API, Linear Algebra
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l, aarch64
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaFree, cudaEventRecord, cudaMallocHost, cudaProfilerStart, cudaEventCreate, cudaEventElapsedTime, cudaEventSynchronize, cudaFreeHost, cudaMalloc, cudaProfilerStop, cudaStreamCreateWithFlags, cudaEventDestroy, cudaStreamSynchronize, cudaMemcpyAsync
+cudaStreamCreateWithFlags, cudaProfilerStop, cudaMalloc, cudaFree, cudaMallocHost, cudaProfilerStart, cudaEventSynchronize, cudaEventRecord, cudaFreeHost, cudaStreamSynchronize, cudaEventDestroy, cudaEventElapsedTime, cudaMemcpyAsync, cudaEventCreate
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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
 

Samples/0_Introduction/matrixMul/matrixMul_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/matrixMul.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMul/matrixMul_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/matrixMul.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMul/matrixMul_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/matrixMul.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMulDrv/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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 $(HOST_ARCH)
@@ -283,9 +300,9 @@ FATBIN_FILE := matrixMul_kernel${TARGET_SIZE}.fatbin
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/matrixMulDrv/README.md

@@ -10,7 +10,7 @@ CUDA Driver API, Matrix Multiply
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l, aarch64
 ## CUDA APIs involved
 
 ### [CUDA Driver API](http://docs.nvidia.com/cuda/cuda-driver-api/index.html)
-cuModuleGetFunction, cuMemcpyHtoD, cuModuleLoadData, cuCtxCreate, cuLaunchKernel, cuDeviceGetName, cuMemAlloc, cuOccupancyMaxPotentialBlockSize, cuDeviceTotalMem, cuMemFree, cuMemcpyDtoH, cuCtxDestroy, cuDeviceGetAttribute
+cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuDeviceGetName, cuDeviceTotalMem, cuDeviceGetAttribute, cuModuleLoadData, cuOccupancyMaxPotentialBlockSize, cuMemAlloc, cuMemFree, cuCtxDestroy, cuModuleGetFunction, cuCtxCreate
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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
 

Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/matrixMulDrv.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -111,6 +111,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/matrixMulDrv.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/matrixMulDrv.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMulDynlinkJIT/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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 $(HOST_ARCH)
@@ -287,8 +304,8 @@ ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 # Generate PTX code from SM 53
 GENCODE_FLAGS += -gencode arch=compute_53,code=compute_53
 else
-# Generate PTX code from SM 35
-GENCODE_FLAGS += -gencode arch=compute_35,code=compute_35
+# Generate PTX code from SM 50
+GENCODE_FLAGS += -gencode arch=compute_50,code=compute_50
 endif
 endif
 

Samples/0_Introduction/matrixMulDynlinkJIT/README.md

@@ -10,7 +10,7 @@ CUDA Driver API, CUDA Dynamically Linked Library
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved
 
 ### [CUDA Driver API](http://docs.nvidia.com/cuda/cuda-driver-api/index.html)
-cuParamSetv, cuMemFree, cuInit, cuModuleGetFunction, cuCtxDestroy, cuCtxCreate, cuDeviceGetName, cuCtxSynchronize, cuParamSeti, cuModuleLoadDataEx, cuDeviceGet, cuFuncSetSharedSize, cuMemAlloc, cuDeviceComputeCapability, cuFuncSetBlockShape, cuMemcpyHtoD, cuParamSetSize, cuLaunchGrid, cuDeviceGetCount, cuLaunchKernel, cuMemcpyDtoH
+cuMemcpyDtoH, cuDeviceGetName, cuParamSeti, cuModuleLoadDataEx, cuModuleGetFunction, cuLaunchGrid, cuFuncSetSharedSize, cuMemFree, cuParamSetSize, cuParamSetv, cuInit, cuMemcpyHtoD, cuLaunchKernel, cuDeviceGet, cuFuncSetBlockShape, cuCtxDestroy, cuDeviceGetCount, cuDeviceComputeCapability, cuCtxSynchronize, cuMemAlloc, cuCtxCreate
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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
 

Samples/0_Introduction/matrixMulDynlinkJIT/helper_cuda_drvapi.h

@@ -95,6 +95,7 @@ inline int _ConvertSMVer2CoresDRV(int major, int minor) {
       {0x80,  64},
       {0x86, 128},
       {0x87, 128},
+      {0x90, 128},
       {-1, -1}};
 
   int index = 0;

Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/matrixMulDynlinkJIT.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,compute_35;</CodeGeneration>
+      <CodeGeneration>compute_50,compute_50;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -116,6 +116,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/matrixMulDynlinkJIT.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,compute_35;</CodeGeneration>
+      <CodeGeneration>compute_50,compute_50;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -112,6 +112,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/matrixMulDynlinkJIT.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,compute_35;</CodeGeneration>
+      <CodeGeneration>compute_50,compute_50;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -112,6 +112,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMul_nvrtc/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)

Samples/0_Introduction/matrixMul_nvrtc/README.md

@@ -10,7 +10,7 @@ CUDA Runtime API, Linear Algebra, Runtime Compilation
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,14 +23,14 @@ x86_64, ppc64le, aarch64
 ## CUDA APIs involved
 
 ### [CUDA Driver API](http://docs.nvidia.com/cuda/cuda-driver-api/index.html)
-cuModuleGetFunction, cuMemAlloc, cuLaunchKernel, cuCtxSynchronize, cuMemFree, cuMemcpyDtoH, cuMemcpyHtoD
+cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuCtxSynchronize, cuMemAlloc, cuMemFree, cuModuleGetFunction
 
 ## Dependencies needed to build/run
-[NVRTC](../../README.md#nvrtc)
+[NVRTC](../../../README.md#nvrtc)
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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

Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -113,6 +113,6 @@ xcopy /y /e /s "$(CudaToolkitDir)include\cooperative_groups" .\cooperative_group
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -109,6 +109,6 @@ xcopy /y /e /s "$(CudaToolkitDir)include\cooperative_groups" .\cooperative_group
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -109,6 +109,6 @@ xcopy /y /e /s "$(CudaToolkitDir)include\cooperative_groups" .\cooperative_group
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/mergeSort/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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)
@@ -279,9 +296,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/mergeSort/NsightEclipse.xml

@@ -4,9 +4,9 @@
   <name>mergeSort</name>
   <cuda_api_list>
     <toolkit>cudaMalloc</toolkit>
-    <toolkit>cudaFree</toolkit>
     <toolkit>cudaDeviceSynchronize</toolkit>
     <toolkit>cudaMemcpy</toolkit>
+    <toolkit>cudaFree</toolkit>
   </cuda_api_list>
   <description><![CDATA[This sample implements a merge sort (also known as Batcher's sort), algorithms belonging to the class of sorting networks. While generally subefficient on large sequences compared to algorithms with better asymptotic algorithmic complexity (i.e. merge sort or radix sort), may be the algorithms of choice for sorting batches of short- to mid-sized (key, value) array pairs. Refer to the excellent tutorial by H. W. Lang http://www.iti.fh-flensburg.de/lang/algorithmen/sortieren/networks/indexen.htm]]></description>
   <devicecompilation>whole</devicecompilation>
@@ -33,8 +33,6 @@
     <scope>1:CUDA Advanced Topics</scope>
     <scope>1:Data-Parallel Algorithms</scope>
   </scopes>
-  <sm-arch>sm35</sm-arch>
-  <sm-arch>sm37</sm-arch>
   <sm-arch>sm50</sm-arch>
   <sm-arch>sm52</sm-arch>
   <sm-arch>sm53</sm-arch>
@@ -46,6 +44,8 @@
   <sm-arch>sm80</sm-arch>
   <sm-arch>sm86</sm-arch>
   <sm-arch>sm87</sm-arch>
+  <sm-arch>sm89</sm-arch>
+  <sm-arch>sm90</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/0_Introduction/mergeSort/README.md

@@ -10,7 +10,7 @@ Data-Parallel Algorithms
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [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 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
 
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaMalloc, cudaFree, cudaDeviceSynchronize, cudaMemcpy
+cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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
 

Samples/0_Introduction/mergeSort/mergeSort_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/mergeSort.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -111,6 +111,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/mergeSort/mergeSort_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/mergeSort.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/mergeSort/mergeSort_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/mergeSort.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
+      <CodeGeneration>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;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/simpleAWBarrier/Makefile

@@ -113,6 +113,10 @@ ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
 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++
@@ -165,6 +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 $(HOST_ARCH)
@@ -305,20 +322,23 @@ ifeq ($(TARGET_OS),linux)
 #$(warning $(GCCVERSION))
 
     IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 51000)
-
+ ifneq ($(CUSTOM_HOST_COMPILER), 1)
     ifeq ($(IS_MIN_VERSION), 1)
         $(info >>> GCC Version is greater or equal to  5.1.0 <<<)
     else
         $(info >>> Waiving build. Minimum GCC version required is  5.1.0<<<)
         SAMPLE_ENABLED := 0
     endif
+ else
+    $(warning >>> Custom HOST_COMPILER set; skipping GCC version check. This may lead to unintended behavior. Please note the minimum equivalent GCC version is  5.1.0 <<<)
+ endif
 endif
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 70 72 75 80 86 87
+SMS ?= 70 72 75 80 86 87 90
 else
-SMS ?= 70 75 80 86
+SMS ?= 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/simpleAWBarrier/NsightEclipse.xml

@@ -6,17 +6,17 @@
     <flag>--std=c++11</flag>
   </cflags>
   <cuda_api_list>
-    <toolkit>cudaFree</toolkit>
-    <toolkit>cudaMallocHost</toolkit>
-    <toolkit>cudaOccupancyMaxActiveBlocksPerMultiprocessor</toolkit>
-    <toolkit>cudaOccupancyMaxPotentialBlockSize</toolkit>
-    <toolkit>cudaDeviceGetAttribute</toolkit>
-    <toolkit>cudaFreeHost</toolkit>
-    <toolkit>cudaMalloc</toolkit>
     <toolkit>cudaStreamCreateWithFlags</toolkit>
-    <toolkit>cudaLaunchCooperativeKernel</toolkit>
+    <toolkit>cudaFree</toolkit>
+    <toolkit>cudaDeviceGetAttribute</toolkit>
+    <toolkit>cudaMallocHost</toolkit>
+    <toolkit>cudaFreeHost</toolkit>
     <toolkit>cudaStreamSynchronize</toolkit>
+    <toolkit>cudaLaunchCooperativeKernel</toolkit>
+    <toolkit>cudaMalloc</toolkit>
+    <toolkit>cudaOccupancyMaxActiveBlocksPerMultiprocessor</toolkit>
     <toolkit>cudaMemcpyAsync</toolkit>
+    <toolkit>cudaOccupancyMaxPotentialBlockSize</toolkit>
   </cuda_api_list>
   <description><![CDATA[A simple demonstration of arrive wait barriers.]]></description>
   <devicecompilation>whole</devicecompilation>
@@ -53,6 +53,8 @@
   <sm-arch>sm80</sm-arch>
   <sm-arch>sm86</sm-arch>
   <sm-arch>sm87</sm-arch>
+  <sm-arch>sm89</sm-arch>
+  <sm-arch>sm90</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/0_Introduction/simpleAWBarrier/README.md

@@ -10,7 +10,7 @@ Arrive Wait Barrier
 
 ## Supported SM Architectures
 
-[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 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
 
@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l, aarch64
 ## CUDA APIs involved
 
 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaFree, cudaMallocHost, cudaOccupancyMaxActiveBlocksPerMultiprocessor, cudaOccupancyMaxPotentialBlockSize, cudaDeviceGetAttribute, cudaFreeHost, cudaMalloc, cudaStreamCreateWithFlags, cudaLaunchCooperativeKernel, cudaStreamSynchronize, cudaMemcpyAsync
+cudaStreamCreateWithFlags, cudaFree, cudaDeviceGetAttribute, cudaMallocHost, cudaFreeHost, cudaStreamSynchronize, cudaLaunchCooperativeKernel, cudaMalloc, cudaOccupancyMaxActiveBlocksPerMultiprocessor, cudaMemcpyAsync, cudaOccupancyMaxPotentialBlockSize
 
 ## Dependencies needed to build/run
-[CPP11](../../README.md#cpp11), [MBCG](../../README.md#mbcg)
+[CPP11](../../../README.md#cpp11), [MBCG](../../../README.md#mbcg)
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.6](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

Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/simpleAWBarrier.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_89,sm_89;compute_90,sm_90;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/simpleAWBarrier.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_89,sm_89;compute_90,sm_90;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>