Updating samples for CUDA 12.5

Fix cudaExtent.width set error.

CHANGELOG.md

@@ -1,5 +1,22 @@
 ## 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

Common/helper_cuda.h

@@ -666,6 +666,7 @@ inline int _ConvertSMVer2Cores(int major, int minor) {
       {0x80,  64},
       {0x86, 128},
       {0x87, 128},
+      {0x89, 128},
       {0x90, 128},
       {-1, -1}};
 
@@ -714,6 +715,7 @@ inline const char* _ConvertSMVer2ArchName(int major, int minor) {
       {0x80, "Ampere"},
       {0x86, "Ampere"},
       {0x87, "Ampere"},
+      {0x89, "Ada"},
       {0x90, "Hopper"},
       {-1, "Graphics Device"}};
 

Common/helper_cuda_drvapi.h

@@ -114,6 +114,7 @@ inline int _ConvertSMVer2CoresDRV(int major, int minor) {
       {0x80,  64},
       {0x86, 128},
       {0x87, 128},
+      {0x89, 128},
       {0x90, 128},
       {-1, -1}};
 

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;

README.md

@@ -1,14 +1,12 @@
 # CUDA Samples
 
-Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 12.0](https://developer.nvidia.com/cuda-downloads).
+Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads).
 
 ## Release Notes
 
 This section describes the release notes for the CUDA Samples on GitHub only.
 
-### CUDA 12.0
-* Added new flags for JIT compiling
-* Removed deprecated APIs in Hopper Architecture
+### CUDA 12.5
 
 ### [older versions...](./CHANGELOG.md)
 
@@ -16,7 +14,7 @@ This section describes the release notes for the CUDA Samples on GitHub only.
 
 ### Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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
@@ -91,6 +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.
@@ -245,6 +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.

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 $(HOST_ARCH)
@@ -320,7 +337,7 @@ endif
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/UnifiedMemoryStreams/README.md

@@ -28,7 +28,7 @@ cudaStreamDestroy, cudaFree, cudaMallocManaged, cudaStreamAttachMemAsync, cudaSe
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 $(HOST_ARCH)
@@ -281,7 +298,7 @@ LIBRARIES :=
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/asyncAPI/NsightEclipse.xml

@@ -57,6 +57,7 @@
   <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>

Samples/0_Introduction/asyncAPI/README.md

@@ -10,7 +10,7 @@ Asynchronous Data Transfers, CUDA Streams and Events
 
 ## Supported SM Architectures
 
-[SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](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
 
@@ -27,7 +27,7 @@ cudaProfilerStop, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaMallocHost, cudaPro
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

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

@@ -49,6 +49,7 @@
   <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>

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

@@ -10,7 +10,7 @@ CPP11 CUDA
 
 ## Supported SM Architectures
 
-[SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](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
 
@@ -30,7 +30,7 @@ cudaMalloc, cudaMemcpy, cudaMemset, cudaFree
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 $(HOST_ARCH)
@@ -281,7 +298,7 @@ LIBRARIES :=
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/clock/NsightEclipse.xml

@@ -45,6 +45,7 @@
   <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>

Samples/0_Introduction/clock/README.md

@@ -10,7 +10,7 @@ Performance Strategies
 
 ## Supported SM Architectures
 
-[SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](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
 
@@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaFree
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 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 9.0 ](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
 
@@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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="$(CUDAPropsPath)\CUDA 12.0.targets" />
+    <Import Project="$(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 12.0.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="$(CUDAPropsPath)\CUDA 12.0.targets" />
+    <Import Project="$(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 12.0.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="$(CUDAPropsPath)\CUDA 12.0.targets" />
+    <Import Project="$(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 $(HOST_ARCH)
@@ -281,7 +298,7 @@ LIBRARIES :=
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/concurrentKernels/NsightEclipse.xml

@@ -55,6 +55,7 @@
   <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>

Samples/0_Introduction/concurrentKernels/README.md

@@ -10,7 +10,7 @@ Performance Strategies
 
 ## Supported SM Architectures
 
-[SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](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
 
@@ -27,7 +27,7 @@ cudaStreamDestroy, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaMallocHost, cudaEv
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 $(HOST_ARCH)
@@ -281,7 +298,7 @@ LIBRARIES :=
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/cppIntegration/NsightEclipse.xml

@@ -39,6 +39,7 @@
   <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>

Samples/0_Introduction/cppIntegration/README.md

@@ -10,7 +10,7 @@ CPP-CUDA Integration
 
 ## Supported SM Architectures
 
-[SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](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
 
@@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaFree
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 $(HOST_ARCH)
@@ -281,7 +298,7 @@ LIBRARIES :=
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/cppOverload/NsightEclipse.xml

@@ -50,6 +50,7 @@
   <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>

Samples/0_Introduction/cppOverload/README.md

@@ -10,7 +10,7 @@ C++ Function Overloading, CUDA Streams and Events
 
 ## Supported SM Architectures
 
-[SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](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
 
@@ -27,7 +27,7 @@ cudaMemcpy, cudaFuncSetCacheConfig, cudaFree, cudaMallocHost, cudaSetDevice, cud
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 $(HOST_ARCH)
@@ -323,7 +340,7 @@ endif
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+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 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 9.0 ](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
 
@@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaGetLastError, cudaSetDevice, cudaG
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 $(HOST_ARCH)
@@ -287,7 +304,7 @@ LIBRARIES :=
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 60 61 70 75 80 86 90
+SMS ?= 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/fp16ScalarProduct/NsightEclipse.xml

@@ -44,6 +44,7 @@
   <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>

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 9.0 ](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
 
@@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaMallocHost, cudaFreeHost, cudaMalloc, cudaGetDevicePro
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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;compute_90,sm_90;</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 12.0.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 12.0.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;compute_90,sm_90;</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 12.0.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 12.0.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;compute_90,sm_90;</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 12.0.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 $(HOST_ARCH)
@@ -281,7 +298,7 @@ LIBRARIES :=
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/matrixMul/NsightEclipse.xml

@@ -54,6 +54,7 @@
   <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>

Samples/0_Introduction/matrixMul/README.md

@@ -10,7 +10,7 @@ CUDA Runtime API, Linear Algebra
 
 ## Supported SM Architectures
 
-[SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](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
 
@@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaProfilerStop, cudaMalloc, cudaFree, cudaMallocHos
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 $(HOST_ARCH)
@@ -285,7 +302,7 @@ FATBIN_FILE := matrixMul_kernel${TARGET_SIZE}.fatbin
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+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 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 9.0 ](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
 
@@ -27,7 +27,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuDeviceGetName, cuDeviceTotalMem, c
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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)

Samples/0_Introduction/matrixMulDynlinkJIT/README.md

@@ -10,7 +10,7 @@ CUDA Driver API, CUDA Dynamically Linked Library
 
 ## Supported SM Architectures
 
-[SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](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
 
@@ -27,7 +27,7 @@ cuMemcpyDtoH, cuDeviceGetName, cuParamSeti, cuModuleLoadDataEx, cuModuleGetFunct
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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/matrixMulDynlinkJIT_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.0.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.$(Platform).user.props" />
@@ -116,6 +116,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.0.targets" />
+    <Import Project="$(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 12.0.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.$(Platform).user.props" />
@@ -112,6 +112,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.0.targets" />
+    <Import Project="$(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 12.0.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.$(Platform).user.props" />
@@ -112,6 +112,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.0.targets" />
+    <Import Project="$(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 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 9.0 ](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
 
@@ -30,7 +30,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuCtxSynchronize, cuMemAlloc, cuMemF
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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 12.0.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 12.0.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 12.0.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 12.0.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 12.0.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 $(HOST_ARCH)
@@ -281,7 +298,7 @@ LIBRARIES :=
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/mergeSort/NsightEclipse.xml

@@ -44,6 +44,7 @@
   <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>

Samples/0_Introduction/mergeSort/README.md

@@ -10,7 +10,7 @@ Data-Parallel Algorithms
 
 ## Supported SM Architectures
 
-[SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](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
 
@@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 12.0.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_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_90,sm_90;</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 12.0.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 90
 else
-SMS ?= 70 75 80 86 90
+SMS ?= 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/simpleAWBarrier/NsightEclipse.xml

@@ -53,6 +53,7 @@
   <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>

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 9.0 ](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
 
@@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaFree, cudaDeviceGetAttribute, cudaMallocHost, cud
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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 12.0.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;compute_90,sm_90;</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 12.0.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 12.0.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;compute_90,sm_90;</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 12.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.0.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;compute_90,sm_90;</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 12.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/simpleAssert/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 $(HOST_ARCH)
@@ -287,7 +304,7 @@ LIBRARIES :=
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
 SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 50 52 60 61 70 75 80 86 90
+SMS ?= 50 52 60 61 70 75 80 86 89 90
 endif
 
 ifeq ($(SMS),)

Samples/0_Introduction/simpleAssert/NsightEclipse.xml

@@ -39,6 +39,7 @@
   <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>

Samples/0_Introduction/simpleAssert/README.md

@@ -10,7 +10,7 @@ Assert
 
 ## Supported SM Architectures
 
-[SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](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
 
@@ -27,7 +27,7 @@ cudaDeviceSynchronize, cudaGetErrorString
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.0](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/simpleAssert/simpleAssert_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.0.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)/simpleAssert.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <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_90,sm_90;</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 12.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>