Update samples for CUDA 11.8 with correct props

2026-10-23 21:28:17 +08:00 · 2022-10-14 17:43:37 -07:00
parent b312abaa07
commit 81992093d2
1146 changed files with 4209 additions and 4272 deletions
--- a/Samples/6_Performance/UnifiedMemoryPerf/Makefile
+++ b/Samples/6_Performance/UnifiedMemoryPerf/Makefile
@@ -285,9 +285,9 @@ LIBRARIES :=

 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 35 37 50 52 60 61 70 75 80 86 90
 endif

 ifeq ($(SMS),)
--- a/Samples/6_Performance/UnifiedMemoryPerf/NsightEclipse.xml
+++ b/Samples/6_Performance/UnifiedMemoryPerf/NsightEclipse.xml
@@ -3,19 +3,19 @@
 <entry>
  <name>UnifiedMemoryPerf</name>
  <cuda_api_list>
+    <toolkit>cudaMemcpy</toolkit>
    <toolkit>cudaStreamDestroy</toolkit>
+    <toolkit>cudaMemPrefetchAsync</toolkit>
    <toolkit>cudaFree</toolkit>
    <toolkit>cudaMallocHost</toolkit>
    <toolkit>cudaMallocManaged</toolkit>
-    <toolkit>cudaMemPrefetchAsync</toolkit>
-    <toolkit>cudaStreamCreate</toolkit>
    <toolkit>cudaStreamAttachMemAsync</toolkit>
+    <toolkit>cudaHostGetDevicePointer</toolkit>
    <toolkit>cudaFreeHost</toolkit>
+    <toolkit>cudaStreamSynchronize</toolkit>
    <toolkit>cudaMalloc</toolkit>
    <toolkit>cudaMemcpyAsync</toolkit>
-    <toolkit>cudaStreamSynchronize</toolkit>
-    <toolkit>cudaHostGetDevicePointer</toolkit>
-    <toolkit>cudaMemcpy</toolkit>
+    <toolkit>cudaStreamCreate</toolkit>
    <toolkit>cudaGetDeviceProperties</toolkit>
  </cuda_api_list>
  <description><![CDATA[This sample demonstrates the performance comparision using matrix multiplication kernel of Unified Memory with/without hints and other types of memory like zero copy buffers, pageable, pagelocked memory performing synchronous and Asynchronous transfers on a single GPU.]]></description>
@@ -66,6 +66,7 @@
  <sm-arch>sm80</sm-arch>
  <sm-arch>sm86</sm-arch>
  <sm-arch>sm87</sm-arch>
+  <sm-arch>sm90</sm-arch>
  <supported_envs>
    <env>
      <arch>x86_64</arch>
--- a/Samples/6_Performance/UnifiedMemoryPerf/README.md
+++ b/Samples/6_Performance/UnifiedMemoryPerf/README.md
@@ -10,7 +10,7 @@ CUDA Systems Integration, Unified Memory, CUDA Streams and Events, Pinned System

 ## Supported SM Architectures

-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)

 ## Supported OSes

@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l, aarch64
 ## CUDA APIs involved

 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaStreamDestroy, cudaFree, cudaMallocHost, cudaMallocManaged, cudaMemPrefetchAsync, cudaStreamCreate, cudaStreamAttachMemAsync, cudaFreeHost, cudaMalloc, cudaMemcpyAsync, cudaStreamSynchronize, cudaHostGetDevicePointer, cudaMemcpy, cudaGetDeviceProperties
+cudaMemcpy, cudaStreamDestroy, cudaMemPrefetchAsync, cudaFree, cudaMallocHost, cudaMallocManaged, cudaStreamAttachMemAsync, cudaHostGetDevicePointer, cudaFreeHost, cudaStreamSynchronize, cudaMalloc, cudaMemcpyAsync, cudaStreamCreate, cudaGetDeviceProperties

 ## Dependencies needed to build/run
 [UVM](../../../README.md#uvm)

 ## Prerequisites

-Download and install the [CUDA Toolkit 11.6](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.8](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.

 ## Build and Run
--- a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj
+++ b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj
@@ -38,7 +38,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
  </ImportGroup>
  <ImportGroup Label="PropertySheets">
    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
      <OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -110,6 +110,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj
+++ b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj
@@ -34,7 +34,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.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>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -106,6 +106,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2022.vcxproj
+++ b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2022.vcxproj
@@ -34,7 +34,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
  </ImportGroup>
  <ImportGroup Label="PropertySheets">
    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
      <OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -106,6 +106,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/6_Performance/alignedTypes/Makefile
+++ b/Samples/6_Performance/alignedTypes/Makefile
@@ -279,9 +279,9 @@ LIBRARIES :=

 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 35 37 50 52 60 61 70 75 80 86 90
 endif

 ifeq ($(SMS),)
--- a/Samples/6_Performance/alignedTypes/NsightEclipse.xml
+++ b/Samples/6_Performance/alignedTypes/NsightEclipse.xml
@@ -3,11 +3,11 @@
 <entry>
  <name>alignedTypes</name>
  <cuda_api_list>
-    <toolkit>cudaMemset</toolkit>
+    <toolkit>cudaMemcpy</toolkit>
    <toolkit>cudaFree</toolkit>
    <toolkit>cudaDeviceSynchronize</toolkit>
+    <toolkit>cudaMemset</toolkit>
    <toolkit>cudaMalloc</toolkit>
-    <toolkit>cudaMemcpy</toolkit>
    <toolkit>cudaGetDeviceProperties</toolkit>
  </cuda_api_list>
  <description><![CDATA[A simple test, showing huge access speed gap between aligned and misaligned structures. It measures per-element copy throughput for aligned and misaligned structures on big chunks of data.]]></description>
@@ -46,6 +46,7 @@
  <sm-arch>sm80</sm-arch>
  <sm-arch>sm86</sm-arch>
  <sm-arch>sm87</sm-arch>
+  <sm-arch>sm90</sm-arch>
  <supported_envs>
    <env>
      <arch>x86_64</arch>
--- a/Samples/6_Performance/alignedTypes/README.md
+++ b/Samples/6_Performance/alignedTypes/README.md
@@ -10,7 +10,7 @@ Performance Strategies

 ## Supported SM Architectures

-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)

 ## Supported OSes

@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved

 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaMemset, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaMemcpy, cudaGetDeviceProperties
+cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMemset, cudaMalloc, cudaGetDeviceProperties

 ## Prerequisites

-Download and install the [CUDA Toolkit 11.6](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.8](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.

 ## Build and Run

--- a/Samples/6_Performance/alignedTypes/alignedTypes_vs2017.vcxproj
+++ b/Samples/6_Performance/alignedTypes/alignedTypes_vs2017.vcxproj
@@ -38,7 +38,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
  </ImportGroup>
  <ImportGroup Label="PropertySheets">
    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
      <OutputFile>$(OutDir)/alignedTypes.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/6_Performance/alignedTypes/alignedTypes_vs2019.vcxproj
+++ b/Samples/6_Performance/alignedTypes/alignedTypes_vs2019.vcxproj
@@ -34,7 +34,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.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>$(OutDir)/alignedTypes.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/6_Performance/alignedTypes/alignedTypes_vs2022.vcxproj
+++ b/Samples/6_Performance/alignedTypes/alignedTypes_vs2022.vcxproj
@@ -34,7 +34,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
  </ImportGroup>
  <ImportGroup Label="PropertySheets">
    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
      <OutputFile>$(OutDir)/alignedTypes.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/6_Performance/transpose/Makefile
+++ b/Samples/6_Performance/transpose/Makefile
@@ -279,9 +279,9 @@ LIBRARIES :=

 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87
+SMS ?= 53 61 70 72 75 80 86 87 90
 else
-SMS ?= 35 37 50 52 60 61 70 75 80 86
+SMS ?= 35 37 50 52 60 61 70 75 80 86 90
 endif

 ifeq ($(SMS),)
--- a/Samples/6_Performance/transpose/NsightEclipse.xml
+++ b/Samples/6_Performance/transpose/NsightEclipse.xml
@@ -3,17 +3,17 @@
 <entry>
  <name>transpose</name>
  <cuda_api_list>
-    <toolkit>cudaFree</toolkit>
-    <toolkit>cudaEventRecord</toolkit>
-    <toolkit>cudaEventCreate</toolkit>
-    <toolkit>cudaEventElapsedTime</toolkit>
-    <toolkit>cudaEventSynchronize</toolkit>
-    <toolkit>cudaMalloc</toolkit>
-    <toolkit>cudaEventDestroy</toolkit>
-    <toolkit>cudaGetLastError</toolkit>
    <toolkit>cudaMemcpy</toolkit>
-    <toolkit>cudaGetDeviceProperties</toolkit>
+    <toolkit>cudaMalloc</toolkit>
+    <toolkit>cudaFree</toolkit>
+    <toolkit>cudaGetLastError</toolkit>
+    <toolkit>cudaEventSynchronize</toolkit>
+    <toolkit>cudaEventRecord</toolkit>
    <toolkit>cudaGetDevice</toolkit>
+    <toolkit>cudaEventDestroy</toolkit>
+    <toolkit>cudaEventElapsedTime</toolkit>
+    <toolkit>cudaGetDeviceProperties</toolkit>
+    <toolkit>cudaEventCreate</toolkit>
  </cuda_api_list>
  <description><![CDATA[This sample demonstrates Matrix Transpose.  Different performance are shown to achieve high performance.]]></description>
  <devicecompilation>whole</devicecompilation>
@@ -55,6 +55,7 @@
  <sm-arch>sm80</sm-arch>
  <sm-arch>sm86</sm-arch>
  <sm-arch>sm87</sm-arch>
+  <sm-arch>sm90</sm-arch>
  <supported_envs>
    <env>
      <arch>x86_64</arch>
--- a/Samples/6_Performance/transpose/README.md
+++ b/Samples/6_Performance/transpose/README.md
@@ -10,7 +10,7 @@ Performance Strategies, Linear Algebra

 ## Supported SM Architectures

-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.3 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)

 ## Supported OSes

@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
 ## CUDA APIs involved

 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaFree, cudaEventRecord, cudaEventCreate, cudaEventElapsedTime, cudaEventSynchronize, cudaMalloc, cudaEventDestroy, cudaGetLastError, cudaMemcpy, cudaGetDeviceProperties, cudaGetDevice
+cudaMemcpy, cudaMalloc, cudaFree, cudaGetLastError, cudaEventSynchronize, cudaEventRecord, cudaGetDevice, cudaEventDestroy, cudaEventElapsedTime, cudaGetDeviceProperties, cudaEventCreate

 ## Prerequisites

-Download and install the [CUDA Toolkit 11.6](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.8](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.

 ## Build and Run

--- a/Samples/6_Performance/transpose/transpose_vs2017.vcxproj
+++ b/Samples/6_Performance/transpose/transpose_vs2017.vcxproj
@@ -38,7 +38,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
  </ImportGroup>
  <ImportGroup Label="PropertySheets">
    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
      <OutputFile>$(OutDir)/transpose.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/6_Performance/transpose/transpose_vs2019.vcxproj
+++ b/Samples/6_Performance/transpose/transpose_vs2019.vcxproj
@@ -34,7 +34,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.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>$(OutDir)/transpose.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/6_Performance/transpose/transpose_vs2022.vcxproj
+++ b/Samples/6_Performance/transpose/transpose_vs2022.vcxproj
@@ -34,7 +34,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
  </ImportGroup>
  <ImportGroup Label="PropertySheets">
    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
      <OutputFile>$(OutDir)/transpose.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>