mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2026-10-23 21:28:17 +08:00
Update samples for CUDA 11.8 with correct props
This commit is contained in:
Rob Nertney
@@ -322,9 +322,9 @@ endif
|
||||
|
||||
# Gencode arguments
|
||||
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
|
||||
SMS ?= 61 70 72 75 80 86 87
|
||||
SMS ?= 61 70 72 75 80 86 87 90
|
||||
else
|
||||
SMS ?= 60 61 70 75 80 86
|
||||
SMS ?= 60 61 70 75 80 86 90
|
||||
endif
|
||||
|
||||
ifeq ($(SMS),)
|
||||
|
||||
@@ -8,22 +8,22 @@
|
||||
<flag>--std=c++11</flag>
|
||||
</cflags>
|
||||
<cuda_api_list>
|
||||
<toolkit>cudaDeviceEnablePeerAccess</toolkit>
|
||||
<toolkit>cudaMemset</toolkit>
|
||||
<toolkit>cudaFree</toolkit>
|
||||
<toolkit>cudaMallocManaged</toolkit>
|
||||
<toolkit>cudaMemPrefetchAsync</toolkit>
|
||||
<toolkit>cudaHostAlloc</toolkit>
|
||||
<toolkit>cudaOccupancyMaxActiveBlocksPerMultiprocessor</toolkit>
|
||||
<toolkit>cudaStreamCreate</toolkit>
|
||||
<toolkit>cudaGetDeviceCount</toolkit>
|
||||
<toolkit>cudaFreeHost</toolkit>
|
||||
<toolkit>cudaSetDevice</toolkit>
|
||||
<toolkit>cudaDeviceCanAccessPeer</toolkit>
|
||||
<toolkit>cudaMemPrefetchAsync</toolkit>
|
||||
<toolkit>cudaFree</toolkit>
|
||||
<toolkit>cudaLaunchCooperativeKernel</toolkit>
|
||||
<toolkit>cudaStreamSynchronize</toolkit>
|
||||
<toolkit>cudaMemAdvise</toolkit>
|
||||
<toolkit>cudaMallocManaged</toolkit>
|
||||
<toolkit>cudaSetDevice</toolkit>
|
||||
<toolkit>cudaGetDeviceCount</toolkit>
|
||||
<toolkit>cudaGetDeviceProperties</toolkit>
|
||||
<toolkit>cudaFreeHost</toolkit>
|
||||
<toolkit>cudaMemset</toolkit>
|
||||
<toolkit>cudaStreamCreate</toolkit>
|
||||
<toolkit>cudaStreamSynchronize</toolkit>
|
||||
<toolkit>cudaDeviceEnablePeerAccess</toolkit>
|
||||
<toolkit>cudaMemAdvise</toolkit>
|
||||
<toolkit>cudaOccupancyMaxActiveBlocksPerMultiprocessor</toolkit>
|
||||
<toolkit>cudaDeviceCanAccessPeer</toolkit>
|
||||
</cuda_api_list>
|
||||
<description><![CDATA[This sample implements a conjugate gradient solver on multiple GPUs using Multi Device Cooperative Groups, also uses Unified Memory optimized using prefetching and usage hints.]]></description>
|
||||
<devicecompilation>whole</devicecompilation>
|
||||
@@ -71,6 +71,7 @@
|
||||
<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>
|
||||
|
||||
@@ -10,7 +10,7 @@ Unified Memory, Linear Algebra, Cooperative Groups, MultiDevice Cooperative Grou
|
||||
|
||||
## Supported SM Architectures
|
||||
|
||||
[SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
|
||||
[SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
|
||||
|
||||
## Supported OSes
|
||||
|
||||
@@ -23,14 +23,14 @@ x86_64, ppc64le, aarch64
|
||||
## CUDA APIs involved
|
||||
|
||||
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
|
||||
cudaDeviceEnablePeerAccess, cudaMemset, cudaFree, cudaMallocManaged, cudaMemPrefetchAsync, cudaHostAlloc, cudaOccupancyMaxActiveBlocksPerMultiprocessor, cudaStreamCreate, cudaGetDeviceCount, cudaFreeHost, cudaSetDevice, cudaDeviceCanAccessPeer, cudaLaunchCooperativeKernel, cudaStreamSynchronize, cudaMemAdvise, cudaGetDeviceProperties
|
||||
cudaHostAlloc, cudaMemPrefetchAsync, cudaFree, cudaLaunchCooperativeKernel, cudaMallocManaged, cudaSetDevice, cudaGetDeviceCount, cudaGetDeviceProperties, cudaFreeHost, cudaMemset, cudaStreamCreate, cudaStreamSynchronize, cudaDeviceEnablePeerAccess, cudaMemAdvise, cudaOccupancyMaxActiveBlocksPerMultiprocessor, cudaDeviceCanAccessPeer
|
||||
|
||||
## Dependencies needed to build/run
|
||||
[UVM](../../../README.md#uvm), [MDCG](../../../README.md#mdcg), [CPP11](../../../README.md#cpp11)
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Download and install the [CUDA Toolkit 11.6](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
|
||||
Download and install the [CUDA Toolkit 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
|
||||
|
||||
@@ -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)/conjugateGradientMultiDeviceCG.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
|
||||
<CodeGeneration>compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
|
||||
<Include>./;../../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
@@ -108,6 +108,6 @@
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
</PropertyGroup>
|
||||
<Import Project="$(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>$(OutDir)/conjugateGradientMultiDeviceCG.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
|
||||
<CodeGeneration>compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
|
||||
<Include>./;../../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
@@ -104,6 +104,6 @@
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
|
||||
@@ -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)/conjugateGradientMultiDeviceCG.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
|
||||
<CodeGeneration>compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
|
||||
<Include>./;../../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
@@ -104,6 +104,6 @@
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
|
||||
Reference in New Issue
Block a user