NASP/cuda-samples
85
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-10-23 21:28:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update samples for CUDA 11.8 with correct props

Browse Source
This commit is contained in:
Rob Nertney
2022-10-14 17:43:37 -07:00
parent b312abaa07
commit 81992093d2
1146 changed files with 4209 additions and 4272 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Samples/3_CUDA_Features/globalToShmemAsyncCopy/Makefile
View File

@@ -310,9 +310,9 @@ endif
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 70 72 75 80 86 87
SMS ?= 70 72 75 80 86 87 90
else
SMS ?= 70 75 80 86
SMS ?= 70 75 80 86 90
endif
ifeq ($(SMS),)

23
Samples/3_CUDA_Features/globalToShmemAsyncCopy/NsightEclipse.xml
View File

@@ -6,20 +6,20 @@
<flag>--std=c++11</flag>
</cflags>
<cuda_api_list>
<toolkit>cudaFree</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaMallocHost</toolkit>
<toolkit>cudaEventCreate</toolkit>
<toolkit>cudaMemsetAsync</toolkit>
<toolkit>cudaEventElapsedTime</toolkit>
<toolkit>cudaEventSynchronize</toolkit>
<toolkit>cudaDeviceGetAttribute</toolkit>
<toolkit>cudaFreeHost</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaStreamCreateWithFlags</toolkit>
<toolkit>cudaEventDestroy</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaDeviceGetAttribute</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaMallocHost</toolkit>
<toolkit>cudaEventSynchronize</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaFreeHost</toolkit>
<toolkit>cudaStreamSynchronize</toolkit>
<toolkit>cudaEventDestroy</toolkit>
<toolkit>cudaEventElapsedTime</toolkit>
<toolkit>cudaMemsetAsync</toolkit>
<toolkit>cudaMemcpyAsync</toolkit>
<toolkit>cudaEventCreate</toolkit>
</cuda_api_list>
<description><![CDATA[This sample implements matrix multiplication which uses asynchronous copy of data from global to shared memory when on compute capability 8.0 or higher. Also demonstrates arrive-wait barrier for synchronization.]]></description>
<devicecompilation>whole</devicecompilation>
@@ -59,6 +59,7 @@
<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>

6
Samples/3_CUDA_Features/globalToShmemAsyncCopy/README.md
View File

@@ -10,7 +10,7 @@ CUDA Runtime API, Linear Algebra, CPP11 CUDA
## Supported SM Architectures
[SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
[SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l, aarch64
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaFree, cudaEventRecord, cudaMallocHost, cudaEventCreate, cudaMemsetAsync, cudaEventElapsedTime, cudaEventSynchronize, cudaDeviceGetAttribute, cudaFreeHost, cudaMalloc, cudaStreamCreateWithFlags, cudaEventDestroy, cudaStreamSynchronize, cudaMemcpyAsync
cudaStreamCreateWithFlags, cudaMalloc, cudaDeviceGetAttribute, cudaFree, cudaMallocHost, cudaEventSynchronize, cudaEventRecord, cudaFreeHost, cudaStreamSynchronize, cudaEventDestroy, cudaEventElapsedTime, cudaMemsetAsync, cudaMemcpyAsync, cudaEventCreate
## Dependencies needed to build/run
[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

6
Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2017.vcxproj
View File

@@ -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)/globalToShmemAsyncCopy.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_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>

6
Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2019.vcxproj
View File

@@ -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)/globalToShmemAsyncCopy.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_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>

6
Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2022.vcxproj
View File

@@ -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)/globalToShmemAsyncCopy.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_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>