NASP/cuda-samples
85
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-10-23 13:18:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add and update samples with CUDA 11.2 support

Browse Source
This commit is contained in:
Mahesh Doijade
2020-12-10 01:05:32 +05:30
parent 92b0568792
commit 1cd3264681
355 changed files with 30425 additions and 7495 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Samples/EGLStream_CUDA_Interop/Makefile
View File

@@ -361,6 +361,8 @@ else
endif
endif
ALL_CCFLAGS += --threads 0
ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"
endif

2
Samples/EGLStream_CUDA_Interop/README.md
View File

@@ -30,7 +30,7 @@ cuDeviceGet, cuDeviceGetAttribute, cuDeviceComputeCapability, cuDeviceGetCount,
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

2
Samples/MersenneTwisterGP11213/Makefile
View File

@@ -293,6 +293,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --threads 0
LIBRARIES += -lcurand_static -lculibos
################################################################################

20
Samples/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "MersenneTwisterGP11213", "MersenneTwisterGP11213_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

107
Samples/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2015.vcxproj
View File

@@ -1,107 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>MersenneTwisterGP11213_vs2015</RootNamespace>
<ProjectName>MersenneTwisterGP11213</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>curand.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/MersenneTwisterGP11213.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,compute_35;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="MersenneTwister.cpp" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

2
Samples/MersenneTwisterGP11213/README.md
View File

@@ -27,7 +27,7 @@ x86_64, ppc64le, armv7l
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

2
Samples/NV12toBGRandResize/Makefile
View File

@@ -305,6 +305,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --threads 0
ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"
endif

112
Samples/NV12toBGRandResize/NV12toBGRandResize_vs2015.vcxproj
View File

@@ -1,112 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>NV12toBGRandResize_vs2015</RootNamespace>
<ProjectName>NV12toBGRandResize</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/NV12toBGRandResize.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="bgr_resize.cu" />
<CudaCompile Include="nv12_resize.cu" />
<CudaCompile Include="nv12_to_bgr_planar.cu" />
<ClCompile Include="resize_convert_main.cpp" />
<CudaCompile Include="utils.cu" />
<ClInclude Include="resize_convert.h" />
<ClInclude Include="utils.h" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/NV12toBGRandResize/NV12toBGRandResize_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -112,6 +113,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/NV12toBGRandResize/NV12toBGRandResize_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -108,6 +109,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

2
Samples/NV12toBGRandResize/README.md
View File

@@ -27,7 +27,7 @@ cudaMemcpy2D, cudaMallocManaged
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
## Build and Run

2
Samples/UnifiedMemoryPerf/Makefile
View File

@@ -305,6 +305,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --threads 0
ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"
endif

2
Samples/UnifiedMemoryPerf/README.md
View File

@@ -28,7 +28,7 @@ cudaMallocManaged, cudaStreamAttachMemAsync, cudaMemcpyAsync, cudaMallocHost, cu
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

110
Samples/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2015.vcxproj
View File

@@ -1,110 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>UnifiedMemoryPerf_vs2015</RootNamespace>
<ProjectName>UnifiedMemoryPerf</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="commonKernels.cu" />
<ClCompile Include="helperFunctions.cpp" />
<CudaCompile Include="matrixMultiplyPerf.cu" />
<ClInclude Include="commonDefs.hpp" />
<ClInclude Include="commonKernels.hpp" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -110,6 +111,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -106,6 +107,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

2
Samples/bandwidthTest/Makefile
View File

@@ -299,6 +299,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --threads 0
ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"
endif

2
Samples/bandwidthTest/README.md
View File

@@ -27,7 +27,7 @@ cudaSetDevice, cudaHostAlloc, cudaFree, cudaMallocHost, cudaFreeHost, cudaMemcpy
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
## Build and Run

20
Samples/bandwidthTest/bandwidthTest_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "bandwidthTest", "bandwidthTest_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

107
Samples/bandwidthTest/bandwidthTest_vs2015.vcxproj
View File

@@ -1,107 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>bandwidthTest_vs2015</RootNamespace>
<ProjectName>bandwidthTest</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/bandwidthTest.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="bandwidthTest.cu" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/bandwidthTest/bandwidthTest_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/bandwidthTest/bandwidthTest_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

2
Samples/batchedLabelMarkersAndLabelCompressionNPP/Makefile
View File

@@ -301,6 +301,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --threads 0
LIBRARIES += -lnppisu_static -lnppif_static -lnppc_static -lculibos
ifeq ($(SAMPLE_ENABLED),0)

2
Samples/batchedLabelMarkersAndLabelCompressionNPP/README.md
View File

@@ -28,7 +28,7 @@ x86_64, ppc64le, armv7l
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

20
Samples/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "batchedLabelMarkersAndLabelCompressionNPP", "batchedLabelMarkersAndLabelCompressionNPP_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

107
Samples/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2015.vcxproj
View File

@@ -1,107 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>batchedLabelMarkersAndLabelCompressionNPP_vs2015</RootNamespace>
<ProjectName>batchedLabelMarkersAndLabelCompressionNPP</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/batchedLabelMarkersAndLabelCompressionNPP.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,compute_35;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="batchedLabelMarkersAndLabelCompressionNPP.cpp" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

6
Samples/bf16TensorCoreGemm/Makefile
View File

@@ -301,11 +301,9 @@ ifeq ($(TARGET_OS),linux)
GCCVERSION += 00
# Remove spaces from the version number
GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION))
# Crop the version number to 3 decimals.
GCCVERSION := $(shell expr `echo $(GCCVERSION)` | cut -b1-3)
#$(warning $(GCCVERSION))
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 500)
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 50000)
ifeq ($(IS_MIN_VERSION), 1)
$(info >>> GCC Version is greater or equal to 5.0.0 <<<)
@@ -334,7 +332,7 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --std=c++11
ALL_CCFLAGS += --std=c++11 --threads 0
ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"

2
Samples/bf16TensorCoreGemm/README.md
View File

@@ -27,7 +27,7 @@ cudaMallocManaged, cudaDeviceSynchronize, cudaFuncSetAttribute, cudaEventCreate,
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
## Build and Run

95
Samples/bf16TensorCoreGemm/bf16TensorCoreGemm.cu
View File

@@ -62,7 +62,7 @@
#include <cuda.h>
#include <cuda_bf16.h>
#include <mma.h>
#include <cuda_pipeline.h>
#include <cuda/pipeline>
// helper functions and utilities to work with CUDA
#include <helper_functions.h>
@@ -70,10 +70,6 @@
// Externally configurable parameters.
// Switch for choosing cpp interface for cuda pipeline
// vs primitives interface.
#define USE_CPP_API 0
#ifndef CPU_DEBUG
// Set this to 1 to verify the correctness of the GPU-computed matrix.
#define CPU_DEBUG 0
@@ -183,7 +179,6 @@ const char* kernelNames[] = {"compute_bf16gemm_async_copy", "compute_bf16gemm",
"simple_wmma_bf16gemm"};
using namespace nvcuda;
namespace nvcuda_namespace = nvcuda::experimental;
__host__ void init_host_matrices(__nv_bfloat16 *a, __nv_bfloat16 *b, float *c)
{
@@ -369,8 +364,8 @@ __global__ void compute_bf16gemm(const __nv_bfloat16 *A, const __nv_bfloat16 *B,
#pragma unroll
for (int i = 0; i < N; i++) {
*((int4*)(dst_gmem_warp_stream_ptr + GLOBAL_MEM_STRIDE * i) + laneId) =
*((int4*)(shmem_warp_stream_ptr + SHMEM_STRIDE * i) + laneId);
*((float4*)(dst_gmem_warp_stream_ptr + GLOBAL_MEM_STRIDE * i) + laneId) =
*((float4*)(shmem_warp_stream_ptr + SHMEM_STRIDE * i) + laneId);
}
__syncthreads();
@@ -388,7 +383,7 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
const unsigned int laneId = threadIdx.x % WARP_SIZE;
// Offset in shared memory from which the B matrix is stored.
const size_t shmem_idx_b_off = BLOCK_COL_TILES * M;
constexpr size_t shmem_idx_b_off = BLOCK_COL_TILES * M;
// This pointer is used to access the C and D matrix tiles this warp computes.
float *shmem_warp_tile_ptr = (float*)&shmem[0][0] + (warpId / BLOCK_ROW_WARPS) * SHMEM_STRIDE * N * BLOCK_ROW_WARPS + (warpId % BLOCK_ROW_WARPS) * SHMEM_OFFSET;
@@ -401,9 +396,10 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
// in a loss of precision). Zero still needs to be specially handled though.
beta /= alpha;
#if USE_CPP_API
nvcuda_namespace::pipeline pipe;
#endif
cuda::pipeline<cuda::thread_scope_thread> pipe = cuda::make_pipeline();
const auto shape4 = cuda::aligned_size_t<alignof(float4)>(sizeof(float4));
constexpr int loadStride = 2; // load 4 floats, left-shift by 2.
// Each CTA slides along the 128 x 128 tiles from the top left corner of the matrix to the
// right and down, and selects the next tile to compute. Once there's no such tile,
// all warps in this CTA exit.
@@ -423,24 +419,17 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
// Stream multiple C tiles to shared memory.
#pragma unroll
for (int i = 0; i < N; i++) {
#if USE_CPP_API
nvcuda_namespace::memcpy_async(*((int4*)(shmem_warp_stream_ptr + SHMEM_STRIDE * i) + laneId),
*((int4*)(src_gmem_warp_stream_ptr + GLOBAL_MEM_STRIDE * i) + laneId),
pipe);
pipe.commit();
#else
__pipeline_memcpy_async((reinterpret_cast<int4*>(&shmem_warp_stream_ptr[(SHMEM_STRIDE * i)])) + laneId,
(reinterpret_cast<const int4*>(&src_gmem_warp_stream_ptr[(GLOBAL_MEM_STRIDE * i)])) + laneId,
sizeof(int4));
__pipeline_commit();
#endif
pipe.producer_acquire();
cuda::memcpy_async(&shmem_warp_stream_ptr[(SHMEM_STRIDE * i) + (laneId << loadStride)],
&src_gmem_warp_stream_ptr[(GLOBAL_MEM_STRIDE * i) + (laneId << loadStride)],
shape4, pipe);
pipe.producer_commit();
}
#if USE_CPP_API
pipe.wait_prior<0>();
#else
__pipeline_wait_prior(0);
#endif
// Now wait for all the above issued 8 batches to complete.
cuda::pipeline_consumer_wait_prior<0>(pipe);
__syncthreads();
// These fragments will accumulate the result of A and B matrix fragment multiplications
@@ -455,16 +444,7 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
const float *tile_ptr = shmem_warp_tile_ptr + i * SHMEM_STRIDE * N + j * N;
wmma::load_matrix_sync(c[i][j], tile_ptr, SHMEM_STRIDE, C_LAYOUT);
}
}
__syncthreads();
// Scale the C matrix.
#pragma unroll
for (int i = 0; i < WARP_COL_TILES; i++) {
#pragma unroll
for (int j = 0; j < WARP_ROW_TILES; j++) {
// Scale the C matrix.
#pragma unroll
for (int t = 0; t < c[i][j].num_elements; t++) {
c[i][j].x[t] *= beta;
@@ -472,48 +452,46 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
}
}
pipe.consumer_release();
// sync here so that shared memory can then be used for loading A & B matrices.
__syncthreads();
// Select what warp copies what matrix to shared memory.
// Warps 0-3 copy the A matrix, warps 4-7 copy the B matrix.
const __nv_bfloat16 *warp_ptr = (warpId < (WARPS_PER_BLOCK/2)) ? (&A[block_tile_i * M * K_GLOBAL] + M * K_GLOBAL * (warpId % (WARPS_PER_BLOCK/2)) * 2) :
(&B[block_tile_j * N * K_GLOBAL] + N * K_GLOBAL * (warpId % (WARPS_PER_BLOCK/2)) * 2);
constexpr int chunksPerLane = ((WARP_SIZE/2) / CHUNK_COPY_LINES_PER_WARP) * 2;
constexpr int loadStrideBfloat8 = 3; // load 8 bfloats, left-shift by 3.
const int laneLoadElem = (laneId % CHUNK_COPY_LINE_LANES) << loadStrideBfloat8;
const int stridePerLaneCopy = (laneId / CHUNK_COPY_LINE_LANES);
// Go through the global K dimension by a fixed step at a time.
#pragma unroll
for (int tile_k = 0; tile_k < K_TILES; tile_k += CHUNK_K) {
// Copy slices of the A and B matrices to shared memory.
// The first half of the warps in the CTA copy the A matrix, the rest copy the B matrix.
size_t shmem_idx = warpId < (WARPS_PER_BLOCK/2) ? (M * (warpId % (WARPS_PER_BLOCK/2)) * 2) :
(N * (warpId % (WARPS_PER_BLOCK/2)) * 2 + shmem_idx_b_off);
// As for bf16 MMA M == N we use M for warp 4-7 + shmem_idx_b_off.
size_t shmem_idx = (M * (warpId % (WARPS_PER_BLOCK/2)) * 2) + ((warpId / (WARPS_PER_BLOCK/2)) * shmem_idx_b_off);
// First half of the warp copies the first row / column of the matrix,
// the second half of the warp copies the next.
const __nv_bfloat16 *lane_ptr = (warp_ptr + tile_k * K + (laneId / CHUNK_COPY_LINE_LANES) * K_GLOBAL);
const __nv_bfloat16 *lane_ptr = warp_ptr + tile_k * K + stridePerLaneCopy * K_GLOBAL + laneLoadElem;
// Shift the second half of the warp to the next row / column in the shared memory.
shmem_idx += laneId / CHUNK_COPY_LINE_LANES;
shmem_idx += stridePerLaneCopy;
#pragma unroll
for(int i = 0; i < ((WARP_SIZE/2) / CHUNK_COPY_LINES_PER_WARP) * 2; i++) {
for(int i = 0; i < chunksPerLane; i++) {
// Copy 16 bytes at once in each lane.
#if USE_CPP_API
nvcuda_namespace::memcpy_async(*((int4*)&shmem[shmem_idx][0] + (laneId % CHUNK_COPY_LINE_LANES)),
*((int4*)lane_ptr + (laneId % CHUNK_COPY_LINE_LANES)), pipe);
pipe.commit();
#else
__pipeline_memcpy_async((int4*)&shmem[shmem_idx][0] + (laneId % CHUNK_COPY_LINE_LANES),
(int4*)lane_ptr + (laneId % CHUNK_COPY_LINE_LANES), sizeof(int4));
__pipeline_commit();
#endif
pipe.producer_acquire();
cuda::memcpy_async(&shmem[shmem_idx][laneLoadElem], lane_ptr, shape4, pipe);
pipe.producer_commit();
// Advance the global memory pointer and the shared memory index.
lane_ptr = lane_ptr + K_GLOBAL * CHUNK_COPY_LINES_PER_WARP;
shmem_idx += CHUNK_COPY_LINES_PER_WARP;
}
#if USE_CPP_API
pipe.wait_prior<0>();
#else
__pipeline_wait_prior(0);
#endif
cuda::pipeline_consumer_wait_prior<0>(pipe);
__syncthreads();
// Compute a grid of C matrix tiles in each warp.
@@ -545,6 +523,7 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
}
}
pipe.consumer_release();
__syncthreads();
}

20
Samples/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "bf16TensorCoreGemm", "bf16TensorCoreGemm_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

107
Samples/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2015.vcxproj
View File

@@ -1,107 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>bf16TensorCoreGemm_vs2015</RootNamespace>
<ProjectName>bf16TensorCoreGemm</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/bf16TensorCoreGemm.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="bf16TensorCoreGemm.cu" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

6
Samples/binaryPartitionCG/Makefile
View File

@@ -295,11 +295,9 @@ ifeq ($(TARGET_OS),linux)
GCCVERSION += 00
# Remove spaces from the version number
GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION))
# Crop the version number to 3 decimals.
GCCVERSION := $(shell expr `echo $(GCCVERSION)` | cut -b1-3)
#$(warning $(GCCVERSION))
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 470)
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 47000)
ifeq ($(IS_MIN_VERSION), 1)
$(info >>> GCC Version is greater or equal to 4.7.0 <<<)
@@ -332,7 +330,7 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --std=c++11
ALL_CCFLAGS += --std=c++11 --threads 0
ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"

2
Samples/binaryPartitionCG/README.md
View File

@@ -24,7 +24,7 @@ x86_64, ppc64le, armv7l
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
## Build and Run

20
Samples/binaryPartitionCG/binaryPartitionCG_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "binaryPartitionCG", "binaryPartitionCG_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

107
Samples/binaryPartitionCG/binaryPartitionCG_vs2015.vcxproj
View File

@@ -1,107 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>binaryPartitionCG_vs2015</RootNamespace>
<ProjectName>binaryPartitionCG</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/binaryPartitionCG.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="binaryPartitionCG.cu" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/binaryPartitionCG/binaryPartitionCG_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/binaryPartitionCG/binaryPartitionCG_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

8
Samples/boxFilterNPP/Makefile
View File

@@ -301,12 +301,14 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
INCLUDES += -I../../Common/UtilNPP -I../../Common/FreeImage/include
ALL_CCFLAGS += --threads 0
LIBRARIES += -L../../Common/FreeImage/lib/x64 -L../../Common/FreeImage/lib/$(TARGET_OS) -L../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH) -lnppisu_static -lnppif_static -lnppc_static -lculibos -lfreeimage
INCLUDES += -I../../Common/UtilNPP
LIBRARIES += -lnppisu_static -lnppif_static -lnppc_static -lculibos -lfreeimage
# Attempt to compile a minimal application linked against FreeImage. If a.out exists, FreeImage is properly set up.
$(shell echo "#include \"FreeImage.h\"" > test.c; echo "int main() { return 0; }" >> test.c ; $(NVCC) $(ALL_CCFLAGS) $(INCLUDES) $(LIBRARIES) -l freeimage test.c)
$(shell echo "#include \"FreeImage.h\"" > test.c; echo "int main() { return 0; }" >> test.c ; $(NVCC) $(ALL_CCFLAGS) $(INCLUDES) $(ALL_LDFLAGS) $(LIBRARIES) -l freeimage test.c)
FREEIMAGE := $(shell find a.out 2>/dev/null)
$(shell rm a.out test.c 2>/dev/null)

4
Samples/boxFilterNPP/NsightEclipse.xml
View File

@@ -10,7 +10,7 @@
</files>
<includepaths>
<path>../../Common/UtilNPP</path>
<path>../../Common/FreeImage/include</path>
<path os="Windows">../../Common/FreeImage/Dist/x64</path>
<path>./</path>
<path>../</path>
<path>../../common/inc</path>
@@ -34,8 +34,6 @@
<library>freeimage</library>
</libraries>
<librarypaths>
<path>../../Common/FreeImage/lib/$(TARGET_OS)</path>
<path>../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH)</path>
</librarypaths>
<nsight_eclipse>true</nsight_eclipse>
<primary_file>boxFilterNPP.cpp</primary_file>

2
Samples/boxFilterNPP/README.md
View File

@@ -27,7 +27,7 @@ x86_64, ppc64le, armv7l
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

20
Samples/boxFilterNPP/boxFilterNPP_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "boxFilterNPP", "boxFilterNPP_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

117
Samples/boxFilterNPP/boxFilterNPP_vs2015.vcxproj
View File

@@ -1,117 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>boxFilterNPP_vs2015</RootNamespace>
<ProjectName>boxFilterNPP</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/include;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/lib/x64;../../Common/FreeImage/lib/$(TARGET_OS);../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/boxFilterNPP.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,compute_35;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Platform)'=='Win32'">
<Link>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Platform)'=='x64'">
<Link>
<AdditionalDependencies>freeimage.lib;%(AdditionalDependencies)</AdditionalDependencies>
</Link>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="boxFilterNPP.cpp" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

9
Samples/boxFilterNPP/boxFilterNPP_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -58,12 +58,12 @@
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/include;</AdditionalIncludeDirectories>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/Dist/x64;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/lib/x64;../../Common/FreeImage/lib/$(TARGET_OS);../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH);</AdditionalLibraryDirectories>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/Dist/x64;</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/boxFilterNPP.exe</OutputFile>
</Link>
<CudaCompile>
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -117,6 +118,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

9
Samples/boxFilterNPP/boxFilterNPP_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -54,12 +54,12 @@
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/include;</AdditionalIncludeDirectories>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/Dist/x64;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/lib/x64;../../Common/FreeImage/lib/$(TARGET_OS);../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH);</AdditionalLibraryDirectories>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/Dist/x64;</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/boxFilterNPP.exe</OutputFile>
</Link>
<CudaCompile>
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -113,6 +114,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

8
Samples/cannyEdgeDetectorNPP/Makefile
View File

@@ -301,12 +301,14 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
INCLUDES += -I../../Common/UtilNPP -I../../Common/FreeImage/include
ALL_CCFLAGS += --threads 0
LIBRARIES += -L../../Common/FreeImage/lib/x64 -L../../Common/FreeImage/lib/$(TARGET_OS) -L../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH) -lnppisu_static -lnppif_static -lnppc_static -lculibos -lfreeimage
INCLUDES += -I../../Common/UtilNPP
LIBRARIES += -lnppisu_static -lnppif_static -lnppc_static -lculibos -lfreeimage
# Attempt to compile a minimal application linked against FreeImage. If a.out exists, FreeImage is properly set up.
$(shell echo "#include \"FreeImage.h\"" > test.c; echo "int main() { return 0; }" >> test.c ; $(NVCC) $(ALL_CCFLAGS) $(INCLUDES) $(LIBRARIES) -l freeimage test.c)
$(shell echo "#include \"FreeImage.h\"" > test.c; echo "int main() { return 0; }" >> test.c ; $(NVCC) $(ALL_CCFLAGS) $(INCLUDES) $(ALL_LDFLAGS) $(LIBRARIES) -l freeimage test.c)
FREEIMAGE := $(shell find a.out 2>/dev/null)
$(shell rm a.out test.c 2>/dev/null)

4
Samples/cannyEdgeDetectorNPP/NsightEclipse.xml
View File

@@ -7,7 +7,7 @@
<fallback_min_ptx>true</fallback_min_ptx>
<includepaths>
<path>../../Common/UtilNPP</path>
<path>../../Common/FreeImage/include</path>
<path os="Windows">../../Common/FreeImage/Dist/x64</path>
<path>./</path>
<path>../</path>
<path>../../common/inc</path>
@@ -30,8 +30,6 @@
<library>freeimage</library>
</libraries>
<librarypaths>
<path>../../Common/FreeImage/lib/$(TARGET_OS)</path>
<path>../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH)</path>
</librarypaths>
<nsight_eclipse>true</nsight_eclipse>
<primary_file>cannyEdgeDetectorNPP.cpp</primary_file>

2
Samples/cannyEdgeDetectorNPP/README.md
View File

@@ -27,7 +27,7 @@ x86_64, ppc64le, armv7l
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

20
Samples/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cannyEdgeDetectorNPP", "cannyEdgeDetectorNPP_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

117
Samples/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2015.vcxproj
View File

@@ -1,117 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>cannyEdgeDetectorNPP_vs2015</RootNamespace>
<ProjectName>cannyEdgeDetectorNPP</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/include;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/lib/x64;../../Common/FreeImage/lib/$(TARGET_OS);../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/cannyEdgeDetectorNPP.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,compute_35;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Platform)'=='Win32'">
<Link>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Platform)'=='x64'">
<Link>
<AdditionalDependencies>freeimage.lib;%(AdditionalDependencies)</AdditionalDependencies>
</Link>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="cannyEdgeDetectorNPP.cpp" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

9
Samples/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -58,12 +58,12 @@
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/include;</AdditionalIncludeDirectories>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/Dist/x64;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/lib/x64;../../Common/FreeImage/lib/$(TARGET_OS);../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH);</AdditionalLibraryDirectories>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/Dist/x64;</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/cannyEdgeDetectorNPP.exe</OutputFile>
</Link>
<CudaCompile>
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -117,6 +118,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

9
Samples/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -54,12 +54,12 @@
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/include;</AdditionalIncludeDirectories>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/Dist/x64;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/lib/x64;../../Common/FreeImage/lib/$(TARGET_OS);../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH);</AdditionalLibraryDirectories>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/Dist/x64;</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/cannyEdgeDetectorNPP.exe</OutputFile>
</Link>
<CudaCompile>
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -113,6 +114,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

2
Samples/concurrentKernels/Makefile
View File

@@ -299,6 +299,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --threads 0
ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"
endif

2
Samples/concurrentKernels/README.md
View File

@@ -24,7 +24,7 @@ x86_64, ppc64le, armv7l
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
## Build and Run

20
Samples/concurrentKernels/concurrentKernels_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "concurrentKernels", "concurrentKernels_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

5
Samples/concurrentKernels/concurrentKernels_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/concurrentKernels/concurrentKernels_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

2
Samples/conjugateGradientCudaGraphs/Makefile
View File

@@ -299,6 +299,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --threads 0
LIBRARIES += -lcublas_static -lcublasLt_static -lcusparse_static -lculibos
ifeq ($(SAMPLE_ENABLED),0)

2
Samples/conjugateGradientCudaGraphs/README.md
View File

@@ -30,7 +30,7 @@ cudaStreamBeginCapture, cudaStreamEndCapture, cudaGraphCreate, cudaGraphLaunch,
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

20
Samples/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "conjugateGradientCudaGraphs", "conjugateGradientCudaGraphs_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

107
Samples/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2015.vcxproj
View File

@@ -1,107 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>conjugateGradientCudaGraphs_vs2015</RootNamespace>
<ProjectName>conjugateGradientCudaGraphs</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cublas.lib;cusparse.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/conjugateGradientCudaGraphs.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>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="conjugateGradientCudaGraphs.cu" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

6
Samples/conjugateGradientMultiBlockCG/Makefile
View File

@@ -307,11 +307,9 @@ ifeq ($(TARGET_OS),linux)
GCCVERSION += 00
# Remove spaces from the version number
GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION))
# Crop the version number to 3 decimals.
GCCVERSION := $(shell expr `echo $(GCCVERSION)` | cut -b1-3)
#$(warning $(GCCVERSION))
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 470)
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 47000)
ifeq ($(IS_MIN_VERSION), 1)
$(info >>> GCC Version is greater or equal to 4.7.0 <<<)
@@ -344,7 +342,7 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --std=c++11
ALL_CCFLAGS += --std=c++11 --threads 0
ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"

2
Samples/conjugateGradientMultiBlockCG/README.md
View File

@@ -27,7 +27,7 @@ x86_64, ppc64le, aarch64
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

20
Samples/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "conjugateGradientMultiBlockCG", "conjugateGradientMultiBlockCG_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

107
Samples/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2015.vcxproj
View File

@@ -1,107 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>conjugateGradientMultiBlockCG_vs2015</RootNamespace>
<ProjectName>conjugateGradientMultiBlockCG</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/conjugateGradientMultiBlockCG.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="conjugateGradientMultiBlockCG.cu" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

6
Samples/conjugateGradientMultiDeviceCG/Makefile
View File

@@ -307,11 +307,9 @@ ifeq ($(TARGET_OS),linux)
GCCVERSION += 00
# Remove spaces from the version number
GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION))
# Crop the version number to 3 decimals.
GCCVERSION := $(shell expr `echo $(GCCVERSION)` | cut -b1-3)
#$(warning $(GCCVERSION))
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 470)
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 47000)
ifeq ($(IS_MIN_VERSION), 1)
$(info >>> GCC Version is greater or equal to 4.7.0 <<<)
@@ -344,7 +342,7 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += -ewp -maxrregcount=64 --std=c++11
ALL_CCFLAGS += -ewp -maxrregcount=64 --std=c++11 --threads 0
LIBRARIES += -lcudadevrt

2
Samples/conjugateGradientMultiDeviceCG/README.md
View File

@@ -30,7 +30,7 @@ cudaMemAdvise, cudaMemPrefetchAsync, cudaLaunchCooperativeKernelMultiDevice, cud
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

20
Samples/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "conjugateGradientMultiDeviceCG", "conjugateGradientMultiDeviceCG_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

108
Samples/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2015.vcxproj
View File

@@ -1,108 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>conjugateGradientMultiDeviceCG_vs2015</RootNamespace>
<ProjectName>conjugateGradientMultiDeviceCG</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudadevrt.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(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>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<ExtensibleWholeProgramCompilation>true</ExtensibleWholeProgramCompilation>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="conjugateGradientMultiDeviceCG.cu" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -72,6 +72,7 @@
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<ExtensibleWholeProgramCompilation>true</ExtensibleWholeProgramCompilation>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -108,6 +109,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -68,6 +68,7 @@
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<ExtensibleWholeProgramCompilation>true</ExtensibleWholeProgramCompilation>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -104,6 +105,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

2
Samples/cuSolverDn_LinearSolver/Makefile
View File

@@ -286,6 +286,8 @@ LIBRARIES :=
################################################################################
ALL_CCFLAGS += --threads 0
LIBRARIES += -lcusolver -lcublas -lcusparse
ifeq ($(SAMPLE_ENABLED),0)

2
Samples/cuSolverDn_LinearSolver/README.md
View File

@@ -27,7 +27,7 @@ x86_64, ppc64le, aarch64
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

109
Samples/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2015.vcxproj
View File

@@ -1,109 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>cuSolverDn_LinearSolver_vs2015</RootNamespace>
<ProjectName>cuSolverDn_LinearSolver</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cusolver.lib;cublas.lib;cusparse.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/cuSolverDn_LinearSolver.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration></CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="cuSolverDn_LinearSolver.cpp" />
<ClCompile Include="mmio.c" />
<ClCompile Include="mmio_wrapper.cpp" />
<ClInclude Include="mmio.h" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -109,6 +110,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -105,6 +106,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

2
Samples/cuSolverSp_LinearSolver/Makefile
View File

@@ -303,6 +303,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --threads 0
LIBRARIES += -lcusolver -lcusparse
ifeq ($(SAMPLE_ENABLED),0)

2
Samples/cuSolverSp_LinearSolver/README.md
View File

@@ -27,7 +27,7 @@ x86_64, ppc64le, armv7l
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

109
Samples/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2015.vcxproj
View File

@@ -1,109 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>cuSolverSp_LinearSolver_vs2015</RootNamespace>
<ProjectName>cuSolverSp_LinearSolver</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cusolver.lib;cusparse.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/cuSolverSp_LinearSolver.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>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="cuSolverSp_LinearSolver.cpp" />
<ClCompile Include="mmio.c" />
<ClCompile Include="mmio_wrapper.cpp" />
<ClInclude Include="mmio.h" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -109,6 +110,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -105,6 +106,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

2
Samples/cudaCompressibleMemory/Makefile
View File

@@ -382,6 +382,8 @@ else
endif
endif
ALL_CCFLAGS += --threads 0
LIBRARIES += -lcudart_static
ifeq ($(SAMPLE_ENABLED),0)

2
Samples/cudaCompressibleMemory/README.md
View File

@@ -30,7 +30,7 @@ cudaMalloc, cudaFree
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
## Build and Run

20
Samples/cudaCompressibleMemory/cudaCompressibleMemory_vs2015.sln
View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cudaCompressibleMemory", "cudaCompressibleMemory_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

108
Samples/cudaCompressibleMemory/cudaCompressibleMemory_vs2015.vcxproj
View File

@@ -1,108 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>cudaCompressibleMemory_vs2015</RootNamespace>
<ProjectName>cudaCompressibleMemory</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cuda.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/cudaCompressibleMemory.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>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="compMalloc.cpp" />
<CudaCompile Include="saxpy.cu" />
<ClInclude Include="compMalloc.h" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
</ImportGroup>
</Project>

5
Samples/cudaCompressibleMemory/cudaCompressibleMemory_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -108,6 +109,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

5
Samples/cudaCompressibleMemory/cudaCompressibleMemory_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -104,6 +105,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup>
</Project>

6
Samples/cudaNvSci/Makefile
View File

@@ -306,11 +306,9 @@ ifeq ($(TARGET_OS),linux)
GCCVERSION += 00
# Remove spaces from the version number
GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION))
# Crop the version number to 3 decimals.
GCCVERSION := $(shell expr `echo $(GCCVERSION)` | cut -b1-3)
#$(warning $(GCCVERSION))
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 470)
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 47000)
ifeq ($(IS_MIN_VERSION), 1)
$(info >>> GCC Version is greater or equal to 4.7.0 <<<)
@@ -400,7 +398,7 @@ else
endif
endif
ALL_CCFLAGS += --std=c++11
ALL_CCFLAGS += --std=c++11 --threads 0
LIBRARIES += -lnvscibuf -lnvscisync

2
Samples/cudaNvSci/README.md
View File

@@ -30,7 +30,7 @@ cudaImportExternalMemory, cudaExternalMemoryGetMappedBuffer, cudaExternalMemoryG
## Prerequisites
Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

16
Samples/cudaNvSci/cudaNvSci.cpp
View File

@@ -122,12 +122,10 @@ class cudaNvSciSignal {
void setRawBufAttrList(uint64_t size) {
NvSciBufType bufType = NvSciBufType_RawBuffer;
uint64_t tempAlignment = 0;
bool cpuAccess = false;
NvSciBufAttrValAccessPerm perm = NvSciBufAccessPerm_ReadWrite;
NvSciBufAttrKeyValuePair rawBufAttrs[] = {
{NvSciBufRawBufferAttrKey_Size, &size, sizeof(size)},
{NvSciBufRawBufferAttrKey_Align, &tempAlignment, sizeof(tempAlignment)},
{NvSciBufGeneralAttrKey_Types, &bufType, sizeof(bufType)},
{NvSciBufGeneralAttrKey_NeedCpuAccess, &cpuAccess, sizeof(cpuAccess)},
{NvSciBufGeneralAttrKey_RequiredPerm, &perm, sizeof(perm)},
@@ -234,13 +232,11 @@ class cudaNvSciSignal {
memset(pairArrayOut, 0, sizeof(NvSciBufAttrKeyValuePair) * 10);
pairArrayOut[0].key = NvSciBufRawBufferAttrKey_Size;
pairArrayOut[1].key = NvSciBufRawBufferAttrKey_Align;
checkNvSciErrors(
NvSciBufAttrListGetAttrs(m_buffAttrListOut[0], pairArrayOut, 2));
NvSciBufAttrListGetAttrs(m_buffAttrListOut[0], pairArrayOut, 1));
uint64_t size = *(uint64_t *)pairArrayOut[0].value;
uint64_t offset = *(uint64_t *)pairArrayOut[1].value;
cudaExternalMemoryHandleDesc memHandleDesc;
memset(&memHandleDesc, 0, sizeof(memHandleDesc));
@@ -251,7 +247,7 @@ class cudaNvSciSignal {
cudaExternalMemoryBufferDesc bufferDesc;
memset(&bufferDesc, 0, sizeof(bufferDesc));
bufferDesc.offset = offset;
bufferDesc.offset = 0;
bufferDesc.size = size;
m_bufSize = size;
checkCudaErrors(cudaExternalMemoryGetMappedBuffer(
@@ -410,12 +406,10 @@ class cudaNvSciWait {
void setRawBufAttrList(uint64_t size) {
NvSciBufType bufType = NvSciBufType_RawBuffer;
uint64_t tempAlignment = 0;
bool cpuAccess = false;
NvSciBufAttrValAccessPerm perm = NvSciBufAccessPerm_ReadWrite;
NvSciBufAttrKeyValuePair rawBufAttrs[] = {
{NvSciBufRawBufferAttrKey_Size, &size, sizeof(size)},
{NvSciBufRawBufferAttrKey_Align, &tempAlignment, sizeof(tempAlignment)},
{NvSciBufGeneralAttrKey_Types, &bufType, sizeof(bufType)},
{NvSciBufGeneralAttrKey_NeedCpuAccess, &cpuAccess, sizeof(cpuAccess)},
{NvSciBufGeneralAttrKey_RequiredPerm, &perm, sizeof(perm)},
@@ -475,13 +469,11 @@ class cudaNvSciWait {
memset(pairArrayOut, 0, sizeof(NvSciBufAttrKeyValuePair) * 10);
pairArrayOut[0].key = NvSciBufRawBufferAttrKey_Size;
pairArrayOut[1].key = NvSciBufRawBufferAttrKey_Align;
checkNvSciErrors(
NvSciBufAttrListGetAttrs(m_buffAttrListOut, pairArrayOut, 2));
NvSciBufAttrListGetAttrs(m_buffAttrListOut, pairArrayOut, 1));
uint64_t size = *(uint64_t *)pairArrayOut[0].value;
uint64_t offset = *(uint64_t *)pairArrayOut[1].value;
cudaExternalMemoryHandleDesc memHandleDesc;
memset(&memHandleDesc, 0, sizeof(memHandleDesc));
@@ -492,7 +484,7 @@ class cudaNvSciWait {
cudaExternalMemoryBufferDesc bufferDesc;
memset(&bufferDesc, 0, sizeof(bufferDesc));
bufferDesc.offset = offset;
bufferDesc.offset = 0;
bufferDesc.size = size;
m_bufSize = size;

6
Samples/cudaNvSciNvMedia/Makefile
View File

@@ -314,11 +314,9 @@ ifeq ($(TARGET_OS),linux)
GCCVERSION += 00
# Remove spaces from the version number
GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION))
# Crop the version number to 3 decimals.
GCCVERSION := $(shell expr `echo $(GCCVERSION)` | cut -b1-3)
#$(warning $(GCCVERSION))
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 470)
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 47000)
ifeq ($(IS_MIN_VERSION), 1)
$(info >>> GCC Version is greater or equal to 4.7.0 <<<)
@@ -408,7 +406,7 @@ else
endif
endif
ALL_CCFLAGS += --std=c++11
ALL_CCFLAGS += --std=c++11 --threads 0
LIBRARIES += -lnvscibuf -lnvscisync -lnvmedia

Some files were not shown because too many files have changed in this diff Show More