Update samples for CUDA 11.8 with correct props

2026-10-23 21:28:17 +08:00 · 2022-10-14 17:43:37 -07:00
parent b312abaa07
commit 81992093d2
1146 changed files with 4209 additions and 4272 deletions
--- a/Samples/5_Domain_Specific/simpleVulkanMMAP/Makefile
+++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/Makefile
@@ -340,9 +340,9 @@ endif

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

 ifeq ($(SMS),)
--- a/Samples/5_Domain_Specific/simpleVulkanMMAP/NsightEclipse.xml
+++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/NsightEclipse.xml
@@ -6,36 +6,36 @@
    <flag>--std=c++11</flag>
  </cflags>
  <cuda_api_list>
+    <driver>cuMemCreate</driver>
+    <driver>cuMemAddressReserve</driver>
+    <driver>cuMemGetAllocationGranularity</driver>
+    <driver>cuMemAddressFree</driver>
+    <driver>cuMemUnmap</driver>
+    <driver>cuMemMap</driver>
    <driver>cuMemRelease</driver>
    <driver>cuMemExportToShareableHandle</driver>
    <driver>cuMemSetAccess</driver>
-    <driver>cuMemMap</driver>
-    <driver>cuMemCreate</driver>
-    <driver>cuMemAddressFree</driver>
-    <driver>cuMemGetAllocationGranularity</driver>
-    <driver>cuMemUnmap</driver>
-    <driver>cuMemAddressReserve</driver>
-    <toolkit>cudaOccupancyMaxActiveBlocksPerMultiprocessor</toolkit>
+    <toolkit>cudaWaitExternalSemaphoresAsync</toolkit>
    <toolkit>cudaImportExternalSemaphore</toolkit>
-    <toolkit>cudaStreamCreateWithFlags</toolkit>
-    <toolkit>cudaMemcpyAsync</toolkit>
-    <toolkit>cudaStreamDestroy</toolkit>
-    <toolkit>cudaSignalExternalSemaphoresAsync</toolkit>
-    <toolkit>cudaMallocHost</toolkit>
-    <toolkit>cudaMalloc</toolkit>
-    <toolkit>cudaSetDevice</toolkit>
-    <toolkit>cudaGetDeviceProperties</toolkit>
-    <toolkit>cudaGetDeviceCount</toolkit>
    <toolkit>cudaDeviceGetAttribute</toolkit>
+    <toolkit>cudaSetDevice</toolkit>
+    <toolkit>cudaLaunchHostFunc</toolkit>
+    <toolkit>cudaMallocHost</toolkit>
+    <toolkit>cudaSignalExternalSemaphoresAsync</toolkit>
+    <toolkit>cudaFreeHost</toolkit>
+    <toolkit>cudaMemsetAsync</toolkit>
+    <toolkit>cudaMemcpyAsync</toolkit>
+    <toolkit>cudaGetDeviceCount</toolkit>
+    <toolkit>cudaStreamCreateWithFlags</toolkit>
+    <toolkit>cudaStreamDestroy</toolkit>
+    <toolkit>cudaDestroyExternalSemaphore</toolkit>
    <toolkit>cudaSignalSemaphore</toolkit>
    <toolkit>cudaWaitSemaphore</toolkit>
-    <toolkit>cudaDestroyExternalSemaphore</toolkit>
-    <toolkit>cudaStreamSynchronize</toolkit>
    <toolkit>cudaFree</toolkit>
-    <toolkit>cudaLaunchHostFunc</toolkit>
-    <toolkit>cudaMemsetAsync</toolkit>
-    <toolkit>cudaFreeHost</toolkit>
-    <toolkit>cudaWaitExternalSemaphoresAsync</toolkit>
+    <toolkit>cudaStreamSynchronize</toolkit>
+    <toolkit>cudaMalloc</toolkit>
+    <toolkit>cudaOccupancyMaxActiveBlocksPerMultiprocessor</toolkit>
+    <toolkit>cudaGetDeviceProperties</toolkit>
  </cuda_api_list>
  <description><![CDATA[ This sample demonstrates Vulkan CUDA Interop via cuMemMap APIs. CUDA exports buffers that Vulkan imports as vertex buffer. CUDA invokes kernels to operate on vertices and synchronizes with Vulkan through vulkan semaphores imported by CUDA. This sample depends on Vulkan SDK, GLFW3 libraries, for building this sample please refer to "Build_instructions.txt" provided in this sample's directory]]></description>
  <devicecompilation>whole</devicecompilation>
@@ -91,6 +91,7 @@
  <sm-arch>sm80</sm-arch>
  <sm-arch>sm86</sm-arch>
  <sm-arch>sm87</sm-arch>
+  <sm-arch>sm90</sm-arch>
  <sources>
    <extracompilation>../../../Common/helper_multiprocess.cpp</extracompilation>
    <extraheader>../../../Common/helper_multiprocess.h</extraheader>
--- a/Samples/5_Domain_Specific/simpleVulkanMMAP/README.md
+++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/README.md
@@ -10,7 +10,7 @@ cuMemMap IPC, MMAP, Graphics Interop, CUDA Vulkan Interop, Data Parallel Algorit

 ## Supported SM Architectures

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

 ## Supported OSes

@@ -23,17 +23,17 @@ x86_64, aarch64
 ## CUDA APIs involved

 ### [CUDA Driver API](http://docs.nvidia.com/cuda/cuda-driver-api/index.html)
-cuMemRelease, cuMemExportToShareableHandle, cuMemSetAccess, cuMemMap, cuMemCreate, cuMemAddressFree, cuMemGetAllocationGranularity, cuMemUnmap, cuMemAddressReserve
+cuMemCreate, cuMemAddressReserve, cuMemGetAllocationGranularity, cuMemAddressFree, cuMemUnmap, cuMemMap, cuMemRelease, cuMemExportToShareableHandle, cuMemSetAccess

 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaOccupancyMaxActiveBlocksPerMultiprocessor, cudaImportExternalSemaphore, cudaStreamCreateWithFlags, cudaMemcpyAsync, cudaStreamDestroy, cudaSignalExternalSemaphoresAsync, cudaMallocHost, cudaMalloc, cudaSetDevice, cudaGetDeviceProperties, cudaGetDeviceCount, cudaDeviceGetAttribute, cudaSignalSemaphore, cudaWaitSemaphore, cudaDestroyExternalSemaphore, cudaStreamSynchronize, cudaFree, cudaLaunchHostFunc, cudaMemsetAsync, cudaFreeHost, cudaWaitExternalSemaphoresAsync
+cudaWaitExternalSemaphoresAsync, cudaImportExternalSemaphore, cudaDeviceGetAttribute, cudaSetDevice, cudaLaunchHostFunc, cudaMallocHost, cudaSignalExternalSemaphoresAsync, cudaFreeHost, cudaMemsetAsync, cudaMemcpyAsync, cudaGetDeviceCount, cudaStreamCreateWithFlags, cudaStreamDestroy, cudaDestroyExternalSemaphore, cudaSignalSemaphore, cudaWaitSemaphore, cudaFree, cudaStreamSynchronize, cudaMalloc, cudaOccupancyMaxActiveBlocksPerMultiprocessor, cudaGetDeviceProperties

 ## Dependencies needed to build/run
 [X11](../../../README.md#x11), [VULKAN](../../../README.md#vulkan)

 ## Prerequisites

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

 ## Build and Run
--- a/Samples/5_Domain_Specific/simpleVulkanMMAP/findvulkan.mk
+++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/findvulkan.mk
@@ -57,6 +57,7 @@ ifeq ("$(TARGET_OS)","linux")
    RHEL   = $(shell echo $(DISTRO) | grep -i 'red\|rhel' >/dev/null 2>&1; echo $$?)
    CENTOS = $(shell echo $(DISTRO) | grep -i centos      >/dev/null 2>&1; echo $$?)
    SUSE   = $(shell echo $(DISTRO) | grep -i 'suse\|sles' >/dev/null 2>&1; echo $$?)
+    KYLIN  = $(shell echo $(DISTRO) | grep -i kylin        >/dev/null 2>&1; echo $$?)
    ifeq ("$(UBUNTU)","0")
      ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-armv7l)
        GLPATH := /usr/arm-linux-gnueabihf/lib
@@ -103,6 +104,11 @@ ifeq ("$(TARGET_OS)","linux")
      GLLINK    ?= -L/usr/lib64/nvidia
      DFLT_PATH ?= /usr/lib64
    endif
+    ifeq ("$(KYLIN)","0")
+      GLPATH    ?= /usr/lib64/nvidia
+      GLLINK    ?= -L/usr/lib64/nvidia
+      DFLT_PATH ?= /usr/lib64
+    endif

  VULKAN_SDK_PATH ?= ${VULKAN_SDK}

--- a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2017.vcxproj
+++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2017.vcxproj
@@ -38,7 +38,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
  </ImportGroup>
  <ImportGroup Label="PropertySheets">
    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
      <OutputFile>$(OutDir)/simpleVulkanMMAP.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -123,6 +123,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2019.vcxproj
+++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2019.vcxproj
@@ -34,7 +34,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
  </ImportGroup>
  <ImportGroup Label="PropertySheets">
    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
      <OutputFile>$(OutDir)/simpleVulkanMMAP.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -119,6 +119,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2022.vcxproj
+++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2022.vcxproj
@@ -34,7 +34,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
  </ImportGroup>
  <ImportGroup Label="PropertySheets">
    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
      <OutputFile>$(OutDir)/simpleVulkanMMAP.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -119,6 +119,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>