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/nbody/Makefile
+++ b/Samples/5_Domain_Specific/nbody/Makefile
@@ -299,9 +299,9 @@ 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/nbody/NsightEclipse.xml
+++ b/Samples/5_Domain_Specific/nbody/NsightEclipse.xml
@@ -6,24 +6,24 @@
    <flag>-ftz=true</flag>
  </cflags>
  <cuda_api_list>
-    <toolkit>cudaMemcpyToSymbol</toolkit>
-    <toolkit>cudaGraphicsMapResources</toolkit>
-    <toolkit>cudaEventRecord</toolkit>
-    <toolkit>cudaStreamQuery</toolkit>
-    <toolkit>cudaEventCreate</toolkit>
-    <toolkit>cudaGraphicsResourceGetMappedPointer</toolkit>
-    <toolkit>cudaGetDeviceCount</toolkit>
-    <toolkit>cudaEventElapsedTime</toolkit>
-    <toolkit>cudaDeviceSynchronize</toolkit>
-    <toolkit>cudaEventSynchronize</toolkit>
-    <toolkit>cudaGraphicsResourceSetMapFlags</toolkit>
-    <toolkit>cudaSetDeviceFlags</toolkit>
-    <toolkit>cudaEventDestroy</toolkit>
-    <toolkit>cudaDeviceCanAccessPeer</toolkit>
-    <toolkit>cudaSetDevice</toolkit>
    <toolkit>cudaGraphicsUnmapResources</toolkit>
+    <toolkit>cudaSetDeviceFlags</toolkit>
+    <toolkit>cudaGraphicsResourceSetMapFlags</toolkit>
+    <toolkit>cudaGraphicsResourceGetMappedPointer</toolkit>
+    <toolkit>cudaGraphicsMapResources</toolkit>
+    <toolkit>cudaSetDevice</toolkit>
+    <toolkit>cudaEventSynchronize</toolkit>
+    <toolkit>cudaGetDeviceCount</toolkit>
    <toolkit>cudaGetDeviceProperties</toolkit>
+    <toolkit>cudaDeviceSynchronize</toolkit>
+    <toolkit>cudaEventRecord</toolkit>
    <toolkit>cudaGetDevice</toolkit>
+    <toolkit>cudaMemcpyToSymbol</toolkit>
+    <toolkit>cudaStreamQuery</toolkit>
+    <toolkit>cudaEventDestroy</toolkit>
+    <toolkit>cudaEventElapsedTime</toolkit>
+    <toolkit>cudaDeviceCanAccessPeer</toolkit>
+    <toolkit>cudaEventCreate</toolkit>
  </cuda_api_list>
  <description><![CDATA[This sample demonstrates efficient all-pairs simulation of a gravitational n-body simulation in CUDA.  This sample accompanies the GPU Gems 3 chapter "Fast N-Body Simulation with CUDA".  With CUDA 5.5, performance on Tesla K20c has increased to over 1.8TFLOP/s single precision.  Double Performance has also improved on all Kepler and Fermi GPU architectures as well.  Starting in CUDA 4.0, the nBody sample has been updated to take advantage of new features to easily scale the n-body simulation across multiple GPUs in a single PC.  Adding "-numbodies=<bodies>" to the command line will allow users to set # of bodies for simulation.  Adding “-numdevices=<N>” to the command line option will cause the sample to use N devices (if available) for simulation.  In this mode, the position and velocity data for all bodies are read from system memory using “zero copy” rather than from device memory.  For a small number of devices (4 or fewer) and a large enough number of bodies, bandwidth is not a bottleneck so we can achieve strong scaling across these devices.]]></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>
  <supported_envs>
    <env>
      <arch>x86_64</arch>
--- a/Samples/5_Domain_Specific/nbody/README.md
+++ b/Samples/5_Domain_Specific/nbody/README.md
@@ -10,7 +10,7 @@ Graphics Interop, Data Parallel Algorithms, Physically-Based Simulation

 ## Supported SM Architectures

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

 ## Supported OSes

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

 ### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
-cudaMemcpyToSymbol, cudaGraphicsMapResources, cudaEventRecord, cudaStreamQuery, cudaEventCreate, cudaGraphicsResourceGetMappedPointer, cudaGetDeviceCount, cudaEventElapsedTime, cudaDeviceSynchronize, cudaEventSynchronize, cudaGraphicsResourceSetMapFlags, cudaSetDeviceFlags, cudaEventDestroy, cudaDeviceCanAccessPeer, cudaSetDevice, cudaGraphicsUnmapResources, cudaGetDeviceProperties, cudaGetDevice
+cudaGraphicsUnmapResources, cudaSetDeviceFlags, cudaGraphicsResourceSetMapFlags, cudaGraphicsResourceGetMappedPointer, cudaGraphicsMapResources, cudaSetDevice, cudaEventSynchronize, cudaGetDeviceCount, cudaGetDeviceProperties, cudaDeviceSynchronize, cudaEventRecord, cudaGetDevice, cudaMemcpyToSymbol, cudaStreamQuery, cudaEventDestroy, cudaEventElapsedTime, cudaDeviceCanAccessPeer, cudaEventCreate

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

 ## 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/nbody/findgllib.mk
+++ b/Samples/5_Domain_Specific/nbody/findgllib.mk
@@ -53,11 +53,12 @@ endif
 ifeq ("$(TARGET_OS)","linux")
    # $(info) >> findgllib.mk -> LINUX path <<<)
    # Each set of Linux Distros have different paths for where to find their OpenGL libraries reside
-    UBUNTU = $(shell echo $(DISTRO) | grep -i ubuntu      >/dev/null 2>&1; echo $$?)
-    FEDORA = $(shell echo $(DISTRO) | grep -i fedora      >/dev/null 2>&1; echo $$?)
-    RHEL   = $(shell echo $(DISTRO) | grep -i 'red\|rhel' >/dev/null 2>&1; echo $$?)
-    CENTOS = $(shell echo $(DISTRO) | grep -i centos      >/dev/null 2>&1; echo $$?)
+    UBUNTU = $(shell echo $(DISTRO) | grep -i ubuntu       >/dev/null 2>&1; echo $$?)
+    FEDORA = $(shell echo $(DISTRO) | grep -i fedora       >/dev/null 2>&1; echo $$?)
+    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)-$(TARGET_ARCH),x86_64-armv7l)
        GLPATH := /usr/arm-linux-gnueabihf/lib
@@ -87,27 +88,17 @@ ifeq ("$(TARGET_OS)","linux")
        DFLT_PATH ?= /usr/lib
      endif
    endif
+
    ifeq ("$(SUSE)","0")
      GLPATH    ?= /usr/X11R6/lib64
      GLLINK    ?= -L/usr/X11R6/lib64
      DFLT_PATH ?= /usr/lib64
-    endif
-    ifeq ("$(FEDORA)","0")
+    else 
      GLPATH    ?= /usr/lib64/nvidia
      GLLINK    ?= -L/usr/lib64/nvidia
      DFLT_PATH ?= /usr/lib64
    endif
-    ifeq ("$(RHEL)","0")
-      GLPATH    ?= /usr/lib64/nvidia
-      GLLINK    ?= -L/usr/lib64/nvidia
-      DFLT_PATH ?= /usr/lib64
-    endif
-    ifeq ("$(CENTOS)","0")
-      GLPATH    ?= /usr/lib64/nvidia
-      GLLINK    ?= -L/usr/lib64/nvidia
-      DFLT_PATH ?= /usr/lib64
-    endif
-  
+      
  # find libGL, libGLU 
  GLLIB  := $(shell find -L $(GLPATH) $(DFLT_PATH) -name libGL.so  -print 2>/dev/null)
  GLULIB := $(shell find -L $(GLPATH) $(DFLT_PATH) -name libGLU.so -print 2>/dev/null)
--- a/Samples/5_Domain_Specific/nbody/nbody_vs2017.vcxproj
+++ b/Samples/5_Domain_Specific/nbody/nbody_vs2017.vcxproj
@@ -38,7 +38,7 @@
  </PropertyGroup>
  <Import Project="$(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>$(OutDir)/nbody.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -125,6 +125,6 @@
  </ItemGroup>
  <Import Project="$(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/nbody/nbody_vs2019.vcxproj
+++ b/Samples/5_Domain_Specific/nbody/nbody_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)/nbody.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>
@@ -121,6 +121,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/5_Domain_Specific/nbody/nbody_vs2022.vcxproj
+++ b/Samples/5_Domain_Specific/nbody/nbody_vs2022.vcxproj
@@ -34,7 +34,7 @@
  </PropertyGroup>
  <Import Project="$(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>$(OutDir)/nbody.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
      <Include>./;../../../Common</Include>
      <Defines>WIN32</Defines>
@@ -121,6 +121,6 @@
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
  </ImportGroup>
 </Project>