确定 nvcc 需要哪些 gencode (compute_, arch_) 值 - 在 CMake 中

Question

我使用 CMake 作为我的代码的构建系统，其中涉及 CUDA。我正在考虑自动化决定我需要将哪个 compute_XX 和 arch_XX 传递给我的 nvcc 以便为我当前机器上的 GPU 编译的任务。

有没有办法做到这一点：
1. 使用 NVIDIA GPU 部署套件？
2. 没有 NVIDIA GPU 部署套件？
CMake 的 FindCUDA 可以帮助您确定这些开关的值吗？

Answer 1

我的策略是编译和运行一个探测卡的bash脚本和returnscmake的gencode。灵感来自University of Chicago's SLURM。处理错误或多个GPU或其他情况，根据需要修改。

在您的项目文件夹中创建一个文件 cudaComputeVersion.bash 并确保它可以从 shell 中执行。在此文件中放入：

#!/bin/bash

# create a 'here document' that is code we compile and use to probe the card
cat << EOF > /tmp/cudaComputeVersion.cu
#include <stdio.h>
int main()
{
cudaDeviceProp prop;
cudaGetDeviceProperties(&prop,0);
int v = prop.major * 10 + prop.minor;
printf("-gencode arch=compute_%d,code=sm_%d\n",v,v);
}
EOF

# probe the card and cleanup
/usr/local/cuda/bin/nvcc /tmp/cudaComputeVersion.cu -o /tmp/cudaComputeVersion
/tmp/cudaComputeVersion
rm /tmp/cudaComputeVersion.cu
rm /tmp/cudaComputeVersion

并在你的 CMakeLists.txt 中输入：

# at cmake-build-time, probe the card and set a cmake variable
execute_process(COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/cudaComputeVersion.bash OUTPUT_VARIABLE GENCODE)
# at project-compile-time, include the gencode into the compile options
set(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS}; "${GENCODE}")

# this makes CMake all chatty and allows you to see that GENCODE was set correctly
set(CMAKE_VERBOSE_MAKEFILE TRUE)

干杯

Answer 2

对@orthopteroid 的答案略有改进，这几乎确保生成一个唯一的临时文件，并且只需要一个而不是两个临时文件。

以下进入scripts/get_cuda_sm.sh：

#!/bin/bash 
#
# Prints the compute capability of the first CUDA device installed
# on the system, or alternatively the device whose index is the
# first command-line argument

device_index=${1:-0}
timestamp=$(date +%s.%N)
gcc_binary=$(which g++)
gcc_binary=${gcc_binary:-g++}
cuda_root=${CUDA_DIR:-/usr/local/cuda}
CUDA_INCLUDE_DIRS=${CUDA_INCLUDE_DIRS:-${cuda_root}/include}
CUDA_CUDART_LIBRARY=${CUDA_CUDART_LIBRARY:-${cuda_root}/lib64/libcudart.so}
generated_binary="/tmp/cuda-compute-version-helper-$$-$timestamp"
# create a 'here document' that is code we compile and use to probe the card
source_code="$(cat << EOF 
#include <stdio.h>
#include <cuda_runtime_api.h>

int main()
{
        cudaDeviceProp prop;
        cudaError_t status;
        int device_count;
        status = cudaGetDeviceCount(&device_count);
        if (status != cudaSuccess) { 
                fprintf(stderr,"cudaGetDeviceCount() failed: %s\n", cudaGetErrorString(status)); 
                return -1;
        }
        if (${device_index} >= device_count) {
                fprintf(stderr, "Specified device index %d exceeds the maximum (the device count on this system is %d)\n", ${device_index}, device_count);
                return -1;
        }
        status = cudaGetDeviceProperties(&prop, ${device_index});
        if (status != cudaSuccess) { 
                fprintf(stderr,"cudaGetDeviceProperties() for device ${device_index} failed: %s\n", cudaGetErrorString(status)); 
                return -1;
        }
        int v = prop.major * 10 + prop.minor;
        printf("%d\n", v);
}
EOF
)"
echo "$source_code" | $gcc_binary -x c++ -I"$CUDA_INCLUDE_DIRS" -o "$generated_binary" - -x none "$CUDA_CUDART_LIBRARY"

# probe the card and cleanup

$generated_binary
rm $generated_binary

下面进入 CMakeLists.txt 或 CMake 模块：

if (NOT CUDA_TARGET_COMPUTE_CAPABILITY)
    if("$ENV{CUDA_SM}" STREQUAL "")
        set(ENV{CUDA_INCLUDE_DIRS} "${CUDA_INCLUDE_DIRS}")
        set(ENV{CUDA_CUDART_LIBRARY} "${CUDA_CUDART_LIBRARY}")
        set(ENV{CMAKE_CXX_COMPILER} "${CMAKE_CXX_COMPILER}")
        execute_process(COMMAND 
            bash -c "${CMAKE_CURRENT_SOURCE_DIR}/scripts/get_cuda_sm.sh" 
            OUTPUT_VARIABLE CUDA_TARGET_COMPUTE_CAPABILITY_)
    else()
        set(CUDA_TARGET_COMPUTE_CAPABILITY_ $ENV{CUDA_SM})
    endif()

    set(CUDA_TARGET_COMPUTE_CAPABILITY "${CUDA_TARGET_COMPUTE_CAPABILITY_}" 
        CACHE STRING "CUDA compute capability of the (first) CUDA device on \
        the system, in XY format (like the X.Y format but no dot); see table \
        of features and capabilities by capability X.Y value at \
        https://en.wikipedia.org/wiki/CUDA#Version_features_and_specifications")

    execute_process(COMMAND 
        bash -c "echo -n $(echo ${CUDA_TARGET_COMPUTE_CAPABILITY})" 
        OUTPUT_VARIABLE CUDA_TARGET_COMPUTE_CAPABILITY)
    execute_process(COMMAND 
        bash -c "echo ${CUDA_TARGET_COMPUTE_CAPABILITY} | sed 's/^\([0-9]\)\([0-9]\)/\1.\2/;' | xargs echo -n" 
        OUTPUT_VARIABLE FORMATTED_COMPUTE_CAPABILITY)

    message(STATUS 
        "CUDA device-side code will assume compute capability \
        ${FORMATTED_COMPUTE_CAPABILITY}")
endif()

set(CUDA_GENCODE
    "arch=compute_${CUDA_TARGET_COMPUTE_CAPABILITY}, code=compute_${CUDA_TARGET_COMPUTE_CAPABILITY}")
set(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS} -gencode ${CUDA_GENCODE} )

Answer 3

在使用 CMake 3.7 或更新版本时，您可以使用 cuda_select_nvcc_arch_flags() macro in the FindCUDA 模块，而无需任何其他脚本。

include(FindCUDA)
set(CUDA_ARCH_LIST Auto CACHE STRING
    "List of CUDA architectures (e.g. Pascal, Volta, etc) or \
compute capability versions (6.1, 7.0, etc) to generate code for. \
Set to Auto for automatic detection (default)."
)
cuda_select_nvcc_arch_flags(CUDA_ARCH_FLAGS ${CUDA_ARCH_LIST})
list(APPEND CUDA_NVCC_FLAGS ${CUDA_ARCH_FLAGS})

例如，上面在我的机器上将 CUDA_ARCH_FLAGS 设置为 -gencode arch=compute_61,code=sm_61。 CUDA_ARCH_LIST 缓存变量可以由用户配置为特定计算能力生成代码而不是自动检测。

注意：自 CMake 3.10 以来，FindCUDA 模块已被弃用。但是，在最新的 CMake 版本 (v3.14) 中似乎还没有提供 cuda_select_nvcc_arch_flags() 宏的等效替代方案。有关详细信息，请参阅 CMake 问题跟踪器中的 relevant issue。

确定 nvcc 需要哪些 gencode (compute_, arch_) 值 - 在 CMake 中

Determining which gencode (compute_, arch_) values I need for nvcc - within CMake

cuda

cmake

build-automation

detection