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

Question

I\'m using CMake as a build system for my code, which involves CUDA. I was thinking of automating the task of deciding which compute_XX and arch_XX

Answer 1

A slight improvement over @orthopteroid's answer, which pretty much ensures a unique temporary file is generated, and only requires one instead of two temporary files.

The following goes into 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 
#include 

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

and the following goes into CMakeLists.txt or a CMake module:

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} )