Shell script for determining the SM value for your (single) GPU. Based on https://gist.github.com/eyalroz/71ce52fa80acdd1c3b192e43a6c1d930

get_cuda_arch.sh

#!/bin/bash
#
# Prints the compute capability of all the CUDA device installed
# on the system.

timestamp=$(date +%s.%N)
gcc_binary=${CMAKE_CXX_COMPILER:-$(which c++)}
cuda_root=${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;
        }
        printf("Device, compute capability, PCI bus ID\n");
        for (int i=0; i < device_count; i++) {
                status = cudaGetDeviceProperties(&prop, i);
                if (status != cudaSuccess) {
                        fprintf(stderr,"cudaGetDeviceProperties() for device %d failed: %s\n", i, cudaGetErrorString(status));
                        return -1;
                }
                int v = prop.major * 10 + prop.minor;
                printf("%s, %d, %X\n", prop.name, v, prop.pciBusID);
        }
}
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