The “invalid argument” error of cudaMemcpyAsync

Check following CUDA code:

#include <iostream>

#define cudaSafeCall(call)  \
        do {\
            cudaError_t err = call;\
            if (cudaSuccess != err) \
            {\
                std::cerr << "CUDA error in " << __FILE__ << "(" << __LINE__ << "): " \
                    << cudaGetErrorString(err) << std::endl;\
                exit(EXIT_FAILURE);\
            }\
        } while(0)

int main(void)
{
    char *a, *d_a;
    cudaStream_t st;
    cudaSafeCall(cudaStreamCreate(&st));
    cudaSafeCall(cudaMallocHost(&a, 10));
    cudaSafeCall(cudaMalloc(&d_a, 4));
    cudaSafeCall(cudaMemcpyAsync(a, d_a, 10, cudaMemcpyHostToDevice, st));
    return 0;
}

The d_a is allocated only 4 bytes, but we want to copy 10 bytes. In this case, cudaMemcpyAsync will complain invalid argument error:

$ nvcc test.cu
$ ./a.out
CUDA error in test.cu(21): invalid argument