Could a CUDA kernel call a cublas function?

Question

I know it sound weird, but here is my scenario:

I need to do a matrix-matrix multiplication (A(n*k)*B(k*n)), but I only needs the diagonal elements to be evaluated f

Answer 1

Here has a code example for your problem, I think this code link could help you. Thanks the Github's author.

__global__ void invokeDeviceCublasSgemm(cublasStatus_t *returnValue,
                                    int n,
                                    const float *d_alpha,
                                    const float *d_A,
                                    const float *d_B,
                                    const float *d_beta,
                                    float *d_C)
{   
    cublasHandle_t cnpHandle;
    cublasStatus_t status = cublasCreate(&cnpHandle);

    if (status != CUBLAS_STATUS_SUCCESS){
        *returnValue = status;
        return;
    }

    /* Perform operation using cublas */
    status = cublasSgemm(cnpHandle,
                CUBLAS_OP_N, CUBLAS_OP_N,
                n, n, n,
                d_alpha,
                d_A, n,
                d_B, n,
                d_beta,
                d_C, n);
    cublasDestroy(cnpHandle);
    *returnValue = status;
}