CUDA How to access constant memory in device kernel when the constant memory is declared in the host code?

Question

For the record this is homework so help as little or as much with that in mind. We are using constant memory to store a \"mask matrix\" that will be used to perform a convol

Answer 1

Below is a "minimum-sized" example showing the use of __constant__ symbols. You do not need to pass any pointer to the __global__ function.

#include 
#include 
#include 

__constant__ float test_const;

__global__ void test_kernel(float* d_test_array) {
    d_test_array[threadIdx.x] = test_const;
}

#include 
int main(int argc, char **argv) {

    float test = 3.f;

    int N = 16;

    float* test_array = (float*)malloc(N*sizeof(float)); 

    float* d_test_array;
    cudaMalloc((void**)&d_test_array,N*sizeof(float));

    cudaMemcpyToSymbol(test_const, &test, sizeof(float));
    test_kernel<<<1,N>>>(d_test_array);

    cudaMemcpy(test_array,d_test_array,N*sizeof(float),cudaMemcpyDeviceToHost);

    for (int i=0; i