93
edits
Changes
→Assignment 2
int ymin, int ymax, float dx, float dy, float dxxinv, float dyyinv) {//MODIFY to suit algorithm
int j = blockIdx.x * blockDim.x + threadIdx.x + 1;
//above: we are using block and thread indexes to replace some of the iteration logic
if (j < n - 1) {
cudaMemcpy(d_b, b, n* m * sizeof(float), cudaMemcpyHostToDevice);
dim3 dGrid(m1);
dim3 dBlock(m);
