// Device arrays
float *d_a, *d_b, *d_c;
// Allocate memory on the device (GPU)
cudaMalloc((void**)&d_a, N * sizeof(float));
cudaMalloc((void**)&d_b, N * sizeof(float));
cudaMalloc((void**)&d_c, N * sizeof(float));
// Copy host arrays to device (Offloading data on GPU)
cudaMemcpy(d_a, h_a, N * sizeof(float), cudaMemcpyHostToDevice);
cudaMemcpy(d_b, h_b, N * sizeof(float), cudaMemcpyHostToDevice);
Running in FUNCTIONAL mode...
Compiling...
Executing...
Elapsed time for GPU computation: 7.97878 ms
Exit status: 0
కామెంట్లు లేవు:
కామెంట్ను పోస్ట్ చేయండి