Changes

A-Team

16 bytes added, 06:30, 1 April 2019

→‎Initial implementation

int i = blockIdx.x * blockDim.x + threadIdx.x;

int j = blockIdx.y * blockDim.y + threadIdx.y;

//matrix multiplication if (i < ni && j < nj) { float sum = 0.0f;

for (int k = 0; k < nk; k++)

sum += d_a[i * nk + k] * d_b[k * nj + j];

d_p[i * nj + j] = sum;

}

113

edits