14 lines
220 B
Plaintext
14 lines
220 B
Plaintext
#include <stdio.h>
|
|
#include <cuda.h>
|
|
|
|
extern "C" {
|
|
__global__ void add(float *x, float *y)
|
|
{
|
|
int index = threadIdx.x;
|
|
int stride = blockDim.x;
|
|
|
|
for (int i = index; i < 100; i += stride)
|
|
y[i] = x[i] + y[i];
|
|
}
|
|
}
|