File: cuda_dlink_extension_kernel.cu

package info (click to toggle)
pytorch-cuda 2.6.0%2Bdfsg-7
  • links: PTS, VCS
  • area: contrib
  • in suites: forky, sid, trixie
  • size: 161,620 kB
  • sloc: python: 1,278,832; cpp: 900,322; ansic: 82,710; asm: 7,754; java: 3,363; sh: 2,811; javascript: 2,443; makefile: 597; ruby: 195; xml: 84; objc: 68
file content (22 lines) | stat: -rw-r--r-- 608 bytes parent folder | download | duplicates (4)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
#include <cuda.h>
#include <cuda_runtime.h>
#include <c10/cuda/CUDAException.h>

#include <ATen/ATen.h>

#include "cuda_dlink_extension_add.cuh"

__global__ void add_kernel(const float* a, const float* b, float* output, int size) {
  int i = blockIdx.x * blockDim.x + threadIdx.x;
  if (i < size) {
    add(a + i, b + i, output + i);
  }
}

// output = a * b + c
void add_cuda(const float* a, const float* b, float* output, int size) {
  const int threads = 1024;
  const int blocks = (size + threads - 1) / threads;
  add_kernel<<<blocks, threads>>>(a, b, output, size);
  C10_CUDA_KERNEL_LAUNCH_CHECK();
}