File: cuda_helpers.h

package info (click to toggle)
pytorch-vision 0.14.1-2
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 15,188 kB
  • sloc: python: 49,008; cpp: 10,019; sh: 610; java: 550; xml: 79; objc: 56; makefile: 32
file content (18 lines) | stat: -rw-r--r-- 475 bytes parent folder | download | duplicates (2) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
 
#pragma once

namespace vision {
namespace ops {

#define CUDA_1D_KERNEL_LOOP_T(i, n, index_t)                         \
  for (index_t i = (blockIdx.x * blockDim.x) + threadIdx.x; i < (n); \
       i += (blockDim.x * gridDim.x))

#define CUDA_1D_KERNEL_LOOP(i, n) CUDA_1D_KERNEL_LOOP_T(i, n, int)

template <typename integer>
constexpr __host__ __device__ inline integer ceil_div(integer n, integer m) {
  return (n + m - 1) / m;
}

} // namespace ops
} // namespace vision