MV-532: [MV-MIOpen] Benchmark & Port AvgPool #48
Conversation
| const int32_t KD, | ||
| const int32_t KH, | ||
| const int32_t KW, | ||
| const int32_t SD, | ||
| const int32_t SH, | ||
| const int32_t SW, | ||
| const int32_t PD, | ||
| const int32_t PH, | ||
| const int32_t PW, |
There was a problem hiding this comment.
Missing documentation for those params. And may I ask why don't you include ceil_mode as a param?
| const int32_t KD, | ||
| const int32_t KH, | ||
| const int32_t KW, | ||
| const int32_t SD, | ||
| const int32_t SH, | ||
| const int32_t SW, | ||
| const int32_t PD, | ||
| const int32_t PH, | ||
| const int32_t PW, |
| int32_t gid = threadIdx.x + blockIdx.x * blockDim.x; | ||
| int32_t ncoh = gid / OW, ow = gid % OW; | ||
| int32_t nc = ncoh / OH, oh = ncoh % OH; | ||
| int32_t n = nc / C, c = nc % C; |
There was a problem hiding this comment.
It limits the kernel applicability for tensors <2Gb as discussed in another PR ROCm#3167 (comment) . I suggest to avoid using int32_t for variables
There was a problem hiding this comment.
Recommend to modify like this PR https://github.com/ROCm/MIOpen/pull/3152/files#diff-0a8b79941cc58d4496df527ac51df1ca8e3f4729f4223d1f4714b81c880d24a1 . Then instead of calling input[input_tv.get_tensor_view_idx(tensor_layout_t<4>(n, c, h, w))]); in MIOpenAvgPool.cpp you use input[input_tv.get_tensor_view_idx({n, c, h, w})]);
There was a problem hiding this comment.
May I ask you to provide test for uncont tensor?
Added AvgPool 2D 3D forward and backward with new solvers and bfp16 supported.
Added driver test and gtest for AvgPool.
New API is guarded by MIOPEN_BETA_API macro.
Compared to ROCm pytorch: Link
Average over all cases:
AvgPool 2D