Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Fix permute_multi_embedding kernel (#3227)
Summary: Pull Request resolved: #3227 X-link: facebookresearch/FBGEMM#325 Looks like a typo to use `permute_id = threadIdx.y + blockIdx.x * blockDim.x` which should be `blockDim.y`. This doesn't affect Nvidia because blockDim.x and y are both 32 (32 threads per warp + 32 warps). For AMD GPU, blockDim.x is 64 and blockDim.y is 16, causing numerical issues. Reviewed By: leitian, jianyuh, joebos Differential Revision: D63936776 fbshipit-source-id: cfdf0ff24e41a8ffd137ce066f2b82f3c47399b5
- Loading branch information