[cutlass] Sparse conv3d backward fusion #52361
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Change splitK slices select rules, faster on some shapes, need to be tuned
|
你的PR提交成功，感谢你对开源项目的贡献! |
|
❌ The PR is not created using PR's template. You can refer to this Demo. |
zkh2016
approved these changes
Apr 10, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR types
Performance optimization
PR changes
Others
Describe
1.在
sparse/gpu/conv_grad_kernel.cu中添加了计算d_kernel, d_x时的gather_gemm_scatter融合。2.在生成脚本中添加了sparse conv3d反向融合需要用到的kernel的生成代码。
3.在auto tune中添加反向融合接口。
4.cutlass提供的算子融合在反向时需要将gemm计算结果写入buffer中，一次性分配大小为
sizeof(float) * max_in_channels * max_out_channels * max_splitk_slices = 4 * 256 * 256 *256 bytes = 67MB的buffer。若训练过程中需要更大的buffer则更新。buffer将在训练结束后释放。相比develop版本，添加反向融合后，4卡a100上训练性能提高5%。