[Reland][Gradient Compression] Apply division first to avoid overflow #59576
Conversation
This file contains hidden or 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
If the gradients before allreduce are large, then the sum after allreduce may overflow, especially for FP16. Therefore, apply the division before allreduce. This fix is applied to both C++ and Python comm hooks. Differential Revision: [D28941327](https://our.internmc.facebook.com/intern/diff/D28941327/) [ghstack-poisoned]
wayi1
requested review from
H-Huang,
cbalioglu,
mingzhe09088,
mrshenli,
pritamdamania87,
rohan-varma and
zhaojuanmao
as code owners
💊 CI failures summary and remediationsAs of commit b22840c (more details on the Dr. CI page):
3 failures not recognized by patterns:
This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.Please report bugs/suggestions to the (internal) Dr. CI Users group. |
facebook-github-bot
added
oncall: distributed
wayi1
pushed a commit
that referenced
this pull request
Jun 7, 2021
If the gradients before allreduce are large, then the sum after allreduce may overflow, especially for FP16. Therefore, apply the division before allreduce. This fix is applied to both C++ and Python comm hooks. Differential Revision: [D28941327](https://our.internmc.facebook.com/intern/diff/D28941327/) ghstack-source-id: 130754510 Pull Request resolved: #59576
rohan-varma
approved these changes
Jun 7, 2021
This was referenced Jun 7, 2021
|
This pull request has been merged in 2b398d0. |
deniskokarev
pushed a commit
to deniskokarev/pytorch
that referenced
this pull request
Jun 9, 2021
…pytorch#59576) Summary: Pull Request resolved: pytorch#59576 If the gradients before allreduce are large, then the sum after allreduce may overflow, especially for FP16. Therefore, apply the division before allreduce. This fix is applied to both C++ and Python comm hooks. ghstack-source-id: 130754510 Test Plan: buck test mode/dev-nosan caffe2/test/distributed:c10d -- test_ddp_comm_hook_allreduce_hook_nccl buck test mode/dev-nosan caffe2/test/distributed:c10d -- test_default_ddp_comm_hooks_nccl buck test mode/dev-nosan caffe2/test/distributed:c10d -- test_fp16_compress_wrapper_nccl buck test mode/dev-nosan caffe2/test/distributed:c10d -- test_builtin_ddp_comm_hooks_nccl buck test mode/dev-nosan caffe2/test/distributed:c10d -- test_powerSGD_ddp_comm_hook_nccl buck test mode/dev-nosan caffe2/test/distributed:c10d -- test_ddp_comm_hook_allreduce_hook_nccl_grad_is_view buck test mode/dev-nosan caffe2/test/distributed:c10d -- test_default_ddp_comm_hooks_nccl_is_view buck test mode/dev-nosan caffe2/test/distributed:c10d -- test_fp16_compress_wrapper_is_view buck test mode/dev-nosan caffe2/test/distributed:c10d -- test_builtin_ddp_comm_hooks_nccl_grad_is_view buck test mode/dev-nosan caffe2/test/distributed:c10d -- test_powerSGD_ddp_comm_hook_nccl_grad_is_view Reviewed By: rohan-varma Differential Revision: D28941327 fbshipit-source-id: 932e8ddbdb2bfd609a78943f6dc390d3d6ca333f
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Stack from ghstack:
If the gradients before allreduce are large, then the sum after allreduce may overflow, especially for FP16. Therefore, apply the division before allreduce.
This fix is applied to both C++ and Python comm hooks.
Differential Revision: D28941327