Enable async_io for squad. #617
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
bas-aarts
reviewed
Jul 23, 2020
| @@ -940,6 +940,9 @@ def main(_): | |||
| else: | |||
| os.environ["TF_XLA_FLAGS"] = "--tf_xla_enable_lazy_compilation=false" | |||
|
|
|||
| # Enable async_io to speed up multi-gpu training with XLA and Horovod. | |||
| os.environ["TF_XLA_FLAGS"] += "--tf_xla_async_io_level=1" | |||
There was a problem hiding this comment.
You are right. I was misled by line 939. I wonder why it worked?
There was a problem hiding this comment.
Did some tests. So, the line 939 never worked...
I updated the PR. Thanks @bas-aarts for the catch.
bas-aarts
approved these changes
Jul 23, 2020
| @@ -940,6 +940,9 @@ def main(_): | |||
| else: | |||
| os.environ["TF_XLA_FLAGS"] = "--tf_xla_enable_lazy_compilation=false" | |||
|
|
|||
| # Enable async_io to speed up multi-gpu training with XLA and Horovod. | |||
| os.environ["TF_XLA_FLAGS"] += "--tf_xla_async_io_level=1" | |||
PeganovAnton
pushed a commit
to PeganovAnton/DeepLearningExamples
that referenced
this pull request
Sep 8, 2020
Enable async_io for squad.
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Outdated suggestions cannot be applied.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.
This reduces Horovod overhead when XLA is enabled.
~7-9% speedup is observed for BERT Squad fp32 and ~3-4% speedup for fp16.