Merged
Conversation
pranavsharma
approved these changes
May 8, 2020
stevenlix
pushed a commit
that referenced
this pull request
May 12, 2020
* avoid unneeded buffer zeroing; includes cleanup * fix includes
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description: Changes to LSTM operator to improve an internal first party model. Also cleanup the code after other recent changes.
Motivation and Context
For larger LSTMs, the zero fills of some intermediate buffers was a noticeable chunk of time. The buffer zeroing is not needed in the cases as the buffer is always overwritten by InitializeBuffers() or the first ComputeGemm in the operator. For an internal first party model, this saved 4ms of single-threaded time (reducing the model from 124ms/inference to 120ms).
Also cleanup the #include files used in this module to simplify the code.