Adam operator optimized with Eigen #10229
Merged
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
added 7 commits
April 24, 2018 11:11
|
@luotao1 Could you have a look at this PR? |
|
@dzhwinter How about the same Eigen optimization on GPU execution? |
luotao1
reviewed
Apr 27, 2018
| param_out_(param_out) {} | ||
|
|
||
| void operator()(size_t numel) const { | ||
| Eigen::Map<const Eigen::Array<T, 1, Eigen::Dynamic>> g{ |
There was a problem hiding this comment.
@tpatejko You can use framework::EigenTensor<T, 1> to replace Eigen::Map<const Eigen::Array<T, 1, Eigen::Dynamic>> in next PR.
We have a eigen wrap in https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/fluid/framework/eigen.h.
There was a problem hiding this comment.
@luotao1 Thanks for the remark. I will use it next time.
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Outdated suggestions cannot be applied.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 PR implements Adam operator optimized with Eigen. This is important for CPU execution.
Two benchmarks were taken into account: mnist and machine_translation. The results of profiling on default parameters, on Skylake CPU:
machine translation
mnist: