add support for quantized ops on windows #14955
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
|
Can one of the admins verify this patch? |
mrry
approved these changes
Nov 29, 2017
|
@tensorflow-jenkins test this please. |
|
yeah, this was in the making for some time. thanks for helping with the gemmlowp. |
|
Yes, I think those failures are unrelated. Thanks again! @tensorflow-jenkins test this please. |
sb2nov
added
kokoro:force-run
|
Jenkins, test this please. |
|
@tensorflow-jenkins test this please |
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Outdated suggestions cannot be applied.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.
Quantized ops support on windows. Added some simple python unit test to make sure it works.
Gotcha: I need to use the latest version of gemmlowp in gemmlowp.cmake which is not on mirror.bazel.build so I use github.com directly for now.
This should provide the same functionality as tf on linux. Performance could be better because msvc can't make use of the inline asm in gemmlowp (compiling gemmlowp with clang would show much better results).