[FOR DRAFT-PR ONLY] Enable -ffp-mode=fast for armclang #2755
+10
−11
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
-ffp-mode=fast enables extra compiler optimizations for floating point operators which increases performance, previously set to -ffp-mode=std as it is uncompatible with std::numeric_limits::quiet_NaN/infinity. See https://developer.arm.com/documentation/dui0774/latest/Compiler-Command-line-Options/-ffp-mode for more info. This pull-request puts all incompatible code inside the TFLITE_EMULATE_FLOAT flag, which is not defined on arm targets. Change-Id: Ic8fab0f11497ef4fd834a3a731a8a5625913486e
|
"This PR is being marked as stale due to inactivity. Remove label or comment to prevent closure in 5 days." |
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Outdated suggestions cannot be applied.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.
-ffp-mode=fast enables extra compiler optimizations for floating point operators which increases performance, previously set to -ffp-mode=std as it is uncompatible with std::numeric_limits::quiet_NaN/infinity. See https://developer.arm.com/documentation/dui0774/latest/Compiler-Command-line-Options/-ffp-mode for more info.
This pull-request puts all incompatible code inside the TFLITE_EMULATE_FLOAT flag, which is not defined on arm targets.
It would probably need to be upstreamed to the tensorflow repo, so this is a proof of concept only.
Relevant github issue: #2518