Update/optimize Loongson kernels #885
Merged
+257
−56
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
… into loongsonbase64opti
…loongsonbase64opti
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Outdated suggestions cannot be applied.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.
Short title (summary):
Enable the runtime dispatching for Loongson kernels, disable by default the LASX kernel and optimize the base64 decoding
Description
It turns out that runtime dispatching for Loongson kernels never worked, so that LSX was the sole default. This was fine, but I have tweaked the code to make dispatching work.
I have also improve the performance of the base64 decoding in the two kernels by special casing the sole ignorable character case (our other kernels have this optimization). This makes the performance go from 4 GB/s to 4.75 GB/s in some cases so it is definitely worth having. (@WojciechMula first designed this optimization, I just ported it.)
I am also fixing a C++11 issue: our Loongson kernels required C++14 to be strict about it.
Type of change