Enable vectorisation for ZIP reconstruct stage on Windows #2043
+15
−15
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
The __SSE4_1__ macro that is used to control the use of the vectorised version of the reconstruct() function, is only defined for GCC and clang. As a result, Windows were using the scalar version, which is less performant. This commit fixes the above issue by adding a check for MSVC, similar to what we have on the SSE2 macro check (and in other places in the code base). Signed-off-by: Nikolaos Koutsikos <[email protected]>
Signed-off-by: Nikolaos Koutsikos <[email protected]>
|
Did you experiment with any use of the restrict pointer qualifier (in it's forms, I believe I added a macro for that)? I have seen some evidence that that can help the optimisation as well to remove pointer aliasing, but it's an added complexity if the compiler can already notice that... |
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Outdated suggestions cannot be applied.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.
The SSE4_1 macro that is used to control the use of the vectorised version of the reconstruct() function, is only defined for GCC and clang. As a result, Windows were using the scalar version, which is less performant.
The above issue is now fixed by adding a check for MSVC, similar to what we have on the SSE2 macro check (and in other places in the code base).
At the same time, some basic const correctness is applied to the same file, which could help the compiler apply more optimisations.