PR#431 porting from vvenc. #208
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
Refactor AArch64 Interpolation Filter 16x16 implementation (#431)
* Move InterpolationFilter{ARM.h => _neon.cpp}
Since this header is only used in one place and would not share any code
with an eventual SVE implementation, simply move it to a .cpp file
similar to MCTF.cpp.
* Refactor simdFilter16xX_N8_neon
The use of the vsrcv temporary array rather than simple local variables
meant that LLVM emitted an unnecessary number of load/store instructions
in the inner loops. Refactoring this to make the dependency between loop
iterations more explicit allows for much nicer generated code.
Running a video encoding job on a Neoverse V2 machine using the
--preset=fast setting shows a ~1.8% improvement in reported FPS.
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Outdated suggestions cannot be applied.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.
Additions to original:
adjusted to the circumstances in vvdec: Stride datatypes + namespace
original commit message in vvenc:
Refactor AArch64 Interpolation Filter 16x16 implementation (#431)
Since this header is only used in one place and would not share any code with an eventual SVE implementation, simply move it to a .cpp file similar to MCTF.cpp.
The use of the vsrcv temporary array rather than simple local variables meant that LLVM emitted an unnecessary number of load/store instructions in the inner loops. Refactoring this to make the dependency between loop iterations more explicit allows for much nicer generated code.
Running a video encoding job on a Neoverse V2 machine using the --preset=fast setting shows a ~1.8% improvement in reported FPS.