Optimize the v_lut* functions for RISC-V Vector(RVV).#24582
Merged
asmorkalov merged 1 commit intoopencv:4.xfrom Nov 30, 2023
Merged
Optimize the v_lut* functions for RISC-V Vector(RVV).#24582asmorkalov merged 1 commit intoopencv:4.xfrom
asmorkalov merged 1 commit intoopencv:4.xfrom
Conversation
Contributor
|
@mshabunin Friendly reminder. |
mshabunin
approved these changes
Nov 29, 2023
Contributor
mshabunin
left a comment
There was a problem hiding this comment.
Looks good to me.
Perhaps this optimization (transform_32f) should be reimplemented in a different way or disabled for RISC-V in future. As I can see that vectorized part is disabled for ARM platforms for now.
Merged
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This patch is going to optimize the implementation of Universal Intrinsic functions
v_lut_pairsandv_lut_quadson the RVV backend: when generating index, vector instructions are used to replace loops and std::vector in the existing implementation.In the core module,
v_lut_quadsis used intransform_32fin matmul.simd.hpp. According to the experimental results on k230, this patch improves performance by nearly 10x (although it is still slow than the scalar version, may improve with longer VLEN)Full result are here: core.zip
Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
Patch to opencv_extra has the same branch name.