add rvv fp16 kernels for f16-gemm, f16-igemm, f16-dwconv, f16-spmm#9594
Merged
copybara-service[bot] merged 1 commit intogoogle:masterfrom Mar 2, 2026
Merged
Conversation
ken-unger
commented
Feb 25, 2026
dsharlet
approved these changes
Feb 26, 2026
Collaborator
dsharlet
left a comment
dsharlet
left a comment
There was a problem hiding this comment.
This looks good, but see my comment on the previous fp16 PR: #9516 (comment)
I think we need hardware-config support for detecting fp16 support.
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add RVV FP16 kernels for f16-gemm, f16-igemm, f16-dwconv, f16-spmm
Fixed definition of XNN_HAVE_FLOAT16 for RVV in src/xnnpack/math.h
Note that since there is no scalar fallback for FP16 kernels, not all the operator and subgraph tests will execute for RVV FP16 until the remaining kernels are implemented/integrated. I'll continue with qd8-f16 and other RVV kernels in subsequent PRs.