[FP16] Removed "relaxed" from madd and nmadd.#8411
Open
brendandahl wants to merge 2 commits intoWebAssembly:mainfrom
Open
[FP16] Removed "relaxed" from madd and nmadd.#8411brendandahl wants to merge 2 commits intoWebAssembly:mainfrom
brendandahl wants to merge 2 commits intoWebAssembly:mainfrom
Conversation
With FP16 there won't be any relaxed instructions because the hardware should always be able to promote the type to F32 so there won't be a double rounding issue.
brendandahl
force-pushed
the
remove-relaxed-fp16
branch
from
eb46f4a to
42264c2
Compare
brendandahl
commented
Mar 4, 2026
| switch (curr->op) { | ||
| case RelaxedMaddVecF16x8: | ||
| case RelaxedNmaddVecF16x8: | ||
| case MaddVecF16x8: |
Collaborator
Author
There was a problem hiding this comment.
One thing we haven't resolved, is whether fp16 implies simd is enabled.
Member
There was a problem hiding this comment.
Since it requires the v128 type, I think it's reasonable to require simd.
tlively
reviewed
Mar 4, 2026
Comment on lines
+552
to
+553
| ("f16x8.madd", "makeSIMDTernary(SIMDTernaryOp::MaddVecF16x8)"), | ||
| ("f16x8.nmadd", "makeSIMDTernary(SIMDTernaryOp::NmaddVecF16x8)"), |
Member
There was a problem hiding this comment.
Please align the right hand side to match the above lines.
| switch (curr->op) { | ||
| case RelaxedMaddVecF16x8: | ||
| case RelaxedNmaddVecF16x8: | ||
| case MaddVecF16x8: |
Member
There was a problem hiding this comment.
Since it requires the v128 type, I think it's reasonable to require simd.
Comment on lines
+77
to
+78
| case MaddVecF16x8: | ||
| case NmaddVecF16x8: |
Member
There was a problem hiding this comment.
These the pass should probably leave these in place since they are not relaxed SIMD. We can update the test accordingly, too.
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.
With FP16 there won't be any relaxed instructions because the hardware should always be able to promote the type to F32 so there won't be a double rounding issue.