[LLVM][XTHeadVector] support nvx1i1/nvx2i1/nvx4i1 operands for vector mask operations
#120
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
imkiva
changed the title
vbool16/32/64_t for vector mask operations
imkiva
changed the title
vbool16/32/64_t for vector mask operationsnvx1i1/nvx2i1/nvx4i1 operands for vector mask operations
imkiva
changed the title
nvx1i1/nvx2i1/nvx4i1 operands for vector mask operationsnvx1i1/nvx2i1/nvx4i1 operands for vector mask operations
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Outdated suggestions cannot be applied.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.
This PR fixed an issue introduced in #95 where the element size of
vbool16/32/64_tis computed from fractional LMUL, making it incompatible with XTHeadVector.This PR applies another strategy of setting LMUL and SEW when computing
<n> = SEW/LMULinvbool<n>_t:<n> = 1, 2, 4, 8, we assumeSEW = 8, and setLMUL = 8/4/2/1respectively. This is the same as the old behavior and mainline RVV implementation.<n> = 16, 32, 64, we assumeLMUL = 1, and setSEW = 16/32/64respectively. Thus no fractional LMUL is involved, and the generated code can pass MC validation.