diff options
| author | Luke Lau <luke@igalia.com> | 2025-06-13 18:25:07 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-06-13 18:25:07 +0100 |
| commit | b81d5e06c7cba8c9f1f5380daed4b9ee139214ba (patch) | |
| tree | 7483bb703fa4bad58f50bdc253e0f13afce19b1f /flang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 1072196c2737fcf921ad52e9a44c13423789111b (diff) | |
| download | llvm-b81d5e06c7cba8c9f1f5380daed4b9ee139214ba.zip llvm-b81d5e06c7cba8c9f1f5380daed4b9ee139214ba.tar.gz llvm-b81d5e06c7cba8c9f1f5380daed4b9ee139214ba.tar.bz2 | |
[InstCombine] Fold shuffles through all trivially vectorizable intrinsics (#141979)
This addresses a TODO in foldShuffledIntrinsicOperands to use
isTriviallyVectorizable instead of a hardcoded list of intrinsics, which
in turn allows more intriniscs to be scalarized by VectorCombine.
From what I can tell every intrinsic here should be speculatable so an
assertion was added.
Because this enables intrinsics like abs which have a scalar operand, we
need to also check isVectorIntrinsicWithScalarOpAtArg.
Diffstat (limited to 'flang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions