[all-commits] [llvm/llvm-project] 64eea3: [X86] combineEXTEND_VECTOR_INREG - don't attempt t...
Simon Pilgrim via All-commits
all-commits at lists.llvm.org
Mon Jun 13 09:42:21 PDT 2022
Branch: refs/heads/main
Home: https://github.com/llvm/llvm-project
Commit: 64eea34420e3ee1f6f91a57a72b2edf6f65d6ea7
https://github.com/llvm/llvm-project/commit/64eea34420e3ee1f6f91a57a72b2edf6f65d6ea7
Author: Simon Pilgrim <llvm-dev at redking.me.uk>
Date: 2022-06-13 (Mon, 13 Jun 2022)
Changed paths:
M llvm/lib/Target/X86/X86ISelLowering.cpp
M llvm/test/CodeGen/X86/is_fpclass.ll
M llvm/test/CodeGen/X86/madd.ll
M llvm/test/CodeGen/X86/mulvi32.ll
M llvm/test/CodeGen/X86/pmaddubsw.ll
M llvm/test/CodeGen/X86/promote-cmp.ll
M llvm/test/CodeGen/X86/vector-trunc-math.ll
Log Message:
-----------
[X86] combineEXTEND_VECTOR_INREG - don't attempt to shuffle combine ANY_EXTEND_VECTOR_INREG without SSE41
Without SSE41, ANY_EXTEND_VECTOR_INREG nodes are likely to be prematurely combined to a target shuffle preventing generic sign extension folds.
Fixes a number of sign-extend regressions in D127115.
More information about the All-commits
mailing list