[PATCH] D52121: [X86] Fold (movmsk (setne (and X, (1 << C)), 0)) -> (movmsk (X << C))
Simon Pilgrim via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Sep 14 15:03:49 PDT 2018
RKSimon added inline comments.
================
Comment at: test/CodeGen/X86/movmsk-cmp.ll:1128
+; SSE2-NEXT: psllw $7, %xmm0
+; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
; SSE2-NEXT: pmovmskb %xmm0, %eax
----------------
Are these and masks necessary - we're only using the signbit?
================
Comment at: test/CodeGen/X86/movmsk-cmp.ll:1221
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
----------------
Fix AVX1 case too?
https://reviews.llvm.org/D52121
More information about the llvm-commits
mailing list