[PATCH] D106684: [x86] improve CMOV codegen by pushing add into operands, part 2
Simon Pilgrim via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Sat Jul 24 04:17:26 PDT 2021
RKSimon added inline comments.
================
Comment at: llvm/test/CodeGen/X86/add-cmov.ll:251
+; CHECK-NEXT: cmovneq %rcx, %rax
; CHECK-NEXT: retq
%gep2 = getelementptr inbounds %class.btAxis, %class.btAxis* %ptr, i64 %idx, i32 2, i64 0
----------------
I think this could be: https://llvm.godbolt.org/z/WMaPvfKKh
```
leaq (%rdx,%rdx,4), %rax
shlq $4, %rax
leaq 6(%rax), %rcx
testb $1, %dil
cmovneq %rax, %rcx
leaq 60(%rsi,%rcx), %rax
```
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D106684/new/
https://reviews.llvm.org/D106684
More information about the llvm-commits
mailing list