[PATCH] D106684: [x86] improve CMOV codegen by pushing add into operands, part 2

[Simon Pilgrim via Phabricator via llvm-commits]

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