[llvm] [AArch64][GlobalISel] Take abs scalar codegen closer to SDAG (PR #84886)
David Green via llvm-commits
llvm-commits at lists.llvm.org
Tue Mar 12 14:20:50 PDT 2024
davemgreen wrote:
Given we have a csneg instruction, do we just want `cmp x, 0; csneg x, x`? i.e I would expect us to want to lower to a compare+neg+select (which isn't either of the existing lowerAbs* methods, and might not be easy to tell generically that we want to generate code for, if there is not an obvious way to check for csneg).
https://github.com/llvm/llvm-project/pull/84886
More information about the llvm-commits
mailing list