llvm/llvm-project
Vedi su GitHub[X86] Failure to reduce extended i64 add/sub/mul arithmetic to i32 with known zeros in the upper 32-bits
Open
#142.308 aperta il 1 giu 2025
backend:X86good first issuemissed-optimization
Metriche repository
- Star
- (26.378 star)
- Metriche merge PR
- (Merge medio 1g 2h) (1000 PR mergiate in 30 g)
Descrizione
https://c.godbolt.org/z/3Gv4rPEGq
As noted on #141360 - x86 i64 add/sub/mul arithmetic is not reduced to i32 arithmetic when the upper 32-bits are known to be zero (and can be implicitly zero-extended). We do appear to do this for logic and shift instructions.
On recent CPU targets, ADD/SUB i64 is usually just as cheap as i32 equivalents but MUL can often still benefit, and there's potential for shorter instruction encodings for all of them.
We can either handle this with combineAdd/Sub/Mul in X86ISelLowering.cpp or we can wait until X86ISelDAGToDAG.cpp