Backend: Remove redundant `fcanonicalize`
Open
floating-point
llvm:codegen
- Dominant language
- LLVM
- Stars
- 40.5k
- Forks
- 18.7k
- PR merge metrics
- PR metrics pending
Description
Code like
```
define float @minimumnum_fp32(float %a, float %b, float %c, float %d) {
%minab = call float @llvm.minimumnum.f32(float %a, float %b)
%mincd = call float @llvm.minimumnum.f32(float %c, float %d)
%min = call float @llvm.minimumnum.f32(float %minab, float %mincd)
ret float %min
}
```
On platforms has `fmaxnum_ieee`, the `fcanonicalize` is not needed for the 3rd `llvm.minimumnum.f32`.
Contributor guide
Assessment
This issue has not been assessed yet.