| Issue |
124776
|
| Summary |
AMDGPU should make v2i32 and/or/xor legal
|
| Labels |
backend:AMDGPU,
missed-optimization
|
| Assignees |
|
| Reporter |
arsenm
|
We currently failed to make use of s_or_b64/s_and_b64/s_xor_b64 in the uniform cases, and scalarize into pairs of the 32-bit binary operators. Making them legal is simple (starter patch attached), but avoiding all the regressions is more difficult.
[0001-AMDGPU-Make-v2i32-and-or-xor-legal.patch](https://github.com/user-attachments/files/18576211/0001-AMDGPU-Make-v2i32-and-or-xor-legal.patch)
We need additional combiner work to avoid the regressions
![]()
_______________________________________________
llvm-bugs mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
