[llvm] Reapply "[AMDGPU] Always lower s/udiv64 by constant to MUL" (PR #101942)

Pierre van Houtryve via llvm-commits llvm-commits at lists.llvm.org
Sun Aug 11 23:56:03 PDT 2024

Previous message: [llvm] Reapply "[AMDGPU] Always lower s/udiv64 by constant to MUL" (PR #101942)
Next message: [llvm] Reapply "[AMDGPU] Always lower s/udiv64 by constant to MUL" (PR #101942)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Pierre-vh wrote:

> Where is the AMDGPU regression? can it be fixed?

Some small changes in `fshr.ll` (current version is on the left)
![image](https://github.com/user-attachments/assets/89f3d631-1b5c-4cdf-a51f-976e12d7499b)


https://github.com/llvm/llvm-project/pull/101942

Previous message: [llvm] Reapply "[AMDGPU] Always lower s/udiv64 by constant to MUL" (PR #101942)
Next message: [llvm] Reapply "[AMDGPU] Always lower s/udiv64 by constant to MUL" (PR #101942)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list