[llvm] [AMDGPU] Lower uniform uaddsat.i16 to SALU instructions (PR #210156)

Anshil Gandhi via llvm-commits llvm-commits at lists.llvm.org
Fri Jul 17 11:00:14 PDT 2026

Previous message: [llvm] [AMDGPU] Lower uniform uaddsat.i16 to SALU instructions (PR #210156)
Next message: [llvm] [AMDGPU] Use alias analysis for SMEM/VMEM WAR waitcnts (PR #206569)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

gandhi56 wrote:

I am in favor of Jay's idea to use `promoteUniformToI32` function to encourage combining of nodes in SIISelLowering. I updated the PR with this implementation.

https://github.com/llvm/llvm-project/pull/210156

Previous message: [llvm] [AMDGPU] Lower uniform uaddsat.i16 to SALU instructions (PR #210156)
Next message: [llvm] [AMDGPU] Use alias analysis for SMEM/VMEM WAR waitcnts (PR #206569)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list