[llvm] [AMDGPU] Eliminate unnecessary packing in wider f16 vectors for sdwa/opsel-able instruction (PR #137137)

Vikash Gupta via llvm-commits llvm-commits at lists.llvm.org
Mon May 19 23:01:19 PDT 2025

Previous message: [llvm] [RISCV] Add compress patterns for qc.extu and qc.mvltui (PR #140682)
Next message: [llvm] f8e2e70 - [CGData] Return ArrayRef<std::string> in getNames (NFC) (#140675)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

vg0204 wrote:

@Pierre-vh , @arsenm , @jayfoad , @frederik-h  kind ping for review!

https://github.com/llvm/llvm-project/pull/137137

Previous message: [llvm] [RISCV] Add compress patterns for qc.extu and qc.mvltui (PR #140682)
Next message: [llvm] f8e2e70 - [CGData] Return ArrayRef<std::string> in getNames (NFC) (#140675)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list