[llvm] [AMDGPU] Fix implicit operands of VOPD cndmask instructions (PR #87788)

Joe Nash via llvm-commits llvm-commits at lists.llvm.org
Wed Apr 10 07:28:43 PDT 2024

Previous message: [llvm] 5ae9ffb - [RISCV] Address review comment from 88062
Next message: [llvm] [RISCV] Only support SPLAT_VECTOR for Zvfhmin when also enable the scalar extension of half fp (PR #88275)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Sisyph wrote:

This seems like a good step. LGTM. I agree that it would be better to fix vcc on construction rather than after. For VOPD, it wouldn't even require HwMode, because the instructions are only available in wave32. 

https://github.com/llvm/llvm-project/pull/87788

Previous message: [llvm] 5ae9ffb - [RISCV] Address review comment from 88062
Next message: [llvm] [RISCV] Only support SPLAT_VECTOR for Zvfhmin when also enable the scalar extension of half fp (PR #88275)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list