[all-commits] [llvm/llvm-project] 95ed50: [AMDGPU] Promote <2 x bfloat> select to i32 (#214598)

[Jake Daly via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 95ed5004a6f623b4a542027334681e3c9c4e30ac
      https://github.com/llvm/llvm-project/commit/95ed5004a6f623b4a542027334681e3c9c4e30ac
  Author: Jake Daly <48452250+jakemdaly at users.noreply.github.com>
  Date:   2026-08-07 (Fri, 07 Aug 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/bf16.ll

  Log Message:
  -----------
  [AMDGPU] Promote <2 x bfloat> select to i32 (#214598)

`select` on <2 x bfloat> has no operation action registered, so it
defaults to Expand. The vector legalizer scalarizes it into two 16-bit
selects, which are promoted to i16 and selected as a pair of
V_CNDMASK_B16 plus shifts and a repack to reassemble the result on
targets without true16.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications