[all-commits] [llvm/llvm-project] fcbfff: AMDGPU: Remove floating point dot4 and dot2 from g...

[Changpeng Fang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: fcbfff193e96037aa8131af91cefee2888d3de72
      https://github.com/llvm/llvm-project/commit/fcbfff193e96037aa8131af91cefee2888d3de72
  Author: Changpeng Fang <changpeng.fang at amd.com>
  Date:   2025-06-25 (Wed, 25 Jun 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/VOPInstructions.td
    M llvm/test/MC/AMDGPU/gfx1250_asm_unsupported.s

  Log Message:
  -----------
  AMDGPU: Remove floating point dot4 and dot2 from gfx1250 support (#145751)

We have FeatureDot9Insts for dot2 and FeatureDot11Insts for dot4. And
gfx1250 does not support these two features. So everything was in place
except that we need to copy SubtargetPredicate from pseudo to real for
VOP3_DPP8_t16.



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