[all-commits] [llvm/llvm-project] 22a2d7: [NVPTX] Emit ld.v4.b16 for loading <4 x bfloat> (#...

[Ahmed S. Taei via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 22a2d74c0c6dbde6b3503ec51486d6cf5d0c83f1
      https://github.com/llvm/llvm-project/commit/22a2d74c0c6dbde6b3503ec51486d6cf5d0c83f1
  Author: Ahmed S. Taei <asaadaldien at users.noreply.github.com>
  Date:   2024-09-17 (Tue, 17 Sep 2024)

  Changed paths:
    M llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
    M llvm/test/CodeGen/NVPTX/vector-loads.ll

  Log Message:
  -----------
  [NVPTX] Emit ld.v4.b16 for loading <4 x bfloat> (#109069)

This PR enables emitting a single load instruction for <4 x bfloat>,
otherwise, 2 ld.b32 loads are generated.



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