[all-commits] [llvm/llvm-project] 6115b1: [NVPTX] Add lowering for bitcasts float<->v4i8 (#6...

[Artem Belevich via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 6115b1b9077c8b1777792b30ff45ce756590037b
      https://github.com/llvm/llvm-project/commit/6115b1b9077c8b1777792b30ff45ce756590037b
  Author: Artem Belevich <tra at google.com>
  Date:   2023-10-23 (Mon, 23 Oct 2023)

  Changed paths:
    M llvm/lib/Target/NVPTX/NVPTXInstrInfo.td
    M llvm/test/CodeGen/NVPTX/access-non-generic.ll
    M llvm/test/CodeGen/NVPTX/i8x4-instructions.ll
    M llvm/test/CodeGen/NVPTX/named-barriers.ll
    M llvm/test/CodeGen/NVPTX/reg-types.ll
    M llvm/test/CodeGen/NVPTX/shift-parts.ll

  Log Message:
  -----------
  [NVPTX] Add lowering for bitcasts float<->v4i8 (#69960)

.. and move bitcast from a constant for integer-based types into a
better suited location. It solves the mystery of why we sometimes used
`mov.u32` and sometimes `mov.b32` for loading constants. Now they all
should use `.b32`