[all-commits] [llvm/llvm-project] e97fb2: AMDGPU: Add support for load transpose instruction...

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: e97fb2207e1ef6235a6268dbbd3cc08d437b07ef
      https://github.com/llvm/llvm-project/commit/e97fb2207e1ef6235a6268dbbd3cc08d437b07ef
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-11-25 (Mon, 25 Nov 2024)

  Changed paths:
    M clang/include/clang/Basic/BuiltinsAMDGPU.def
    M clang/lib/CodeGen/CGBuiltin.cpp
    A clang/test/CodeGenOpenCL/builtins-amdgcn-gfx950-read-tr.cl
    M llvm/include/llvm/IR/IntrinsicsAMDGPU.td
    M llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
    M llvm/lib/Target/AMDGPU/DSInstructions.td
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/Analysis/UniformityAnalysis/AMDGPU/intrinsics.ll
    A llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.read.tr.gfx950.ll
    M llvm/test/MC/AMDGPU/gfx950-unsupported.s
    A llvm/test/MC/AMDGPU/gfx950_asm_read_tr.s
    A llvm/test/MC/Disassembler/AMDGPU/gfx950_dasm_ds_read_tr.txt

  Log Message:
  -----------
  AMDGPU: Add support for load transpose instructions for gfx950 (#117378)

This patch support for intrinsics in clang, as well as assembly
instructions in the backend.

Co-authored-by: Sirish Pande <Sirish.Pande at amd.com>



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