[all-commits] [llvm/llvm-project] b01426: [mlir][AMDGPU] New gfx12 barrier instructions and ...

[Daniel Hernandez-Juarez via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: b014265d992ce515826a8d3ce378ca1f643e297d
      https://github.com/llvm/llvm-project/commit/b014265d992ce515826a8d3ce378ca1f643e297d
  Author: Daniel Hernandez-Juarez <dhernandez0 at gmail.com>
  Date:   2024-09-20 (Fri, 20 Sep 2024)

  Changed paths:
    M mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td
    M mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
    M mlir/test/Conversion/AMDGPUToROCDL/amdgpu-to-rocdl.mlir
    M mlir/test/Dialect/LLVMIR/rocdl.mlir
    M mlir/test/Target/LLVMIR/rocdl.mlir

  Log Message:
  -----------
  [mlir][AMDGPU] New gfx12 barrier instructions and update lowering LDSBarrierOp (#109273)

New gfx12 barrier instructions: s.barrier.signal, s.barrier.wait and
s.wait.dscnt. And update lowering LDSBarrierOp accordingly.

CC: @krzysz00 @manupak @giuseros



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