[all-commits] [llvm/llvm-project] f6431f: [MLIR][GPUToNVVM] support fastMath and other non-s...

[runseny via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: f6431f0c52689be4d6a4753d261cb6c415eff5a1
      https://github.com/llvm/llvm-project/commit/f6431f0c52689be4d6a4753d261cb6c415eff5a1
  Author: runseny <145632023+runseny at users.noreply.github.com>
  Date:   2024-07-25 (Thu, 25 Jul 2024)

  Changed paths:
    M mlir/lib/Conversion/GPUCommon/OpToFuncCallLowering.h
    M mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
    M mlir/lib/Conversion/MathToROCDL/MathToROCDL.cpp
    M mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir

  Log Message:
  -----------
  [MLIR][GPUToNVVM] support fastMath and other non-supported mathOp (#99890)

Support fastMath and other non-supported mathOp which only require float
operands and call libdevice function directly to nvvm.

1. lowering mathOp with fastMath attribute to correct libdevice
intrinsic.
2. some mathOp in math dialect has been lowered to libdevice now, but it
doesn't cover all mathOp. so this mr lowers all the remaining mathOp
which only require float operands.



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