[all-commits] [llvm/llvm-project] 76a0c0: [AMDGPU][CostModel] Improve cost estimation for fu...

[Daniil Fukalov via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 76a0c0ee6ffa9c38485776921948d8f930109674
      https://github.com/llvm/llvm-project/commit/76a0c0ee6ffa9c38485776921948d8f930109674
  Author: dfukalov <daniil.fukalov at amd.com>
  Date:   2020-07-16 (Thu, 16 Jul 2020)

  Changed paths:
    M llvm/include/llvm/CodeGen/BasicTTIImpl.h
    M llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
    A llvm/test/Analysis/CostModel/AMDGPU/fused_costs.ll

  Log Message:
  -----------
  [AMDGPU][CostModel] Improve cost estimation for fused {fadd|fsub}(a,fmul(b,c))

Summary:
If result of fmul(b,c) has one use, in almost all cases (except denormals are
IEEE) the pair of operations will be fused in one fma/mad/mac/etc.

Reviewers: rampitec

Reviewed By: rampitec

Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits, kerbowa

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D83919