[all-commits] [llvm/llvm-project] 074c37: AMDGPU: Insert kernarg code after allocas

[Matt Arsenault via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 074c371a4835e7821dd5c9919a9299e342c944de
      https://github.com/llvm/llvm-project/commit/074c371a4835e7821dd5c9919a9299e342c944de
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2020-05-06 (Wed, 06 May 2020)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp
    M llvm/test/CodeGen/AMDGPU/lower-kernargs.ll

  Log Message:
  -----------
  AMDGPU: Insert kernarg code after allocas

This produces more normal looking IR by keeping all the allocas
clustered at the start of the block.