[all-commits] [llvm/llvm-project] d42c7b: AMDGPU: Account for the size of LDS globals used t...

[Matt Arsenault via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: d42c7b22118c763090e3bec180cb8f01b5c4cfeb
      https://github.com/llvm/llvm-project/commit/d42c7b22118c763090e3bec180cb8f01b5c4cfeb
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2020-07-29 (Wed, 29 Jul 2020)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
    M llvm/test/CodeGen/AMDGPU/promote-alloca-padding-size-estimate.ll
    M llvm/test/CodeGen/AMDGPU/promote-alloca-to-lds-constantexpr-use.ll

  Log Message:
  -----------
  AMDGPU: Account for the size of LDS globals used through constant
expressions.

Also "fix" the longstanding bug where the computed size depends on the
order of the visitation. We could try to predict the allocation order
used by legalization, but it would never be 100% perfect. Until we
start fixing the addresses somehow (or have a more reliable allocation
scheme later), just try to compute the size based on the worst case
padding.