[PATCH] D102334: [AMDGPU] Sort LDS globals based on thier size and alignment.

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

Why do we need another pass if we always just produce llvm.amdgcn.module.lds such that codegen will always allocate one single global?



================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h:41
+  // soon as possible.
+  static std::vector<GlobalVariable *> SortedLDSGlobals;
 
----------------
rampitec wrote:
> I do not think you can keep per-module stuff in the TM.
You absolutely cannot do this here


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D102334/new/

https://reviews.llvm.org/D102334