[PATCH] D144221: [amdgpu][nfc] Replace ad hoc LDS frame recalculation with absolute_symbol MD

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp:515
 
-  Info->allocateKnownAddressLDSGlobal(F);
+  Info->allocateKnownAddressLDSGlobal(MF.getFunction().getParent(), F);
 
----------------
F.getParent


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp:599
 
-  Info->allocateKnownAddressLDSGlobal(F);
+  Info->allocateKnownAddressLDSGlobal(MF.getFunction().getParent(), F);
 
----------------
Ditto


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp:124
+  auto Type = M->getDataLayout().getIntPtrType(Ctx, AMDGPUAS::LOCAL_ADDRESS);
+  GV->setMetadata(LLVMContext::MD_absolute_symbol,
+                  MDNode::get(Ctx, ConstantAsMetadata::get(
----------------
Changing the IR in a codegen pass is bad. Can you set this earlier?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D144221/new/

https://reviews.llvm.org/D144221