[PATCH] D155190: [amdgpu][lds] Remove recalculation of LDS frame from backend

[Matt Arsenault via Phabricator via llvm-commits]

arsenm accepted this revision.
arsenm added inline comments.
This revision is now accepted and ready to land.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp:48
+  // pass is disabled. If graphics does not use dynamic LDS, this is never
+  // profitable. Leaving cleanup for a later change.
+  LDSSize = F.getFnAttributeAsParsedInteger("amdgpu-lds-size", 0);
----------------
Not sure exactly what two variables or "profitable" this is talking about 


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp:76
+    std::optional<uint32_t> MaybeAbs = getLDSAbsoluteAddress(GV);
+    if (MaybeAbs) {
+      // Absolute address LDS variables that exist prior to the LDS lowering
----------------
If we did the same thing, could probably fix the bug with amdgpu-gds-size not interacting well with globals


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D155190/new/

https://reviews.llvm.org/D155190