[PATCH] D155125: [amdgpu][lds] Introduce LDS frame size function attribute

[Jon Chesterfield via Phabricator via llvm-commits]

JonChesterfield created this revision.
JonChesterfield added reviewers: arsenm, jmmartinez.
Herald added subscribers: foad, kerbowa, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl.
Herald added a project: All.
JonChesterfield requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

Record the LDS size on functions. Step towards breaking the symbol
association currently used to pair up kernels with struct instances.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D155125

Files:
  llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
  llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp
  llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-all-indirect-accesses.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-constantexpr.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-indirect-extern-uses-max-reachable-alignment.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-via-hybrid.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-via-table.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D155125.539750.patch
Type: text/x-patch
Size: 14053 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230712/8edf4708/attachment.bin>