[PATCH] D139433: [amdgpu] Reimplement LDS lowering

[Jon Chesterfield via Phabricator via llvm-commits]

JonChesterfield created this revision.
JonChesterfield added reviewers: ronlieb, arsenm.
Herald added subscribers: kosarev, foad, kerbowa, mgrang, 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.

Renames the current lowering scheme to "module" and introduces two new
ones, "kernel" and "table", plus a "hybrid" that chooses between those three
on a per-variable basis.

Unit tests are set up to pass with the default lowering of "module" or "hybrid"
with this patch defaulting to "module", which will be a less dramatic codegen
change relative to the current. This reflects the sparsity of test coverage for
the table lowering method. Hybrid is better than module in every respect and
will be default in a subsequent patch.

D138141 <https://reviews.llvm.org/D138141> reborn


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D139433

Files:
  llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
  llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
  llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp
  llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp
  llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.h
  llvm/lib/Target/AMDGPU/SIISelLowering.cpp
  llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-inline-asm.ll
  llvm/test/CodeGen/AMDGPU/addrspacecast-known-non-null.ll
  llvm/test/CodeGen/AMDGPU/ds_write2.ll
  llvm/test/CodeGen/AMDGPU/hsa.ll
  llvm/test/CodeGen/AMDGPU/lds-size.ll
  llvm/test/CodeGen/AMDGPU/local-memory.amdgcn.ll
  llvm/test/CodeGen/AMDGPU/local-memory.r600.ll
  llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll
  llvm/test/CodeGen/AMDGPU/lower-kernel-lds-constexpr.ll
  llvm/test/CodeGen/AMDGPU/lower-kernel-lds-super-align.ll
  llvm/test/CodeGen/AMDGPU/lower-kernel-lds.ll
  llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-memcpy.ll
  llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-merge.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-constantexpr-phi.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-constantexpr.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-inactive.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-offsets.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-single-var-ambiguous.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-single-var-unambiguous.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-used-list.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds-via-table.ll
  llvm/test/CodeGen/AMDGPU/lower-module-lds.ll
  llvm/test/CodeGen/AMDGPU/module-lds-false-sharing.ll
  llvm/test/CodeGen/AMDGPU/noclobber-barrier.ll
  llvm/test/CodeGen/AMDGPU/promote-alloca-stored-pointer-value.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D139433.480488.patch
Type: text/x-patch
Size: 116423 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20221206/24f205ba/attachment-0001.bin>