[PATCH] D84448: [AMDGPU] Make generating cache invalidating instructions optional

Piotr Sobczak via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Thu Jul 23 10:28:49 PDT 2020


piotr created this revision.
Herald added subscribers: llvm-commits, kerbowa, dexonsmith, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely, kzhuravl, arsenm.
Herald added a project: LLVM.

D78800 <https://reviews.llvm.org/D78800> skipped generating cache invalidating instrucions altogether
on AMDPAL. However, this is sometimes too restrictive - we want a
more flexible option to be able to toggle this behaviour on and off
while we work towards developing a correct implementation of the
alternative memory model.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D84448

Files:
  llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp
  llvm/test/CodeGen/AMDGPU/memory-legalizer-amdpal.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D84448.280196.patch
Type: text/x-patch
Size: 8035 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200723/4c7b44c1/attachment.bin>


More information about the llvm-commits mailing list