[PATCH] D25788: AMDGPU/SI: Don't emit multi-dword flat memory ops when they might access scratch

Mandeep Singh Grang via llvm-commits llvm-commits at lists.llvm.org
Wed Oct 19 12:22:18 PDT 2016


mgrang added inline comments.


================
Comment at: test/CodeGen/AMDGPU/flat-address-space.ll:1
-; RUN: llc -O0 -mtriple=amdgcn-mesa-mesa3d -mcpu=bonaire < %s | FileCheck -check-prefix=CHECK %s
-; RUN: llc -O0 -mtriple=amdgcn-mesa-mesa3d -mcpu=tonga < %s | FileCheck -check-prefix=CHECK %s
+; RUN: llc -O0 -mtriple=amdgcn-mesa-mesa3d -mcpu=bonaire < %s | FileCheck -check-prefixes=CHECK %s
+; RUN: llc -O0 -mtriple=amdgcn-mesa-mesa3d -mcpu=tonga < %s | FileCheck -check-prefixes=CHECK %s
----------------
-check-prefixes=CHECK is not needed.


https://reviews.llvm.org/D25788





More information about the llvm-commits mailing list