[PATCH] D74035: [AMDGPU] Cluster MIMG instructions

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Thu May 21 08:03:40 PDT 2020


arsenm added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/cluster_stores.ll:1-2
 ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -debug-only=machine-scheduler -o /dev/null %s 2>&1 | FileCheck --enable-var-scope --check-prefixes=CHECK,DBG %s
 ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --enable-var-scope --check-prefixes=CHECK,GCN %s
 ; REQUIRES: asserts
----------------
This could use a temp file to avoid compiling this twice. Redirect stderr to a temp file and run the dbg check on that?


================
Comment at: llvm/test/CodeGen/AMDGPU/cluster_stores.ll:92
+; DBG: {{^}}[[SU2]]: {{.*}} IMAGE_LOAD
+define amdgpu_ps void @cluster_image_load(<8 x i32> inreg %src, <8 x i32> inreg %dst, i32 %x, i32 %y) {
+entry:
----------------
Could use instruction checks that these are adjacent?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D74035/new/

https://reviews.llvm.org/D74035





More information about the llvm-commits mailing list