llvm-project/llvm/test/CodeGen/AMDGPU/waitcnt-loop-single-basic-block.mir

# RUN: llc -o - %s -march=amdgcn -run-pass=si-insert-waitcnts -verify-machineinstrs | FileCheck -check-prefix=GCN %s

# Check that the waitcnt propogates info in the case of a single basic block loop

# GCN-LABEL: waitcnt-loop-single-basic-block
# GCN: bb.0
# GCN: S_WAITCNT 3952
# GCN-NEXT: GLOBAL_STORE_DWORD
# GCN: S_WAITCNT 3953
# GCN-NEXT: GLOBAL_STORE_DWORD

...
name: waitcnt-loop-single-basic-block
body: |
  bb.0:
    S_BRANCH %bb.1
  bb.1:
    GLOBAL_STORE_DWORD $vgpr7_vgpr8, $vgpr11, 0, 0, 0, implicit $exec
    $vgpr21 = GLOBAL_LOAD_DWORD $vgpr4_vgpr5, 0, 0, 0, implicit $exec
    $vgpr10 = GLOBAL_LOAD_DWORD $vgpr10_vgpr11, 0, 0, 0, implicit $exec
    GLOBAL_STORE_DWORD $vgpr14_vgpr15, $vgpr21, 0, 0, 0, implicit $exec
    $vgpr11 = GLOBAL_LOAD_DWORD $vgpr11_vgpr12, 0, 0, 0, implicit $exec
    S_CBRANCH_SCC1 %bb.1, implicit $scc
  bb.2:
    S_ENDPGM 0
...