llvm/llvm/test/CodeGen/AMDGPU/waitcnt-no-redundant.mir

# RUN: llc -mtriple=amdgcn -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck %s

# Check that the waitcnt pass does *not* insert a redundant waitcnt instr.
# In this testcase, ensure that pass does not insert redundant S_WAITCNT 3952

...
# CHECK-LABEL: name: waitcnt-no-redundant
# CHECK: FLAT_ATOMIC_CMPSWAP
# CHECK-NEXT: S_WAITCNT 3952
# CHECK-NEXT: BUFFER_WBINVL1

name: waitcnt-no-redundant
body: |
  bb.0:
    renamable $vgpr0 = V_MOV_B32_e32 0, implicit $exec

  bb.1:
    S_WAITCNT 3952
    FLAT_ATOMIC_CMPSWAP undef renamable $vgpr0_vgpr1, renamable $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
    S_WAITCNT 3952
    BUFFER_WBINVL1 implicit $exec
    S_BRANCH %bb.1

...

# Check that the waitcnt pass does *not* insert a waitcnt inst after S_BUFFER_LOAD.
# WAR hazard does not apply here, because S_BUFFER_LOAD accesses invariant memory.
...
# CHECK-LABEL: name: waitcnt-no-war-wait
# CHECK: S_WAITCNT 0
# CHECK-NEXT: S_BUFFER_LOAD_DWORD_IMM
# CHECK-NEXT: TBUFFER_STORE_FORMAT_X_OFFEN_exact
name: waitcnt-no-war-wait
body: |
  bb.0:
    renamable $sgpr8 = S_BUFFER_LOAD_DWORD_IMM renamable $sgpr0_sgpr1_sgpr2_sgpr3, 276, 0 :: (dereferenceable invariant load (s32))
    TBUFFER_STORE_FORMAT_X_OFFEN_exact killed renamable $vgpr0, renamable $vgpr15, renamable $sgpr4_sgpr5_sgpr6_sgpr7, renamable $sgpr9, 0, 116, 1, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 7)

...