llvm/llvm/test/CodeGen/AMDGPU/machinelicm-convergent.mir

# RUN: llc -mtriple=amdgcn  -run-pass=early-machinelicm -o - %s | FileCheck %s
# RUN: llc -mtriple=amdgcn  -passes=early-machinelicm -o - %s | FileCheck %s

# Test to check machine LICM does not hoist convergent instructions,
# DS_PERMUTE_B32 in this example.

---
# CHECK-LABEL: name: _amdgpu_cs_main
# CHECK: bb.1:
# CHECK: DS_PERMUTE_B32

name: _amdgpu_cs_main
body: |
  bb.0:
    liveins: $vgpr0, $vgpr1
    successors: %bb.1

    %0:vgpr_32 = COPY $vgpr0
    %1:vgpr_32 = COPY $vgpr1

  bb.1:
    successors: %bb.1, %bb.2

    %2:vgpr_32 = DS_PERMUTE_B32 %0, %1, 0, implicit $exec
    %3:vgpr_32 = V_ADD_CO_U32_e32 %0, %2, implicit-def $vcc, implicit $exec
    S_CBRANCH_SCC1 %bb.1, implicit undef $scc
    S_BRANCH %bb.2

  bb.2:
    $vgpr0 = COPY %3
    S_ENDPGM 0

...