src/llvm-project/llvm/test/CodeGen/AMDGPU/wqm-terminators.mir

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 2
# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass si-wqm -o -  %s | FileCheck %s

--- |
  define amdgpu_ps void @exit_to_exact() {
    ret void
  }
...
---

---
name: exit_to_exact
tracksRegLiveness: true
registers:
  - { id: 0, class: sgpr_32, preferred-register: '' }
  - { id: 1, class: vreg_64, preferred-register: '' }
  - { id: 2, class: sgpr_256, preferred-register: '' }
  - { id: 3, class: sgpr_128, preferred-register: '' }
  - { id: 4, class: vreg_96, preferred-register: '' }
  - { id: 5, class: vreg_64, preferred-register: '' }
  - { id: 6, class: vgpr_32, preferred-register: '' }
liveins:
  - { reg: '$sgpr0', virtual-reg: '%0' }
body: |
  ; CHECK-LABEL: name: exit_to_exact
  ; CHECK: bb.0:
  ; CHECK-NEXT:   successors: %bb.2(0x40000000), %bb.1(0x40000000)
  ; CHECK-NEXT:   liveins: $sgpr0, $vgpr0_vgpr1
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:sreg_32 = COPY $exec_lo
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr0
  ; CHECK-NEXT:   $exec_lo = S_WQM_B32 $exec_lo, implicit-def $scc
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:sgpr_256 = IMPLICIT_DEF
  ; CHECK-NEXT:   [[DEF1:%[0-9]+]]:sgpr_128 = IMPLICIT_DEF
  ; CHECK-NEXT:   S_CMP_EQ_U32 [[COPY1]], 0, implicit-def $scc
  ; CHECK-NEXT:   undef %5.sub0:vreg_64 = V_MUL_F32_e64 0, [[COPY2]].sub0, 0, [[COPY2]].sub1, 0, 0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   %5.sub1:vreg_64 = V_MUL_F32_e64 0, [[COPY2]].sub0, 0, [[COPY2]].sub1, 0, 0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $scc
  ; CHECK-NEXT:   $exec_lo = S_AND_B32 $exec_lo, [[COPY]], implicit-def $scc
  ; CHECK-NEXT:   $scc = COPY [[COPY3]]
  ; CHECK-NEXT:   [[IMAGE_SAMPLE_V3_V2_gfx10_:%[0-9]+]]:vreg_96 = IMAGE_SAMPLE_V3_V2_gfx10 %5, [[DEF]], [[DEF1]], 7, 1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 8)
  ; CHECK-NEXT:   S_CBRANCH_SCC1 %bb.2, implicit $scc
  ; CHECK-NEXT:   S_BRANCH %bb.1
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1:
  ; CHECK-NEXT:   successors: %bb.2(0x80000000)
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.2:
  ; CHECK-NEXT:   [[V_SUB_F32_e64_:%[0-9]+]]:vgpr_32 = nofpexcept V_SUB_F32_e64 0, [[IMAGE_SAMPLE_V3_V2_gfx10_]].sub0, 0, [[IMAGE_SAMPLE_V3_V2_gfx10_]].sub1, 0, 0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   BUFFER_STORE_DWORD_OFFSET_exact [[V_SUB_F32_e64_]], [[DEF1]], [[COPY1]], 4, 0, 0, implicit $exec
  ; CHECK-NEXT:   EXP 0, [[V_SUB_F32_e64_]], [[IMAGE_SAMPLE_V3_V2_gfx10_]].sub0, [[IMAGE_SAMPLE_V3_V2_gfx10_]].sub1, [[IMAGE_SAMPLE_V3_V2_gfx10_]].sub2, 0, 0, 0, implicit $exec
  ; CHECK-NEXT:   S_ENDPGM 0
  bb.0:
    liveins: $sgpr0, $vgpr0_vgpr1

    %0 = COPY $sgpr0
    %1 = COPY $vgpr0_vgpr1
    %2 = IMPLICIT_DEF
    %3 = IMPLICIT_DEF

    S_CMP_EQ_U32 %0, 0, implicit-def $scc
    undef %5.sub0 = V_MUL_F32_e64 0, %1.sub0, 0, %1.sub1, 0, 0, implicit $mode, implicit $exec
    %5.sub1 = V_MUL_F32_e64 0, %1.sub0, 0, %1.sub1, 0, 0, implicit $mode, implicit $exec
    %4 = IMAGE_SAMPLE_V3_V2_gfx10 %5, %2, %3, 7, 1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 8)
    S_CBRANCH_SCC1 %bb.2, implicit killed $scc
    S_BRANCH %bb.1

  bb.1:

  bb.2:
    %6 = nofpexcept V_SUB_F32_e64 0, %4.sub0, 0, %4.sub1, 0, 0, implicit $mode, implicit $exec
    BUFFER_STORE_DWORD_OFFSET_exact %6, %3, %0, 4, 0, 0, implicit $exec
    EXP 0, %6, %4.sub0, %4.sub1, %4.sub2, 0, 0, 0, implicit $exec
    S_ENDPGM 0

...