llvm-project/llvm/test/CodeGen/AMDGPU/inserted-wait-states.mir

# RUN: llc -march=amdgcn -mcpu=tahiti -run-pass post-RA-hazard-rec  %s -o - | FileCheck %s -check-prefixes=GCN
# RUN: llc -march=amdgcn -mcpu=hawaii -run-pass post-RA-hazard-rec  %s -o - | FileCheck %s -check-prefixes=GCN,CIVI
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass post-RA-hazard-rec  %s -o - | FileCheck %s -check-prefixes=GCN,CIVI,VI
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass post-RA-hazard-rec  %s -o - | FileCheck %s -check-prefixes=GCN,CIVI,VI,GFX9

--- |
  define amdgpu_kernel void @div_fmas() { ret void }
  define amdgpu_kernel void @s_getreg() { ret void }
  define amdgpu_kernel void @s_setreg() { ret void }
  define amdgpu_kernel void @vmem_gt_8dw_store() { ret void }
  define amdgpu_kernel void @readwrite_lane() { ret void }
  define amdgpu_kernel void @rfe() { ret void }
  define amdgpu_kernel void @s_mov_fed_b32() { ret void }
  define amdgpu_kernel void @s_movrel() { ret void }
  define amdgpu_kernel void @v_interp() { ret void }
  define amdgpu_kernel void @dpp() { ret void }

  define amdgpu_kernel void @mov_fed_hazard_crash_on_dbg_value(i32 addrspace(1)* %A) {
  entry:
    %A.addr = alloca i32 addrspace(1)*, align 4, addrspace(5)
    store i32 addrspace(1)* %A, i32 addrspace(1)* addrspace(5)* %A.addr, align 4
    call void @llvm.dbg.declare(metadata i32 addrspace(1)* addrspace(5)* %A.addr, metadata !5, metadata !11), !dbg !12
    ret void
  }

  declare void @llvm.dbg.declare(metadata, metadata, metadata) #1

  !llvm.dbg.cu = !{!0}
  !llvm.module.flags = !{!3, !4}

  !0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 3.9.0 (trunk 268929)", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !2)
  !1 = !DIFile(filename: "test01.cl", directory: "/dev/null")
  !2 = !{}
  !3 = !{i32 2, !"Dwarf Version", i32 2}
  !4 = !{i32 2, !"Debug Info Version", i32 3}
  !5 = !DILocalVariable(name: "A", arg: 1, scope: !6, file: !1, line: 1, type: !9)
  !6 = distinct !DISubprogram(name: "test", scope: !1, file: !1, line: 1, type: !7, isLocal: false, isDefinition: true, scopeLine: 1, flags: DIFlagPrototyped, isOptimized: false, unit: !0, retainedNodes: !2)
  !7 = !DISubroutineType(types: !8)
  !8 = !{null, !9}
  !9 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !10, size: 64, align: 32)
  !10 = !DIBasicType(name: "int", size: 32, align: 32, encoding: DW_ATE_signed)
  !11 = !DIExpression()
  !12 = !DILocation(line: 1, column: 30, scope: !6)

...
---
# GCN-LABEL: name: div_fmas

# GCN-LABEL: bb.0:
# GCN: S_MOV_B64
# GCN-NOT: S_NOP
# GCN: V_DIV_FMAS

# GCN-LABEL: bb.1:
# GCN: V_CMP_EQ_I32
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: V_DIV_FMAS_F32

# GCN-LABEL: bb.2:
# GCN: V_CMP_EQ_I32
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: V_DIV_FMAS_F32

# GCN-LABEL: bb.3:
# GCN: V_DIV_SCALE_F32
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: V_DIV_FMAS_F32
name: div_fmas

body: |
  bb.0:
    $vcc = S_MOV_B64 0
    $vgpr0 = V_DIV_FMAS_F32 0, $vgpr1, 0, $vgpr2, 0, $vgpr3, 0, 0, implicit $vcc, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    implicit $vcc = V_CMP_EQ_I32_e32 $vgpr1, $vgpr2, implicit $exec
    $vgpr0 = V_DIV_FMAS_F32 0, $vgpr1, 0, $vgpr2, 0, $vgpr3, 0, 0, implicit $vcc, implicit $exec
    S_BRANCH %bb.2

  bb.2:
    $vcc = V_CMP_EQ_I32_e64 $vgpr1, $vgpr2, implicit $exec
    $vgpr0 = V_DIV_FMAS_F32 0, $vgpr1, 0, $vgpr2, 0, $vgpr3, 0, 0, implicit $vcc, implicit $exec
    S_BRANCH %bb.3

  bb.3:
    $vgpr4, $vcc = V_DIV_SCALE_F32 $vgpr1, $vgpr1, $vgpr3, implicit $exec
    $vgpr0 = V_DIV_FMAS_F32 0, $vgpr1, 0, $vgpr2, 0, $vgpr3, 0, 0, implicit $vcc, implicit $exec
    S_ENDPGM 0

...

...
---
# GCN-LABEL: name: s_getreg

# GCN-LABEL: bb.0:
# GCN: S_SETREG
# GCN: S_NOP 0
# GCN: S_NOP 0
# GCN: S_GETREG

# GCN-LABEL: bb.1:
# GCN: S_SETREG_IMM32
# GCN: S_NOP 0
# GCN: S_NOP 0
# GCN: S_GETREG

# GCN-LABEL: bb.2:
# GCN: S_SETREG
# GCN: S_NOP 0
# GCN: S_GETREG

# GCN-LABEL: bb.3:
# GCN: S_SETREG
# GCN-NEXT: S_GETREG

name: s_getreg

body: |
  bb.0:
    S_SETREG_B32 $sgpr0, 1
    $sgpr1 = S_GETREG_B32 1
    S_BRANCH %bb.1

  bb.1:
    S_SETREG_IMM32_B32 0, 1
    $sgpr1 = S_GETREG_B32 1
    S_BRANCH %bb.2

  bb.2:
    S_SETREG_B32 $sgpr0, 1
    $sgpr1 = S_MOV_B32 0
    $sgpr2 = S_GETREG_B32 1
    S_BRANCH %bb.3

  bb.3:
    S_SETREG_B32 $sgpr0, 0
    $sgpr1 = S_GETREG_B32 1
    S_ENDPGM 0
...

...
---
# GCN-LABEL: name: s_setreg

# GCN-LABEL: bb.0:
# GCN: S_SETREG
# GCN: S_NOP 0
# VI: S_NOP 0
# GCN-NEXT: S_SETREG

# GCN-LABEL: bb.1:
# GCN: S_SETREG
# GCN: S_NOP 0
# VI: S_NOP 0
# GCN-NEXT: S_SETREG

# GCN-LABEL: bb.2:
# GCN: S_SETREG
# GCN-NEXT: S_SETREG

name: s_setreg

body: |
  bb.0:
    S_SETREG_B32 $sgpr0, 1
    S_SETREG_B32 $sgpr1, 1
    S_BRANCH %bb.1

  bb.1:
    S_SETREG_B32 $sgpr0, 64
    S_SETREG_B32 $sgpr1, 128
    S_BRANCH %bb.2

  bb.2:
    S_SETREG_B32 $sgpr0, 1
    S_SETREG_B32 $sgpr1, 0
    S_ENDPGM 0
...

...
---
# GCN-LABEL: name: vmem_gt_8dw_store

# GCN-LABEL: bb.0:
# GCN: BUFFER_STORE_DWORD_OFFSET
# GCN-NEXT: V_MOV_B32
# GCN: BUFFER_STORE_DWORDX3_OFFSET
# CIVI: S_NOP
# GCN-NEXT: V_MOV_B32
# GCN: BUFFER_STORE_DWORDX4_OFFSET
# GCN-NEXT: V_MOV_B32
# GCN: BUFFER_STORE_DWORDX4_OFFSET
# CIVI: S_NOP
# GCN-NEXT: V_MOV_B32
# GCN: BUFFER_STORE_FORMAT_XYZ_OFFSET
# CIVI: S_NOP
# GCN-NEXT: V_MOV_B32
# GCN: BUFFER_STORE_FORMAT_XYZW_OFFSET
# CIVI: S_NOP
# GCN-NEXT: V_MOV_B32

# GCN-LABEL: bb.1:
# GCN: FLAT_STORE_DWORDX2
# GCN-NEXT: V_MOV_B32
# GCN: FLAT_STORE_DWORDX3
# CIVI: S_NOP
# GCN-NEXT: V_MOV_B32
# GCN: FLAT_STORE_DWORDX4
# CIVI: S_NOP
# GCN-NEXT: V_MOV_B32
# GCN: FLAT_ATOMIC_CMPSWAP_X2
# CIVI: S_NOP
# GCN-NEXT: V_MOV_B32
# GCN: FLAT_ATOMIC_FCMPSWAP_X2
# CIVI: S_NOP
# GCN: V_MOV_B32

name: vmem_gt_8dw_store

body: |
  bb.0:
    BUFFER_STORE_DWORD_OFFSET $vgpr3, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 0, 0, 0, 0, implicit $exec
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    BUFFER_STORE_DWORDX3_OFFSET $vgpr2_vgpr3_vgpr4, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    BUFFER_STORE_DWORDX4_OFFSET $vgpr2_vgpr3_vgpr4_vgpr5, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 0, 0, 0, 0, implicit $exec
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    BUFFER_STORE_DWORDX4_OFFSET $vgpr2_vgpr3_vgpr4_vgpr5, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    BUFFER_STORE_FORMAT_XYZ_OFFSET $vgpr2_vgpr3_vgpr4, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    BUFFER_STORE_FORMAT_XYZW_OFFSET $vgpr2_vgpr3_vgpr4_vgpr5, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    BUFFER_ATOMIC_CMPSWAP_X2_OFFSET $vgpr2_vgpr3_vgpr4_vgpr5, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, implicit $exec
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    FLAT_STORE_DWORDX2 $vgpr0_vgpr1, $vgpr2_vgpr3, 0, 0, 0, implicit $exec, implicit $flat_scr
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    FLAT_STORE_DWORDX3 $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4, 0, 0, 0, implicit $exec, implicit $flat_scr
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    FLAT_STORE_DWORDX4 $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5, 0, 0, 0, implicit $exec, implicit $flat_scr
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    FLAT_ATOMIC_CMPSWAP_X2 $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5, 0, 0, implicit $exec, implicit $flat_scr
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    FLAT_ATOMIC_FCMPSWAP_X2 $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5, 0, 0, implicit $exec, implicit $flat_scr
    $vgpr3 = V_MOV_B32_e32 0, implicit $exec
    S_ENDPGM 0

...

...
---

# GCN-LABEL: name: readwrite_lane

# GCN-LABEL: bb.0:
# GCN: V_ADD_I32
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: V_READLANE_B32

# GCN-LABEL: bb.1:
# GCN: V_ADD_I32
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: V_WRITELANE_B32

# GCN-LABEL: bb.2:
# GCN: V_ADD_I32
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: V_READLANE_B32

# GCN-LABEL: bb.3:
# GCN: V_ADD_I32
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: S_NOP
# GCN: V_WRITELANE_B32

name: readwrite_lane

body: |
  bb.0:
    $vgpr0,$sgpr0_sgpr1 = V_ADD_I32_e64 $vgpr1, $vgpr2, implicit $vcc, 0, implicit $exec
    $sgpr4 = V_READLANE_B32 $vgpr4, $sgpr0
    S_BRANCH %bb.1

  bb.1:
    $vgpr0,$sgpr0_sgpr1 = V_ADD_I32_e64 $vgpr1, $vgpr2, implicit $vcc, 0, implicit $exec
    $vgpr4 = V_WRITELANE_B32 $sgpr0, $sgpr0, $vgpr4
    S_BRANCH %bb.2

  bb.2:
    $vgpr0,implicit $vcc = V_ADD_I32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
    $sgpr4 = V_READLANE_B32 $vgpr4, $vcc_lo
    S_BRANCH %bb.3

  bb.3:
    $vgpr0,implicit $vcc = V_ADD_I32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
    $vgpr4 = V_WRITELANE_B32 $sgpr4, $vcc_lo, $vgpr4
    S_ENDPGM 0

...

...
---

# GCN-LABEL: name: rfe

# GCN-LABEL: bb.0:
# GCN: S_SETREG
# VI: S_NOP
# GCN-NEXT: S_RFE_B64

# GCN-LABEL: bb.1:
# GCN: S_SETREG
# GCN-NEXT: S_RFE_B64

name: rfe

body: |
  bb.0:
    S_SETREG_B32 $sgpr0, 3
    S_RFE_B64 $sgpr2_sgpr3
    S_BRANCH %bb.1

  bb.1:
    S_SETREG_B32 $sgpr0, 0
    S_RFE_B64 $sgpr2_sgpr3
    S_ENDPGM 0

...

...
---

# GCN-LABEL: name: s_mov_fed_b32

# GCN-LABEL: bb.0:
# GCN: S_MOV_FED_B32
# GFX9: S_NOP
# GCN-NEXT: S_MOV_B32

# GCN-LABEL: bb.1:
# GCN: S_MOV_FED_B32
# GFX9: S_NOP
# GCN-NEXT: V_MOV_B32
name: s_mov_fed_b32

body: |
  bb.0:
    $sgpr0 = S_MOV_FED_B32 $sgpr0
    $sgpr0 = S_MOV_B32 $sgpr0
    S_BRANCH %bb.1

  bb.1:
    $sgpr0 = S_MOV_FED_B32 $sgpr0
    $vgpr0 = V_MOV_B32_e32 $sgpr0, implicit $exec
    S_ENDPGM 0

...

...
---

# GCN-LABEL: name: s_movrel

# GCN-LABEL: bb.0:
# GCN: S_MOV_B32
# GFX9: S_NOP
# GCN-NEXT: S_MOVRELS_B32

# GCN-LABEL: bb.1:
# GCN: S_MOV_B32
# GFX9: S_NOP
# GCN-NEXT: S_MOVRELS_B64

# GCN-LABEL: bb.2:
# GCN: S_MOV_B32
# GFX9: S_NOP
# GCN-NEXT: S_MOVRELD_B32

# GCN-LABEL: bb.3:
# GCN: S_MOV_B32
# GFX9: S_NOP
# GCN-NEXT: S_MOVRELD_B64

name: s_movrel

body: |
  bb.0:
    $m0 = S_MOV_B32 0
    $sgpr0 = S_MOVRELS_B32 $sgpr0, implicit $m0
    S_BRANCH %bb.1

  bb.1:
    $m0 = S_MOV_B32 0
    $sgpr0_sgpr1 = S_MOVRELS_B64 $sgpr0_sgpr1, implicit $m0
    S_BRANCH %bb.2

  bb.2:
    $m0 = S_MOV_B32 0
    $sgpr0 = S_MOVRELD_B32 $sgpr0, implicit $m0
    S_BRANCH %bb.3

  bb.3:
    $m0 = S_MOV_B32 0
    $sgpr0_sgpr1 = S_MOVRELD_B64 $sgpr0_sgpr1, implicit $m0
    S_ENDPGM 0
...

...
---

# GCN-LABEL: name: v_interp

# GCN-LABEL: bb.0:
# GCN: S_MOV_B32
# GFX9-NEXT: S_NOP
# GCN-NEXT: V_INTERP_P1_F32

# GCN-LABEL: bb.1:
# GCN: S_MOV_B32
# GFX9-NEXT: S_NOP
# GCN-NEXT: V_INTERP_P2_F32

# GCN-LABEL: bb.2:
# GCN: S_MOV_B32
# GFX9-NEXT: S_NOP
# GCN-NEXT: V_INTERP_P1_F32_16bank

# GCN-LABEL: bb.3:
# GCN: S_MOV_B32
# GFX9-NEXT: S_NOP
# GCN-NEXT: V_INTERP_MOV_F32

name: v_interp

body: |
  bb.0:
    $m0 = S_MOV_B32 0
    $vgpr0 = V_INTERP_P1_F32 $vgpr0, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    $m0 = S_MOV_B32 0
    $vgpr0 = V_INTERP_P2_F32 $vgpr0, $vgpr1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.2

  bb.2:
    $m0 = S_MOV_B32 0
    $vgpr0 = V_INTERP_P1_F32_16bank $vgpr0, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.3

  bb.3:
    $m0 = S_MOV_B32 0
    $vgpr0 = V_INTERP_MOV_F32 0, 0, 0, implicit $m0, implicit $exec
    S_ENDPGM 0
...

...
---

# GCN-LABEL: name: dpp

# VI-LABEL: bb.0:
# VI: V_MOV_B32_e32
# VI-NEXT: S_NOP 0
# VI-NEXT: S_NOP 0
# VI-NEXT: V_MOV_B32_dpp

# VI-LABEL: bb.1:
# VI: V_CMPX_EQ_I32_e32
# VI-NEXT: S_NOP 0
# VI-NEXT: S_NOP 0
# VI-NEXT: S_NOP 0
# VI-NEXT: S_NOP 0
# VI-NEXT: S_NOP 0
# VI-NEXT: V_MOV_B32_dpp

name: dpp

body: |
  bb.0:
    $vgpr0 = V_MOV_B32_e32 0, implicit $exec
    $vgpr1 = V_MOV_B32_dpp $vgpr1, $vgpr0, 0, 15, 15, 0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    implicit $exec, implicit $vcc = V_CMPX_EQ_I32_e32 $vgpr0, $vgpr1, implicit $exec
    $vgpr3 = V_MOV_B32_dpp $vgpr3, $vgpr0, 0, 15, 15, 0, implicit $exec
    S_ENDPGM 0
...
---
name:            mov_fed_hazard_crash_on_dbg_value
alignment:       0
exposesReturnsTwice: false
legalized:       false
regBankSelected: false
selected:        false
tracksRegLiveness: true
liveins:
  - { reg: '$sgpr4_sgpr5' }
  - { reg: '$sgpr6_sgpr7' }
  - { reg: '$sgpr9' }
  - { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
frameInfo:
  isFrameAddressTaken: false
  isReturnAddressTaken: false
  hasStackMap:     false
  hasPatchPoint:   false
  stackSize:       16
  offsetAdjustment: 0
  maxAlignment:    8
  adjustsStack:    false
  hasCalls:        false
  maxCallFrameSize: 0
  hasOpaqueSPAdjustment: false
  hasVAStart:      false
  hasMustTailInVarArgFunc: false
stack:
  - { id: 0, name: A.addr, offset: 0, size: 8, alignment: 8, local-offset: 0 }
  - { id: 1, offset: 8, size: 4, alignment: 4 }
body:             |
  bb.0.entry:
    liveins: $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr9, $sgpr0_sgpr1_sgpr2_sgpr3

    $flat_scr_lo = S_ADD_U32 $sgpr6, $sgpr9, implicit-def $scc
    $flat_scr_hi = S_ADDC_U32 $sgpr7, 0, implicit-def $scc, implicit $scc
    DBG_VALUE $noreg, 2, !5, !11, debug-location !12
    $sgpr4_sgpr5 = S_LOAD_DWORDX2_IMM killed $sgpr4_sgpr5, 0, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(4)* undef`)
    dead $sgpr6_sgpr7 = KILL $sgpr4_sgpr5
    $sgpr8 = S_MOV_B32 $sgpr5
    $vgpr0 = V_MOV_B32_e32 killed $sgpr8, implicit $exec
    BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr9, 4, 0, 0, 0, implicit $exec :: (store 4 into %ir.A.addr + 4)
    $sgpr8 = S_MOV_B32 $sgpr4, implicit killed $sgpr4_sgpr5
    $vgpr0 = V_MOV_B32_e32 killed $sgpr8, implicit $exec
    BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr9, 0, 0, 0, 0, implicit $exec :: (store 4 into %ir.A.addr)
    S_ENDPGM 0

...