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

563 lines
13 KiB
YAML

# 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
...