Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/whole-wave-functions-pei.mir
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

512 lines
25 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -run-pass=prologepilog -o - %s | FileCheck %s
---
name: save_inactive_lanes_non_csr_vgpr
alignment: 1
tracksRegLiveness: true
noPhis: true
isSSA: false
noVRegs: true
hasFakeUses: false
tracksDebugUserValues: true
frameInfo:
maxAlignment: 1
isCalleeSavedInfoValid: true
machineFunctionInfo:
maxKernArgAlign: 1
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
returnsVoid: false
occupancy: 16
sgprForEXECCopy: '$sgpr105'
isWholeWaveFunction: true
body: |
bb.0:
; CHECK-LABEL: name: save_inactive_lanes_non_csr_vgpr
; CHECK: liveins: $vgpr0, $vgpr0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION escape 0x0f, 0x09, 0x90, 0x40, 0x94, 0x04, 0x35, 0x24, 0x36, 0xe9, 0x02
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr0
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr0
; CHECK-NEXT: $sgpr0 = S_XOR_SAVEEXEC_B32 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.0, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr0, 0
; CHECK-NEXT: $exec_lo = S_MOV_B32 -1
; CHECK-NEXT: $vgpr0 = V_MOV_B32_e32 14, implicit $exec
; CHECK-NEXT: $exec_lo = S_XOR_B32 $sgpr0, -1, implicit-def $scc
; CHECK-NEXT: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 0, 0, implicit $exec, implicit $flat_scr, implicit $vgpr0(tied-def 0) :: ("amdgpu-thread-private" load (s32) from %stack.0, addrspace 5)
; CHECK-NEXT: $exec_lo = S_MOV_B32 $sgpr0
; CHECK-NEXT: SI_RETURN implicit killed $vgpr0
renamable $sgpr0 = SI_WHOLE_WAVE_FUNC_SETUP implicit-def dead $exec, implicit $exec
$vgpr0 = V_MOV_B32_e32 14, implicit $exec
SI_WHOLE_WAVE_FUNC_RETURN killed renamable $sgpr0, implicit killed $vgpr0
...
---
name: save_all_lanes_csr_vgpr
alignment: 1
tracksRegLiveness: true
noPhis: true
isSSA: false
noVRegs: true
hasFakeUses: false
tracksDebugUserValues: true
frameInfo:
maxAlignment: 1
isCalleeSavedInfoValid: true
machineFunctionInfo:
maxKernArgAlign: 1
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
returnsVoid: false
occupancy: 16
sgprForEXECCopy: '$sgpr105'
isWholeWaveFunction: true
body: |
bb.0:
; CHECK-LABEL: name: save_all_lanes_csr_vgpr
; CHECK: liveins: $vgpr40
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION escape 0x0f, 0x09, 0x90, 0x40, 0x94, 0x04, 0x35, 0x24, 0x36, 0xe9, 0x02
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr0
; CHECK-NEXT: $sgpr0 = S_OR_SAVEEXEC_B32 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr40, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.0, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr40, 0
; CHECK-NEXT: $vgpr40 = V_MOV_B32_e32 14, implicit $exec
; CHECK-NEXT: $vgpr40 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.0, addrspace 5)
; CHECK-NEXT: $exec_lo = S_MOV_B32 $sgpr0
; CHECK-NEXT: SI_RETURN
renamable $sgpr0 = SI_WHOLE_WAVE_FUNC_SETUP implicit-def dead $exec, implicit $exec
$vgpr40 = V_MOV_B32_e32 14, implicit $exec
SI_WHOLE_WAVE_FUNC_RETURN killed renamable $sgpr0
...
---
name: save_csr_sgpr_to_non_csr_vgpr
alignment: 1
tracksRegLiveness: true
noPhis: true
isSSA: false
noVRegs: true
hasFakeUses: false
tracksDebugUserValues: true
frameInfo:
maxAlignment: 1
isCalleeSavedInfoValid: true
machineFunctionInfo:
maxKernArgAlign: 1
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
returnsVoid: false
occupancy: 16
sgprForEXECCopy: '$sgpr105'
isWholeWaveFunction: true
body: |
bb.0:
liveins: $sgpr20, $vgpr191
; CHECK-LABEL: name: save_csr_sgpr_to_non_csr_vgpr
; CHECK: liveins: $sgpr20, $vgpr191, $vgpr192
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION escape 0x0f, 0x09, 0x90, 0x40, 0x94, 0x04, 0x35, 0x24, 0x36, 0xe9, 0x02
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr192
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr20
; CHECK-NEXT: $vcc_lo = S_XOR_SAVEEXEC_B32 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr192, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.0, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr192, 0
; CHECK-NEXT: $exec_lo = S_MOV_B32 -1
; CHECK-NEXT: $vgpr192 = SI_SPILL_S32_TO_VGPR killed $sgpr20, 0, $vgpr192
; CHECK-NEXT: $sgpr20 = S_MOV_B32 14, implicit $exec
; CHECK-NEXT: $sgpr20 = SI_RESTORE_S32_FROM_VGPR $vgpr192, 0
; CHECK-NEXT: $exec_lo = S_XOR_B32 $vcc_lo, -1, implicit-def $scc
; CHECK-NEXT: $vgpr192 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.0, addrspace 5)
; CHECK-NEXT: $exec_lo = S_MOV_B32 $vcc_lo
; CHECK-NEXT: SI_RETURN
$vgpr192 = SI_SPILL_S32_TO_VGPR killed $sgpr20, 0, $vgpr192
renamable $vcc_lo = SI_WHOLE_WAVE_FUNC_SETUP implicit-def dead $exec, implicit $exec
$sgpr20 = S_MOV_B32 14, implicit $exec
$sgpr20 = SI_RESTORE_S32_FROM_VGPR $vgpr192, 0
SI_WHOLE_WAVE_FUNC_RETURN killed renamable $vcc_lo
...
---
name: save_csr_sgpr_to_csr_vgpr
alignment: 1
tracksRegLiveness: true
noPhis: true
isSSA: false
noVRegs: true
hasFakeUses: false
tracksDebugUserValues: true
frameInfo:
maxAlignment: 1
isCalleeSavedInfoValid: true
machineFunctionInfo:
maxKernArgAlign: 1
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
returnsVoid: false
occupancy: 16
sgprForEXECCopy: '$sgpr105'
isWholeWaveFunction: true
body: |
bb.0:
liveins: $sgpr20, $vgpr191
; CHECK-LABEL: name: save_csr_sgpr_to_csr_vgpr
; CHECK: liveins: $sgpr20, $vgpr191
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION escape 0x0f, 0x09, 0x90, 0x40, 0x94, 0x04, 0x35, 0x24, 0x36, 0xe9, 0x02
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr20
; CHECK-NEXT: $vcc_lo = S_OR_SAVEEXEC_B32 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr191, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.0, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr191, 0
; CHECK-NEXT: $vgpr191 = SI_SPILL_S32_TO_VGPR killed $sgpr20, 0, $vgpr191
; CHECK-NEXT: $sgpr20 = S_MOV_B32 14, implicit $exec
; CHECK-NEXT: $sgpr20 = SI_RESTORE_S32_FROM_VGPR $vgpr191, 0
; CHECK-NEXT: $vgpr191 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.0, addrspace 5)
; CHECK-NEXT: $exec_lo = S_MOV_B32 $vcc_lo
; CHECK-NEXT: SI_RETURN
$vgpr191 = SI_SPILL_S32_TO_VGPR killed $sgpr20, 0, $vgpr191
renamable $vcc_lo = SI_WHOLE_WAVE_FUNC_SETUP implicit-def dead $exec, implicit $exec
$sgpr20 = S_MOV_B32 14, implicit $exec
$sgpr20 = SI_RESTORE_S32_FROM_VGPR $vgpr191, 0
SI_WHOLE_WAVE_FUNC_RETURN killed renamable $vcc_lo
...
---
name: vgpr_and_sgpr_csr
alignment: 1
tracksRegLiveness: true
noPhis: true
isSSA: false
noVRegs: true
hasFakeUses: false
tracksDebugUserValues: true
liveins:
- { reg: '$vgpr0' }
- { reg: '$vgpr1' }
frameInfo:
maxAlignment: 4
isCalleeSavedInfoValid: true
machineFunctionInfo:
maxKernArgAlign: 1
hasSpilledSGPRs: true
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
returnsVoid: false
occupancy: 16
spillPhysVGPRs:
- '$vgpr191'
wwmReservedRegs:
- '$vgpr191'
isWholeWaveFunction: true
body: |
bb.0:
liveins: $sgpr20, $vgpr0, $vgpr1, $vgpr191
; CHECK-LABEL: name: vgpr_and_sgpr_csr
; CHECK: liveins: $sgpr20, $vgpr0, $vgpr1, $vgpr40, $vgpr49, $vgpr49
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION escape 0x0f, 0x09, 0x90, 0x40, 0x94, 0x04, 0x35, 0x24, 0x36, 0xe9, 0x02
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr0
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr49
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr20
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr40
; CHECK-NEXT: $vcc_lo = S_XOR_SAVEEXEC_B32 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.0, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr0, 0
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr49, $sgpr32, 8, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.2, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr49, 256
; CHECK-NEXT: $exec_lo = S_MOV_B32 -1
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr40, $sgpr32, 4, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.1, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr40, 128
; CHECK-NEXT: $vgpr0 = SI_SPILL_S32_TO_VGPR killed $sgpr20, 0, $vgpr0
; CHECK-NEXT: S_NOP 0, implicit-def $vgpr40, implicit-def $sgpr20
; CHECK-NEXT: S_NOP 0, implicit-def $vgpr49, implicit-def $sgpr40
; CHECK-NEXT: $sgpr20 = SI_RESTORE_S32_FROM_VGPR $vgpr0, 0
; CHECK-NEXT: $vgpr40 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 4, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.1, addrspace 5)
; CHECK-NEXT: $exec_lo = S_XOR_B32 $vcc_lo, -1, implicit-def $scc
; CHECK-NEXT: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.0, addrspace 5)
; CHECK-NEXT: $vgpr49 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 8, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.2, addrspace 5)
; CHECK-NEXT: $exec_lo = S_MOV_B32 $vcc_lo
; CHECK-NEXT: SI_RETURN
$vgpr191 = SI_SPILL_S32_TO_VGPR killed $sgpr20, 0, $vgpr191
renamable $vcc_lo = SI_WHOLE_WAVE_FUNC_SETUP implicit-def dead $exec, implicit $exec
S_NOP 0, implicit-def $vgpr40, implicit-def $sgpr20
S_NOP 0, implicit-def $vgpr49, implicit-def $sgpr40
$sgpr20 = SI_RESTORE_S32_FROM_VGPR $vgpr191, 0
SI_WHOLE_WAVE_FUNC_RETURN killed renamable $vcc_lo
...
---
name: split_orig_exec
alignment: 1
tracksRegLiveness: true
noPhis: true
isSSA: false
noVRegs: true
hasFakeUses: false
tracksDebugUserValues: true
liveins:
- { reg: '$vgpr0' }
- { reg: '$vgpr1' }
frameInfo:
maxAlignment: 4
isCalleeSavedInfoValid: true
machineFunctionInfo:
maxKernArgAlign: 1
hasSpilledSGPRs: true
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
returnsVoid: false
occupancy: 16
spillPhysVGPRs:
- '$vgpr191'
wwmReservedRegs:
- '$vgpr191'
isWholeWaveFunction: true
body: |
bb.0:
liveins: $sgpr20, $vgpr0, $vgpr1, $vgpr191
; CHECK-LABEL: name: split_orig_exec
; CHECK: liveins: $sgpr20, $vgpr0, $vgpr1, $vgpr40, $vgpr49, $vgpr49
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION escape 0x0f, 0x09, 0x90, 0x40, 0x94, 0x04, 0x35, 0x24, 0x36, 0xe9, 0x02
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr0
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr49
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr3
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr20
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr40
; CHECK-NEXT: $vcc_lo = S_XOR_SAVEEXEC_B32 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.0, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr0, 0
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr49, $sgpr32, 8, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.2, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr49, 256
; CHECK-NEXT: $exec_lo = S_MOV_B32 -1
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr40, $sgpr32, 4, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.1, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr40, 128
; CHECK-NEXT: $vgpr0 = SI_SPILL_S32_TO_VGPR killed $sgpr20, 0, $vgpr0
; CHECK-NEXT: S_NOP 0, implicit-def $vgpr40, implicit-def $sgpr20
; CHECK-NEXT: $sgpr3 = COPY $vcc_lo
; CHECK-NEXT: S_NOP 0, implicit-def $vgpr49, implicit-def $sgpr40
; CHECK-NEXT: $sgpr20 = SI_RESTORE_S32_FROM_VGPR $vgpr0, 0
; CHECK-NEXT: $vgpr40 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 4, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.1, addrspace 5)
; CHECK-NEXT: $exec_lo = S_XOR_B32 $sgpr3, -1, implicit-def $scc
; CHECK-NEXT: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.0, addrspace 5)
; CHECK-NEXT: $vgpr49 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 8, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.2, addrspace 5)
; CHECK-NEXT: $exec_lo = S_MOV_B32 $sgpr3
; CHECK-NEXT: SI_RETURN
$vgpr191 = SI_SPILL_S32_TO_VGPR killed $sgpr20, 0, $vgpr191
renamable $vcc_lo = SI_WHOLE_WAVE_FUNC_SETUP implicit-def dead $exec, implicit $exec
S_NOP 0, implicit-def $vgpr40, implicit-def $sgpr20
$sgpr3 = COPY $vcc_lo
S_NOP 0, implicit-def $vgpr49, implicit-def $sgpr40
$sgpr20 = SI_RESTORE_S32_FROM_VGPR $vgpr191, 0
SI_WHOLE_WAVE_FUNC_RETURN killed renamable $sgpr3
...
---
name: vgpr_superregs
alignment: 1
tracksRegLiveness: true
noPhis: true
isSSA: false
noVRegs: true
hasFakeUses: false
tracksDebugUserValues: true
frameInfo:
maxAlignment: 1
isCalleeSavedInfoValid: true
machineFunctionInfo:
maxKernArgAlign: 1
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
returnsVoid: false
occupancy: 16
sgprForEXECCopy: '$sgpr105'
isWholeWaveFunction: true
body: |
bb.0:
; CHECK-LABEL: name: vgpr_superregs
; CHECK: liveins: $vgpr0, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr40, $vgpr41, $vgpr42, $vgpr0, $vgpr2, $vgpr3, $vgpr4, $vgpr5
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION escape 0x0f, 0x09, 0x90, 0x40, 0x94, 0x04, 0x35, 0x24, 0x36, 0xe9, 0x02
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr0
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr2
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr3
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr4
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr5
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr0
; CHECK-NEXT: $sgpr0 = S_XOR_SAVEEXEC_B32 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.0, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr0, 0
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr2, $sgpr32, 4, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.1, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr2, 128
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr3, $sgpr32, 8, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.2, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr3, 256
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr4, $sgpr32, 12, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.3, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr4, 384
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr5, $sgpr32, 16, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.4, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr5, 512
; CHECK-NEXT: $exec_lo = S_MOV_B32 -1
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr40, $sgpr32, 20, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.5, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr40, 640
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr41, $sgpr32, 24, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.6, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr41, 768
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr42, $sgpr32, 28, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.7, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr42, 896
; CHECK-NEXT: $vgpr0 = V_MOV_B32_e32 14, implicit $exec
; CHECK-NEXT: S_NOP 0, implicit-def $vgpr2_vgpr3_vgpr4_vgpr5, implicit-def $vgpr40_vgpr41_vgpr42
; CHECK-NEXT: $vgpr40 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 20, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.5, addrspace 5)
; CHECK-NEXT: $vgpr41 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 24, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.6, addrspace 5)
; CHECK-NEXT: $vgpr42 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 28, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.7, addrspace 5)
; CHECK-NEXT: $exec_lo = S_XOR_B32 $sgpr0, -1, implicit-def $scc
; CHECK-NEXT: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 0, 0, implicit $exec, implicit $flat_scr, implicit $vgpr0(tied-def 0) :: ("amdgpu-thread-private" load (s32) from %stack.0, addrspace 5)
; CHECK-NEXT: $vgpr2 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 4, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.1, addrspace 5)
; CHECK-NEXT: $vgpr3 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 8, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.2, addrspace 5)
; CHECK-NEXT: $vgpr4 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 12, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.3, addrspace 5)
; CHECK-NEXT: $vgpr5 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 16, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.4, addrspace 5)
; CHECK-NEXT: $exec_lo = S_MOV_B32 $sgpr0
; CHECK-NEXT: SI_RETURN implicit killed $vgpr0
renamable $sgpr0 = SI_WHOLE_WAVE_FUNC_SETUP implicit-def dead $exec, implicit $exec
$vgpr0 = V_MOV_B32_e32 14, implicit $exec
S_NOP 0, implicit-def $vgpr2_vgpr3_vgpr4_vgpr5, implicit-def $vgpr40_vgpr41_vgpr42
SI_WHOLE_WAVE_FUNC_RETURN killed renamable $sgpr0, implicit killed $vgpr0
...
---
name: dont_restore_used_vgprs
alignment: 1
tracksRegLiveness: true
noPhis: true
isSSA: false
noVRegs: true
hasFakeUses: false
tracksDebugUserValues: true
liveins:
- { reg: '$vgpr0' }
- { reg: '$vgpr20' }
- { reg: '$vgpr40' }
frameInfo:
maxAlignment: 1
isCalleeSavedInfoValid: true
machineFunctionInfo:
maxKernArgAlign: 1
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
returnsVoid: false
occupancy: 16
sgprForEXECCopy: '$sgpr105'
isWholeWaveFunction: true
body: |
bb.0:
liveins: $vgpr0, $vgpr20, $vgpr40
; CHECK-LABEL: name: dont_restore_used_vgprs
; CHECK: liveins: $vgpr0, $vgpr20, $vgpr40
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION escape 0x0f, 0x09, 0x90, 0x40, 0x94, 0x04, 0x35, 0x24, 0x36, 0xe9, 0x02
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr0
; CHECK-NEXT: $sgpr0 = S_XOR_SAVEEXEC_B32 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
; CHECK-NEXT: S_NOP 0, implicit $vgpr0, implicit $vgpr20, implicit $vgpr40
; CHECK-NEXT: $exec_lo = S_MOV_B32 $sgpr0
; CHECK-NEXT: SI_RETURN implicit killed $vgpr0
renamable $sgpr0 = SI_WHOLE_WAVE_FUNC_SETUP implicit-def dead $exec, implicit $exec
S_NOP 0, implicit $vgpr0, implicit $vgpr20, implicit $vgpr40
SI_WHOLE_WAVE_FUNC_RETURN killed renamable $sgpr0, implicit killed $vgpr0
...
---
name: multiple_blocks
alignment: 1
tracksRegLiveness: true
noPhis: true
isSSA: false
noVRegs: true
hasFakeUses: false
tracksDebugUserValues: true
liveins:
- { reg: '$vgpr0' }
- { reg: '$vgpr1' }
frameInfo:
maxAlignment: 1
isCalleeSavedInfoValid: true
machineFunctionInfo:
maxKernArgAlign: 1
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
returnsVoid: false
occupancy: 16
sgprForEXECCopy: '$sgpr105'
isWholeWaveFunction: true
body: |
; CHECK-LABEL: name: multiple_blocks
; CHECK: bb.0:
; CHECK-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
; CHECK-NEXT: liveins: $vgpr0, $vgpr1, $vgpr0, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION escape 0x0f, 0x09, 0x90, 0x40, 0x94, 0x04, 0x35, 0x24, 0x36, 0xe9, 0x02
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr0
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr1
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr1
; CHECK-NEXT: $vcc_lo = S_XOR_SAVEEXEC_B32 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.0, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr0, 0
; CHECK-NEXT: SCRATCH_STORE_DWORD_SADDR $vgpr1, $sgpr32, 4, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.1, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $vgpr1, 128
; CHECK-NEXT: $exec_lo = S_MOV_B32 -1
; CHECK-NEXT: $sgpr1 = S_MOV_B32 $exec_lo
; CHECK-NEXT: V_CMPX_EQ_U32_nosdst_e64 $vgpr0, $vgpr1, implicit-def $exec, implicit $exec
; CHECK-NEXT: S_CBRANCH_EXECZ %bb.2, implicit $exec
; CHECK-NEXT: S_BRANCH %bb.1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.1:
; CHECK-NEXT: successors: %bb.2(0x80000000)
; CHECK-NEXT: liveins: $vcc_lo, $sgpr1, $vgpr0, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: renamable $vgpr1 = V_ADD_U32_e64 $vgpr0, $vgpr1, 0, implicit $exec
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.2:
; CHECK-NEXT: liveins: $vcc_lo, $sgpr1, $vgpr0, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: $exec_lo = S_OR_B32 $exec_lo, killed renamable $sgpr1, implicit-def $scc
; CHECK-NEXT: renamable $vgpr0 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr0, $vcc_lo, implicit $exec
; CHECK-NEXT: $exec_lo = S_XOR_B32 $vcc_lo, -1, implicit-def $scc
; CHECK-NEXT: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 0, 0, implicit $exec, implicit $flat_scr, implicit $vgpr0(tied-def 0) :: ("amdgpu-thread-private" load (s32) from %stack.0, addrspace 5)
; CHECK-NEXT: $vgpr1 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 4, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.1, addrspace 5)
; CHECK-NEXT: $exec_lo = S_MOV_B32 $vcc_lo
; CHECK-NEXT: SI_RETURN implicit $vgpr0
bb.0:
successors: %bb.1, %bb.2
liveins: $vgpr0, $vgpr1
renamable $vcc_lo = SI_WHOLE_WAVE_FUNC_SETUP implicit-def dead $exec, implicit $exec
$sgpr1 = S_MOV_B32 $exec_lo
V_CMPX_EQ_U32_nosdst_e64 $vgpr0, $vgpr1, implicit-def $exec, implicit $exec
S_CBRANCH_EXECZ %bb.2, implicit $exec
S_BRANCH %bb.1
bb.1:
liveins: $vcc_lo, $sgpr1, $vgpr0, $vgpr1
renamable $vgpr1 = V_ADD_U32_e64 $vgpr0, $vgpr1, 0, implicit $exec
bb.2:
liveins: $vcc_lo, $sgpr1, $vgpr0, $vgpr1
$exec_lo = S_OR_B32 $exec_lo, killed renamable $sgpr1, implicit-def $scc
renamable $vgpr0 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr0, $vcc_lo, implicit $exec
SI_WHOLE_WAVE_FUNC_RETURN killed renamable $vcc_lo, implicit $vgpr0
...