# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck %s
# Test what happens when an SGPR is unavailable for the unused add
# carry out when materializing the frame index.
# There are truly no free SGPRs, so the entire frame index expansion
# needs to be inverted to restore the original frame register.
---
name: scavenge_sgpr_pei_no_sgprs
tracksRegLiveness: true
stack:
- { id: 0, type: default, offset: 0, size: 4, alignment: 8192 }
- { id: 1, type: default, offset: 0, size: 4, alignment: 8192 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
frameOffsetReg: $sgpr33
stackPtrOffsetReg: $sgpr32
body: |
bb.0:
liveins: $vgpr1
; CHECK-LABEL: name: scavenge_sgpr_pei_no_sgprs
; CHECK: liveins: $vgpr1, $vgpr2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: $sgpr4 = COPY $sgpr33
; CHECK-NEXT: $sgpr33 = frame-setup S_ADD_I32 $sgpr32, 524224, implicit-def $scc
; CHECK-NEXT: $sgpr33 = frame-setup S_AND_B32 killed $sgpr33, 4294443008, implicit-def dead $scc
; CHECK-NEXT: $sgpr6_sgpr7 = S_XOR_SAVEEXEC_B64 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
; CHECK-NEXT: $sgpr5 = S_ADD_I32 $sgpr33, 1048832, implicit-def dead $scc
; CHECK-NEXT: BUFFER_STORE_DWORD_OFFSET $vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3, killed $sgpr5, 0, 0, 0, implicit $exec :: (store (s32) into %stack.3, addrspace 5)
; CHECK-NEXT: $exec = S_MOV_B64 killed $sgpr6_sgpr7
; CHECK-NEXT: $vgpr2 = SI_SPILL_S32_TO_VGPR $sgpr4, 0, undef $vgpr2
; CHECK-NEXT: $sgpr32 = frame-setup S_ADD_I32 $sgpr32, 2097152, implicit-def dead $scc
; CHECK-NEXT: S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr27, implicit-def $sgpr28, implicit-def $sgpr29, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
; CHECK-NEXT: $sgpr33 = S_LSHR_B32 $sgpr33, 6, implicit-def $scc
; CHECK-NEXT: $sgpr33 = S_ADD_I32 killed $sgpr33, 8192, implicit-def $scc
; CHECK-NEXT: $vgpr0 = COPY killed $sgpr33
; CHECK-NEXT: $sgpr33 = S_ADD_I32 killed $sgpr33, -8192, implicit-def $scc
; CHECK-NEXT: $sgpr33 = S_LSHL_B32 $sgpr33, 6, implicit-def $scc
; CHECK-NEXT: $sgpr33 = S_LSHR_B32 $sgpr33, 6, implicit-def $scc
; CHECK-NEXT: $sgpr33 = S_ADD_I32 killed $sgpr33, 16384, implicit-def $scc
; CHECK-NEXT: $vgpr3 = COPY killed $sgpr33
; CHECK-NEXT: $sgpr33 = S_ADD_I32 killed $sgpr33, -16384, implicit-def $scc
; CHECK-NEXT: $sgpr33 = S_LSHL_B32 $sgpr33, 6, implicit-def $scc
; CHECK-NEXT: $vgpr0 = V_OR_B32_e32 killed $vgpr3, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31
; CHECK-NEXT: $sgpr4 = SI_RESTORE_S32_FROM_VGPR $vgpr2, 0
; CHECK-NEXT: $sgpr6_sgpr7 = S_XOR_SAVEEXEC_B64 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
; CHECK-NEXT: $sgpr5 = S_ADD_I32 $sgpr33, 1048832, implicit-def dead $scc
; CHECK-NEXT: $vgpr2 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, killed $sgpr5, 0, 0, 0, implicit $exec :: (load (s32) from %stack.3, addrspace 5)
; CHECK-NEXT: $exec = S_MOV_B64 killed $sgpr6_sgpr7
; CHECK-NEXT: $sgpr32 = frame-destroy S_ADD_I32 $sgpr32, -2097152, implicit-def dead $scc
; CHECK-NEXT: $sgpr33 = COPY $sgpr4
; CHECK-NEXT: S_ENDPGM 0, implicit $vcc
S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr27, implicit-def $sgpr28, implicit-def $sgpr29, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
$vgpr0 = V_MOV_B32_e32 %stack.0, implicit $exec
$vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31
S_ENDPGM 0, implicit $vcc
...
# One 32-bit SGPR is available for the intermediate scale computation,
# so only an extra copy to VALU is necessary.
---
name: scavenge_sgpr_pei_one_sgpr
tracksRegLiveness: true
stack:
- { id: 0, type: default, offset: 0, size: 4, alignment: 8192 }
- { id: 1, type: default, offset: 0, size: 4, alignment: 8192 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
frameOffsetReg: $sgpr33
stackPtrOffsetReg: $sgpr32
body: |
bb.0:
liveins: $vgpr1
; CHECK-LABEL: name: scavenge_sgpr_pei_one_sgpr
; CHECK: liveins: $sgpr29, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: $sgpr29 = frame-setup COPY $sgpr33
; CHECK-NEXT: $sgpr33 = frame-setup S_ADD_I32 $sgpr32, 524224, implicit-def $scc
; CHECK-NEXT: $sgpr33 = frame-setup S_AND_B32 killed $sgpr33, 4294443008, implicit-def dead $scc
; CHECK-NEXT: $sgpr32 = frame-setup S_ADD_I32 $sgpr32, 2097152, implicit-def dead $scc
; CHECK-NEXT: S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr27, implicit-def $sgpr28, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
; CHECK-NEXT: $sgpr33 = S_LSHR_B32 $sgpr33, 6, implicit-def $scc
; CHECK-NEXT: $sgpr33 = S_ADD_I32 killed $sgpr33, 8192, implicit-def $scc
; CHECK-NEXT: $vgpr0 = COPY killed $sgpr33
; CHECK-NEXT: $sgpr33 = S_ADD_I32 killed $sgpr33, -8192, implicit-def $scc
; CHECK-NEXT: $sgpr33 = S_LSHL_B32 $sgpr33, 6, implicit-def $scc
; CHECK-NEXT: $sgpr33 = S_LSHR_B32 $sgpr33, 6, implicit-def $scc
; CHECK-NEXT: $sgpr33 = S_ADD_I32 killed $sgpr33, 16384, implicit-def $scc
; CHECK-NEXT: $vgpr2 = COPY killed $sgpr33
; CHECK-NEXT: $sgpr33 = S_ADD_I32 killed $sgpr33, -16384, implicit-def $scc
; CHECK-NEXT: $sgpr33 = S_LSHL_B32 $sgpr33, 6, implicit-def $scc
; CHECK-NEXT: $vgpr0 = V_OR_B32_e32 killed $vgpr2, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr31
; CHECK-NEXT: $sgpr32 = frame-destroy S_ADD_I32 $sgpr32, -2097152, implicit-def dead $scc
; CHECK-NEXT: $sgpr33 = frame-destroy COPY $sgpr29
; CHECK-NEXT: S_ENDPGM 0, implicit $vcc
S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr27, implicit-def $sgpr28, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
$vgpr0 = V_MOV_B32_e32 %stack.0, implicit $exec
$vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr31
S_ENDPGM 0, implicit $vcc
...
# When only one 64-bit SGPR is available for the unused carry out pre gfx9,
# we must reuse one of the 32-bit SGPR sub-regs to materialize the offset.
---
name: scavenge_sgpr_pei_one_sgpr_64
tracksRegLiveness: true
stack:
- { id: 0, type: default, offset: 0, size: 4, alignment: 8192 }
- { id: 1, type: default, offset: 0, size: 4, alignment: 8192 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
frameOffsetReg: $sgpr33
stackPtrOffsetReg: $sgpr32
body: |
bb.0:
liveins: $vgpr1
; CHECK-LABEL: name: scavenge_sgpr_pei_one_sgpr_64
; CHECK: liveins: $sgpr28, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: $sgpr28 = frame-setup COPY $sgpr33
; CHECK-NEXT: $sgpr33 = frame-setup S_ADD_I32 $sgpr32, 524224, implicit-def $scc
; CHECK-NEXT: $sgpr33 = frame-setup S_AND_B32 killed $sgpr33, 4294443008, implicit-def dead $scc
; CHECK-NEXT: $sgpr32 = frame-setup S_ADD_I32 $sgpr32, 2097152, implicit-def dead $scc
; CHECK-NEXT: S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr27, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
; CHECK-NEXT: $sgpr29 = S_LSHR_B32 $sgpr33, 6, implicit-def $scc
; CHECK-NEXT: $sgpr29 = S_ADD_I32 killed $sgpr29, 8192, implicit-def $scc
; CHECK-NEXT: $vgpr0 = COPY killed $sgpr29
; CHECK-NEXT: $sgpr29 = S_LSHR_B32 $sgpr33, 6, implicit-def $scc
; CHECK-NEXT: $sgpr29 = S_ADD_I32 killed $sgpr29, 16384, implicit-def $scc
; CHECK-NEXT: $vgpr2 = COPY killed $sgpr29
; CHECK-NEXT: $vgpr0 = V_OR_B32_e32 killed $vgpr2, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr31
; CHECK-NEXT: $sgpr32 = frame-destroy S_ADD_I32 $sgpr32, -2097152, implicit-def dead $scc
; CHECK-NEXT: $sgpr33 = frame-destroy COPY $sgpr28
; CHECK-NEXT: S_ENDPGM 0, implicit $vcc
S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr27, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
$vgpr0 = V_MOV_B32_e32 %stack.0, implicit $exec
$vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr31
S_ENDPGM 0, implicit $vcc
...
# Prefer to use vcc as unused carry out.
---
name: scavenge_sgpr_pei_prefer_vcc
tracksRegLiveness: true
stack:
- { id: 0, type: default, offset: 0, size: 4, alignment: 8192 }
- { id: 1, type: default, offset: 0, size: 4, alignment: 8192 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
frameOffsetReg: $sgpr33
stackPtrOffsetReg: $sgpr32
body: |
bb.0:
liveins: $vgpr1
; CHECK-LABEL: name: scavenge_sgpr_pei_prefer_vcc
; CHECK: liveins: $sgpr28, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: $sgpr28 = frame-setup COPY $sgpr33
; CHECK-NEXT: $sgpr33 = frame-setup S_ADD_I32 $sgpr32, 524224, implicit-def $scc
; CHECK-NEXT: $sgpr33 = frame-setup S_AND_B32 killed $sgpr33, 4294443008, implicit-def dead $scc
; CHECK-NEXT: $sgpr32 = frame-setup S_ADD_I32 $sgpr32, 2097152, implicit-def dead $scc
; CHECK-NEXT: S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr27, implicit-def $sgpr30, implicit-def $sgpr31
; CHECK-NEXT: $vgpr0 = V_LSHRREV_B32_e64 6, $sgpr33, implicit $exec
; CHECK-NEXT: $vcc_lo = S_MOV_B32 8192
; CHECK-NEXT: $vgpr0, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr0, 0, implicit $exec
; CHECK-NEXT: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr33, implicit $exec
; CHECK-NEXT: $vcc_lo = S_MOV_B32 16384
; CHECK-NEXT: $vgpr2, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr2, 0, implicit $exec
; CHECK-NEXT: $vgpr0 = V_OR_B32_e32 killed $vgpr2, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr31
; CHECK-NEXT: $sgpr32 = frame-destroy S_ADD_I32 $sgpr32, -2097152, implicit-def dead $scc
; CHECK-NEXT: $sgpr33 = frame-destroy COPY $sgpr28
; CHECK-NEXT: S_ENDPGM 0
S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr27, implicit-def $sgpr30, implicit-def $sgpr31
$vgpr0 = V_MOV_B32_e32 %stack.0, implicit $exec
$vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr31
S_ENDPGM 0
...