This is an archive of the discontinued LLVM Phabricator instance.

Differential D73616

[ARM][LowOverheadLoops] Ensure memory predication
ClosedPublic

Authored by samparker on Jan 29 2020, 3:12 AM.

Details

Reviewers
dmgreen
SjoerdMeijer
Commits
rG4c7f819204d8: [ARM][LowOverheadLoops] Ensure memory predication
Summary

While validating each MVE instruction, check that all instructions that touch memory are somehow predicated upon the VCTP.

Diff Detail

Event Timeline

samparker created this revision.Jan 29 2020, 3:12 AM
Herald added a project: Restricted Project. · View Herald TranscriptJan 29 2020, 3:12 AM
Herald added subscribers: hiraditya, kristof.beyls. · View Herald Transcript
SjoerdMeijer accepted this revision.Feb 4 2020, 2:00 AM

LGTM

This revision is now accepted and ready to land.Feb 4 2020, 2:00 AM
Closed by commit rG4c7f819204d8: [ARM][LowOverheadLoops] Ensure memory predication (authored by samparker). · Explain WhyFeb 5 2020, 5:23 AM
This revision was automatically updated to reflect the committed changes.

Revision Contents

PathSize
llvm/
lib/
Target/
ARM/
3 lines
test/
CodeGen/
Thumb2/
LowOverheadLoops/
203 lines
170 lines

Diff 242567

llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp

Show First 20 Lines • Show All 610 Lines • ▼ Show 20 Linesbool LowOverheadLoop::ValidateMVEInst(MachineInstr* MI) {
// If we find an instruction that has been marked as not valid for tail // If we find an instruction that has been marked as not valid for tail
// predication, only allow the instruction if it's contained within a valid // predication, only allow the instruction if it's contained within a valid
// VPT block. // VPT block.
if ((Flags & ARMII::ValidForTailPredication) == 0 && !IsUse) { if ((Flags & ARMII::ValidForTailPredication) == 0 && !IsUse) {
LLVM_DEBUG(dbgs() << "ARM Loops: Can't tail predicate: " << *MI); LLVM_DEBUG(dbgs() << "ARM Loops: Can't tail predicate: " << *MI);
return false; return false;
} }
return true; // Ensure that all memory operations are predicated.
return !IsUse && MI->mayLoadOrStore() ? false : true;
} }
bool ARMLowOverheadLoops::runOnMachineFunction(MachineFunction &mf) { bool ARMLowOverheadLoops::runOnMachineFunction(MachineFunction &mf) {
const ARMSubtarget &ST = static_cast<const ARMSubtarget&>(mf.getSubtarget()); const ARMSubtarget &ST = static_cast<const ARMSubtarget&>(mf.getSubtarget());
if (!ST.hasLOB()) if (!ST.hasLOB())
return false; return false;
MF = &mf; MF = &mf;
▲ Show 20 Lines • Show All 440 Lines • Show Last 20 Lines

llvm/test/CodeGen/Thumb2/LowOverheadLoops/non-masked-load.mir

  • This file was added.
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve %s -run-pass=arm-low-overhead-loops -o - --verify-machineinstrs | FileCheck %s
--- |
define dso_local arm_aapcs_vfpcc zeroext i8 @non_masked_load(i8* nocapture readonly %a, i8* nocapture readonly %b, i32 %N) {
entry:
%cmp11 = icmp eq i32 %N, 0
%0 = add i32 %N, 15
%1 = lshr i32 %0, 4
%2 = shl nuw i32 %1, 4
%3 = add i32 %2, -16
%4 = lshr i32 %3, 4
%5 = add nuw nsw i32 %4, 1
br i1 %cmp11, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
call void @llvm.set.loop.iterations.i32(i32 %5)
%6 = shl i32 %4, 3
%7 = sub i32 %N, %6
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%lsr.iv20 = phi i8* [ %scevgep21, %vector.body ], [ %b, %vector.ph ]
%lsr.iv = phi i8* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
%vec.phi = phi <16 x i8> [ zeroinitializer, %vector.ph ], [ %13, %vector.body ]
%8 = phi i32 [ %5, %vector.ph ], [ %14, %vector.body ]
%9 = phi i32 [ %N, %vector.ph ], [ %11, %vector.body ]
%lsr.iv2022 = bitcast i8* %lsr.iv20 to <16 x i8>*
%lsr.iv19 = bitcast i8* %lsr.iv to <16 x i8>*
%10 = call <16 x i1> @llvm.arm.mve.vctp8(i32 %9)
%11 = sub i32 %9, 16
%wide.masked.load = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %lsr.iv19, i32 1, <16 x i1> %10, <16 x i8> undef)
%wide.load16 = load <16 x i8>, <16 x i8>* %lsr.iv2022
%12 = add <16 x i8> %wide.masked.load, %vec.phi
%13 = add <16 x i8> %12, %wide.load16
%scevgep = getelementptr i8, i8* %lsr.iv, i32 16
%scevgep21 = getelementptr i8, i8* %lsr.iv20, i32 16
%14 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %8, i32 1)
%15 = icmp ne i32 %14, 0
br i1 %15, label %vector.body, label %middle.block
middle.block: ; preds = %vector.body
%vec.phi.lcssa = phi <16 x i8> [ %vec.phi, %vector.body ]
%.lcssa = phi <16 x i8> [ %13, %vector.body ]
%16 = call <16 x i1> @llvm.arm.mve.vctp8(i32 %7)
%17 = select <16 x i1> %16, <16 x i8> %.lcssa, <16 x i8> %vec.phi.lcssa
%18 = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> %17)
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %middle.block, %entry
%res.0.lcssa = phi i8 [ 0, %entry ], [ %18, %middle.block ]
ret i8 %res.0.lcssa
}
declare <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>*, i32 immarg, <16 x i1>, <16 x i8>) #1
declare i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8>) #2
declare void @llvm.set.loop.iterations.i32(i32) #3
declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #3
declare <16 x i1> @llvm.arm.mve.vctp8(i32) #4
...
---
name: non_masked_load
alignment: 2
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
failedISel: false
tracksRegLiveness: true
hasWinCFI: false
registers: []
liveins:
- { reg: '$r0', virtual-reg: '' }
- { reg: '$r1', virtual-reg: '' }
- { reg: '$r2', virtual-reg: '' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 8
offsetAdjustment: 0
maxAlignment: 4
adjustsStack: false
hasCalls: false
stackProtector: ''
maxCallFrameSize: 0
cvBytesOfCalleeSavedRegisters: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
localFrameSize: 0
savePoint: ''
restorePoint: ''
fixedStack: []
stack:
- { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
- { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites: []
constants: []
machineFunctionInfo: {}
body: |
; CHECK-LABEL: name: non_masked_load
; CHECK: bb.0.entry:
; CHECK: successors: %bb.1(0x80000000)
; CHECK: liveins: $lr, $r0, $r1, $r2
; CHECK: tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr
; CHECK: t2IT 0, 2, implicit-def $itstate
; CHECK: renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate
; CHECK: renamable $r0 = tUXTB killed renamable $r0, 0, $cpsr, implicit killed $r0, implicit $itstate
; CHECK: tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate
; CHECK: frame-setup tPUSH 14, $noreg, killed $lr, implicit-def $sp, implicit $sp
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8
; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4
; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8
; CHECK: dead $r7 = frame-setup tMOVr $sp, 14, $noreg
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_register $r7
; CHECK: renamable $r3 = t2ADDri renamable $r2, 15, 14, $noreg, $noreg
; CHECK: renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
; CHECK: renamable $r3 = t2BICri killed renamable $r3, 15, 14, $noreg, $noreg
; CHECK: renamable $r12 = t2SUBri killed renamable $r3, 16, 14, $noreg, $noreg
; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r3, renamable $r12, 35, 14, $noreg, $noreg
; CHECK: renamable $r3 = t2LSRri killed renamable $r12, 4, 14, $noreg, $noreg
; CHECK: renamable $r3 = t2SUBrs renamable $r2, killed renamable $r3, 34, 14, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.1.vector.body:
; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000)
; CHECK: liveins: $lr, $q0, $r0, $r1, $r2, $r3
; CHECK: renamable $vpr = MVE_VCTP8 renamable $r2, 0, $noreg
; CHECK: $q1 = MVE_VORR killed $q0, killed $q0, 0, $noreg, undef $q1
; CHECK: MVE_VPST 2, implicit $vpr
; CHECK: renamable $r1, renamable $q0 = MVE_VLDRBU8_post killed renamable $r1, 16, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv2022, align 1)
; CHECK: renamable $r0, renamable $q2 = MVE_VLDRBU8_post killed renamable $r0, 16, 1, $noreg :: (load 16 from %ir.lsr.iv19, align 1)
; CHECK: renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 16, 14, $noreg
; CHECK: renamable $q2 = MVE_VADDi8 killed renamable $q2, renamable $q1, 0, $noreg, undef renamable $q2
; CHECK: renamable $q0 = MVE_VADDi8 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0
; CHECK: $lr = t2LEUpdate killed renamable $lr, %bb.1
; CHECK: bb.2.middle.block:
; CHECK: liveins: $q0, $q1, $r3
; CHECK: renamable $vpr = MVE_VCTP8 killed renamable $r3, 0, $noreg
; CHECK: renamable $q0 = MVE_VPSEL killed renamable $q0, killed renamable $q1, 0, killed renamable $vpr
; CHECK: renamable $r0 = MVE_VADDVu8no_acc killed renamable $q0, 0, $noreg
; CHECK: $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r7, def $lr
; CHECK: renamable $r0 = tUXTB killed renamable $r0, 14, $noreg
; CHECK: tBX_RET 14, $noreg, implicit killed $r0
bb.0.entry:
successors: %bb.1(0x80000000)
liveins: $r0, $r1, $r2, $lr
tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr
t2IT 0, 2, implicit-def $itstate
renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate
renamable $r0 = tUXTB killed renamable $r0, 0, $cpsr, implicit killed $r0, implicit $itstate
tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate
frame-setup tPUSH 14, $noreg, killed $lr, implicit-def $sp, implicit $sp
frame-setup CFI_INSTRUCTION def_cfa_offset 8
frame-setup CFI_INSTRUCTION offset $lr, -4
frame-setup CFI_INSTRUCTION offset $r7, -8
$r7 = frame-setup tMOVr $sp, 14, $noreg
frame-setup CFI_INSTRUCTION def_cfa_register $r7
renamable $r3 = t2ADDri renamable $r2, 15, 14, $noreg, $noreg
renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
renamable $r3 = t2BICri killed renamable $r3, 15, 14, $noreg, $noreg
renamable $r12 = t2SUBri killed renamable $r3, 16, 14, $noreg, $noreg
renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg
renamable $lr = nuw nsw t2ADDrs killed renamable $r3, renamable $r12, 35, 14, $noreg, $noreg
renamable $r3 = t2LSRri killed renamable $r12, 4, 14, $noreg, $noreg
renamable $r3 = t2SUBrs renamable $r2, killed renamable $r3, 34, 14, $noreg, $noreg
t2DoLoopStart renamable $lr
bb.1.vector.body:
successors: %bb.1(0x7c000000), %bb.2(0x04000000)
liveins: $lr, $q0, $r0, $r1, $r2, $r3
renamable $vpr = MVE_VCTP8 renamable $r2, 0, $noreg
$q1 = MVE_VORR killed $q0, $q0, 0, $noreg, undef $q1
MVE_VPST 2, implicit $vpr
renamable $r1, renamable $q0 = MVE_VLDRBU8_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv2022, align 1)
renamable $r0, renamable $q2 = MVE_VLDRBU8_post killed renamable $r0, 16, 1, $noreg :: (load 16 from %ir.lsr.iv19, align 1)
renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 16, 14, $noreg
renamable $q2 = MVE_VADDi8 killed renamable $q2, renamable $q1, 0, $noreg, undef renamable $q2
renamable $lr = t2LoopDec killed renamable $lr, 1
renamable $q0 = MVE_VADDi8 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0
t2LoopEnd renamable $lr, %bb.1, implicit-def dead $cpsr
tB %bb.2, 14, $noreg
bb.2.middle.block:
liveins: $q0, $q1, $r3
renamable $vpr = MVE_VCTP8 killed renamable $r3, 0, $noreg
renamable $q0 = MVE_VPSEL killed renamable $q0, killed renamable $q1, 0, killed renamable $vpr
renamable $r0 = MVE_VADDVu8no_acc killed renamable $q0, 0, $noreg
$sp = t2LDMIA_UPD $sp, 14, $noreg, def $r7, def $lr
renamable $r0 = tUXTB killed renamable $r0, 14, $noreg
tBX_RET 14, $noreg, implicit killed $r0
...

llvm/test/CodeGen/Thumb2/LowOverheadLoops/non-masked-store.mir

  • This file was added.
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - --verify-machineinstrs | FileCheck %s
--- |
define dso_local arm_aapcs_vfpcc void @non_masked_store(i8* noalias nocapture %res, i8* nocapture readonly %a, i8* nocapture readonly %b, i32 %N) {
entry:
%cmp10 = icmp eq i32 %N, 0
%0 = add i32 %N, 15
%1 = lshr i32 %0, 4
%2 = shl nuw i32 %1, 4
%3 = add i32 %2, -16
%4 = lshr i32 %3, 4
%5 = add nuw nsw i32 %4, 1
br i1 %cmp10, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
call void @llvm.set.loop.iterations.i32(i32 %5)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%lsr.iv19 = phi i8* [ %scevgep20, %vector.body ], [ %res, %vector.ph ]
%lsr.iv16 = phi i8* [ %scevgep17, %vector.body ], [ %b, %vector.ph ]
%lsr.iv = phi i8* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
%6 = phi i32 [ %5, %vector.ph ], [ %11, %vector.body ]
%7 = phi i32 [ %N, %vector.ph ], [ %9, %vector.body ]
%lsr.iv1921 = bitcast i8* %lsr.iv19 to <16 x i8>*
%lsr.iv1618 = bitcast i8* %lsr.iv16 to <16 x i8>*
%lsr.iv15 = bitcast i8* %lsr.iv to <16 x i8>*
%8 = call <16 x i1> @llvm.arm.mve.vctp8(i32 %7)
%9 = sub i32 %7, 16
%wide.masked.load = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %lsr.iv15, i32 1, <16 x i1> %8, <16 x i8> undef)
%wide.masked.load14 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %lsr.iv1618, i32 1, <16 x i1> %8, <16 x i8> undef)
%10 = add <16 x i8> %wide.masked.load14, %wide.masked.load
store <16 x i8> %10, <16 x i8>* %lsr.iv1921
%scevgep = getelementptr i8, i8* %lsr.iv, i32 16
%scevgep17 = getelementptr i8, i8* %lsr.iv16, i32 16
%scevgep20 = getelementptr i8, i8* %lsr.iv19, i32 16
%11 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %6, i32 1)
%12 = icmp ne i32 %11, 0
br i1 %12, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
declare <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>*, i32 immarg, <16 x i1>, <16 x i8>)
declare void @llvm.masked.store.v16i8.p0v16i8(<16 x i8>, <16 x i8>*, i32 immarg, <16 x i1>)
declare void @llvm.set.loop.iterations.i32(i32)
declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
declare <16 x i1> @llvm.arm.mve.vctp8(i32)
...
---
name: non_masked_store
alignment: 2
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
failedISel: false
tracksRegLiveness: true
hasWinCFI: false
registers: []
liveins:
- { reg: '$r0', virtual-reg: '' }
- { reg: '$r1', virtual-reg: '' }
- { reg: '$r2', virtual-reg: '' }
- { reg: '$r3', virtual-reg: '' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 8
offsetAdjustment: 0
maxAlignment: 4
adjustsStack: false
hasCalls: false
stackProtector: ''
maxCallFrameSize: 0
cvBytesOfCalleeSavedRegisters: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
localFrameSize: 0
savePoint: ''
restorePoint: ''
fixedStack: []
stack:
- { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
- { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites: []
constants: []
machineFunctionInfo: {}
body: |
; CHECK-LABEL: name: non_masked_store
; CHECK: bb.0.entry:
; CHECK: successors: %bb.1(0x80000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3
; CHECK: frame-setup tPUSH 14, $noreg, killed $lr, implicit-def $sp, implicit $sp
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8
; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4
; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8
; CHECK: dead $r7 = frame-setup tMOVr $sp, 14, $noreg
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_register $r7
; CHECK: tCMPi8 renamable $r3, 0, 14, $noreg, implicit-def $cpsr
; CHECK: t2IT 0, 8, implicit-def $itstate
; CHECK: tPOP_RET 0, killed $cpsr, def $r7, def $pc, implicit killed $itstate
; CHECK: renamable $r12 = t2ADDri renamable $r3, 15, 14, $noreg, $noreg
; CHECK: renamable $lr = t2MOVi 1, 14, $noreg, $noreg
; CHECK: renamable $r12 = t2BICri killed renamable $r12, 15, 14, $noreg, $noreg
; CHECK: renamable $r12 = t2SUBri killed renamable $r12, 16, 14, $noreg, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 35, 14, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.1.vector.body:
; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3
; CHECK: renamable $vpr = MVE_VCTP8 renamable $r3, 0, $noreg
; CHECK: renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 16, 14, $noreg
; CHECK: MVE_VPST 4, implicit $vpr
; CHECK: renamable $r1, renamable $q0 = MVE_VLDRBU8_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv15, align 1)
; CHECK: renamable $r2, renamable $q1 = MVE_VLDRBU8_post killed renamable $r2, 16, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv1618, align 1)
; CHECK: renamable $q0 = MVE_VADDi8 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
; CHECK: renamable $r0 = MVE_VSTRBU8_post killed renamable $q0, killed renamable $r0, 16, 1, $noreg :: (store 16 into %ir.lsr.iv1921, align 1)
; CHECK: $lr = t2LEUpdate killed renamable $lr, %bb.1
; CHECK: bb.2.for.cond.cleanup:
; CHECK: tPOP_RET 14, $noreg, def $r7, def $pc
bb.0.entry:
successors: %bb.1(0x80000000)
liveins: $r0, $r1, $r2, $r3, $lr
frame-setup tPUSH 14, $noreg, killed $lr, implicit-def $sp, implicit $sp
frame-setup CFI_INSTRUCTION def_cfa_offset 8
frame-setup CFI_INSTRUCTION offset $lr, -4
frame-setup CFI_INSTRUCTION offset $r7, -8
$r7 = frame-setup tMOVr $sp, 14, $noreg
frame-setup CFI_INSTRUCTION def_cfa_register $r7
tCMPi8 renamable $r3, 0, 14, $noreg, implicit-def $cpsr
t2IT 0, 8, implicit-def $itstate
tPOP_RET 0, killed $cpsr, def $r7, def $pc, implicit killed $itstate
renamable $r12 = t2ADDri renamable $r3, 15, 14, $noreg, $noreg
renamable $lr = t2MOVi 1, 14, $noreg, $noreg
renamable $r12 = t2BICri killed renamable $r12, 15, 14, $noreg, $noreg
renamable $r12 = t2SUBri killed renamable $r12, 16, 14, $noreg, $noreg
renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 35, 14, $noreg, $noreg
t2DoLoopStart renamable $lr
bb.1.vector.body:
successors: %bb.1(0x7c000000), %bb.2(0x04000000)
liveins: $lr, $r0, $r1, $r2, $r3
renamable $vpr = MVE_VCTP8 renamable $r3, 0, $noreg
renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 16, 14, $noreg
MVE_VPST 4, implicit $vpr
renamable $r1, renamable $q0 = MVE_VLDRBU8_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv15, align 1)
renamable $r2, renamable $q1 = MVE_VLDRBU8_post killed renamable $r2, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1618, align 1)
renamable $lr = t2LoopDec killed renamable $lr, 1
renamable $q0 = MVE_VADDi8 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
renamable $r0 = MVE_VSTRBU8_post killed renamable $q0, killed renamable $r0, 16, 1, $noreg :: (store 16 into %ir.lsr.iv1921, align 1)
t2LoopEnd renamable $lr, %bb.1, implicit-def dead $cpsr
tB %bb.2, 14, $noreg
bb.2.for.cond.cleanup:
tPOP_RET 14, $noreg, def $r7, def $pc
...