[RDA] Skip debug values

[samparker]

Summary

Skip debug instructions when iterating through a block to find uses.

[samparker]

Using isDebugInstr instead.

[SjoerdMeijer]

Looks like a straightforward fix to me as top-level function processBasicBlock() skips over debug instructions, and this is consistent with that.

Just one question, one nit: the test case looks big to me, would it be easy to reduce it?

[samparker]

Reduced test case.

[SjoerdMeijer]

Thanks, LGTM

llvm/lib/CodeGen/ReachingDefAnalysis.cpp

ReachingDefAnalysis::getClearance(MachineInstr *MI, MCPhysReg PhysReg) const {
   return InstIds.lookup(MI) - getReachingDef(MI, PhysReg);
 }
 
 void ReachingDefAnalysis::getReachingLocalUses(MachineInstr *Def, int PhysReg,
     SmallPtrSetImpl<MachineInstr*> &Uses) const {
   MachineBasicBlock *MBB = Def->getParent();
   MachineBasicBlock::iterator MI = MachineBasicBlock::iterator(Def);
   while (++MI != MBB->end()) {
+    if (MI->isDebugInstr())
+      continue;
+
     // If/when we find a new reaching def, we know that there's no more uses
     // of 'Def'.
     if (getReachingMIDef(&*MI, PhysReg) != Def)
       return;
 
     for (auto &MO : MI->operands()) {
       if (!MO.isReg() || !MO.isUse() || MO.getReg() != PhysReg)
         continue;
 
       Uses.insert(&*MI);
       if (MO.isKill())
         return;
     }
   }
 }
 
 bool
 ReachingDefAnalysis::getLiveInUses(MachineBasicBlock *MBB, int PhysReg,
                                    SmallPtrSetImpl<MachineInstr*> &Uses) const {
   for (auto &MI : *MBB) {
+    if (MI.isDebugInstr())
+      continue;
     for (auto &MO : MI.operands()) {
       if (!MO.isReg() || !MO.isUse() || MO.getReg() != PhysReg)
         continue;
       if (getReachingDef(&MI, PhysReg) >= 0)
         return false;
       Uses.insert(&MI);
     }
   }

llvm/test/CodeGen/Thumb2/LowOverheadLoops/matrix-debug.mir

+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=thumbv8.1m.main -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s
+
+--- |
+  define dso_local arm_aapcscc void @test_debug(i32 %d, i32* %e, i16* nocapture readonly %k, i16* nocapture readonly %l) !dbg !15 {
+  entry:
+    call void @llvm.dbg.value(metadata i32 %d, metadata !23, metadata !DIExpression()), !dbg !32
+    call void @llvm.dbg.value(metadata i32* %e, metadata !24, metadata !DIExpression()), !dbg !32
+    call void @llvm.dbg.value(metadata i16* %k, metadata !25, metadata !DIExpression()), !dbg !32
+    call void @llvm.dbg.value(metadata i16* %l, metadata !26, metadata !DIExpression()), !dbg !32
+    call void @llvm.dbg.value(metadata i16 0, metadata !29, metadata !DIExpression()), !dbg !32
+    %call = tail call arm_aapcscc signext i16 @get_input(i32 %d, i32* %e, i16 signext 0) #4, !dbg !33
+    call void @llvm.dbg.value(metadata i16 %call, metadata !28, metadata !DIExpression()), !dbg !32
+    call void @llvm.dbg.value(metadata i32 0, metadata !30, metadata !DIExpression()), !dbg !32
+    %cmp30 = icmp sgt i32 %d, 0, !dbg !34
+    br i1 %cmp30, label %for.cond1.preheader.us.preheader, label %for.end11, !dbg !37
+
+  for.cond1.preheader.us.preheader:                 ; preds = %entry
+    %0 = shl i32 %d, 1, !dbg !37
+    br label %for.cond1.preheader.us, !dbg !37
+
+  for.cond1.preheader.us:                           ; preds = %for.cond1.preheader.us.preheader, %for.cond1.for.inc9_crit_edge.us
+    %lsr.iv2 = phi i16* [ %k, %for.cond1.preheader.us.preheader ], [ %9, %for.cond1.for.inc9_crit_edge.us ]
+    %i.031.us = phi i32 [ %inc10.us, %for.cond1.for.inc9_crit_edge.us ], [ 0, %for.cond1.preheader.us.preheader ]
+    call void @llvm.dbg.value(metadata i32 %i.031.us, metadata !30, metadata !DIExpression()), !dbg !32
+    call void @llvm.dbg.value(metadata i32 0, metadata !31, metadata !DIExpression()), !dbg !32
+    %arrayidx7.us = getelementptr inbounds i32, i32* %e, i32 %i.031.us, !dbg !38
+    %arrayidx7.promoted.us = load i32, i32* %arrayidx7.us, align 4, !dbg !41
+    call void @llvm.set.loop.iterations.i32(i32 %d), !dbg !46
+    br label %for.body3.us, !dbg !46
+
+  for.body3.us:                                     ; preds = %for.body3.us, %for.cond1.preheader.us
+    %lsr.iv5 = phi i16* [ %scevgep6, %for.body3.us ], [ %lsr.iv2, %for.cond1.preheader.us ], !dbg !32
+    %lsr.iv1 = phi i16* [ %scevgep, %for.body3.us ], [ %l, %for.cond1.preheader.us ], !dbg !32
+    %add829.us = phi i32 [ %arrayidx7.promoted.us, %for.cond1.preheader.us ], [ %add8.us, %for.body3.us ], !dbg !32
+    %1 = phi i32 [ %d, %for.cond1.preheader.us ], [ %4, %for.body3.us ], !dbg !32
+    call void @llvm.dbg.value(metadata i32 undef, metadata !31, metadata !DIExpression()), !dbg !32
+    %2 = load i16, i16* %lsr.iv5, align 2, !dbg !47
+    %conv.us = sext i16 %2 to i32, !dbg !47
+    %3 = load i16, i16* %lsr.iv1, align 2, !dbg !50
+    %conv5.us = sext i16 %3 to i32, !dbg !50
+    %mul6.us = mul nsw i32 %conv5.us, %conv.us, !dbg !51
+    %add8.us = add nsw i32 %mul6.us, %add829.us, !dbg !41
+    call void @llvm.dbg.value(metadata i32 undef, metadata !31, metadata !DIExpression(DW_OP_plus_uconst, 1, DW_OP_stack_value)), !dbg !32
+    %scevgep = getelementptr i16, i16* %lsr.iv1, i32 1, !dbg !52
+    %scevgep6 = getelementptr i16, i16* %lsr.iv5, i32 1, !dbg !52
+    %4 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %1, i32 1), !dbg !46
+    %5 = icmp ne i32 %4, 0, !dbg !46
+    br i1 %5, label %for.body3.us, label %for.cond1.for.inc9_crit_edge.us, !dbg !46, !llvm.loop !53
+
+  for.cond1.for.inc9_crit_edge.us:                  ; preds = %for.body3.us
+    %6 = bitcast i16* %lsr.iv2 to i1*
+    %sunkaddr = mul i32 %i.031.us, 4, !dbg !41
+    %7 = bitcast i32* %e to i8*, !dbg !41
+    %sunkaddr7 = getelementptr inbounds i8, i8* %7, i32 %sunkaddr, !dbg !41
+    %8 = bitcast i8* %sunkaddr7 to i32*, !dbg !41
+    store i32 %add8.us, i32* %8, align 4, !dbg !41
+    %inc10.us = add nuw nsw i32 %i.031.us, 1, !dbg !55
+    call void @llvm.dbg.value(metadata i32 %inc10.us, metadata !30, metadata !DIExpression()), !dbg !32
+    %scevgep4 = getelementptr i1, i1* %6, i32 %0, !dbg !37
+    %9 = bitcast i1* %scevgep4 to i16*, !dbg !37
+    %exitcond33 = icmp eq i32 %inc10.us, %d, !dbg !34
+    br i1 %exitcond33, label %for.end11, label %for.cond1.preheader.us, !dbg !37, !llvm.loop !56
+
+  for.end11:                                        ; preds = %for.cond1.for.inc9_crit_edge.us, %entry
+    ret void, !dbg !58
+  }
+  declare !dbg !4 dso_local arm_aapcscc signext i16 @get_input(i32, i32*, i16 signext)
+  declare void @llvm.dbg.value(metadata, metadata, metadata)
+  declare void @llvm.set.loop.iterations.i32(i32)
+  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
+
+  !llvm.dbg.cu = !{!0}
+  !llvm.module.flags = !{!10, !11, !12, !13}
+  !llvm.ident = !{!14}
+
+  !0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 10.0.0 (https://github.com/llvm/llvm-project.git 9c91d79dadc660cb6a0ec736389341debd8cd118)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, retainedTypes: !3, splitDebugInlining: false, nameTableKind: None)
+  !1 = !DIFile(filename: "matrix-hang.c", directory: "/home/sampar01/src/tests/tail-predication")
+  !2 = !{}
+  !3 = !{!4}
+  !4 = !DISubprogram(name: "get_input", scope: !1, file: !1, line: 4, type: !5, flags: DIFlagPrototyped, spFlags: DISPFlagOptimized, retainedNodes: !2)
+  !5 = !DISubroutineType(types: !6)
+  !6 = !{!7, !8, !9, !7}
+  !7 = !DIBasicType(name: "short", size: 16, encoding: DW_ATE_signed)
+  !8 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+  !9 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !8, size: 32)
+  !10 = !{i32 7, !"Dwarf Version", i32 4}
+  !11 = !{i32 2, !"Debug Info Version", i32 3}
+  !12 = !{i32 1, !"wchar_size", i32 4}
+  !13 = !{i32 1, !"min_enum_size", i32 4}
+  !14 = !{!"clang version 10.0.0 (https://github.com/llvm/llvm-project.git 9c91d79dadc660cb6a0ec736389341debd8cd118)"}
+  !15 = distinct !DISubprogram(name: "test_debug", scope: !1, file: !1, line: 6, type: !16, scopeLine: 6, flags: DIFlagPrototyped | DIFlagAllCallsDescribed, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !22)
+  !16 = !DISubroutineType(types: !17)
+  !17 = !{null, !18, !19, !21, !21}
+  !18 = !DIDerivedType(tag: DW_TAG_typedef, name: "a", file: !1, line: 1, baseType: !8)
+  !19 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !20, size: 32)
+  !20 = !DIDerivedType(tag: DW_TAG_typedef, name: "b", file: !1, line: 2, baseType: !8)
+  !21 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !7, size: 32)
+  !22 = !{!23, !24, !25, !26, !27, !28, !29, !30, !31}
+  !23 = !DILocalVariable(name: "d", arg: 1, scope: !15, file: !1, line: 6, type: !18)
+  !24 = !DILocalVariable(name: "e", arg: 2, scope: !15, file: !1, line: 6, type: !19)
+  !25 = !DILocalVariable(name: "k", arg: 3, scope: !15, file: !1, line: 6, type: !21)
+  !26 = !DILocalVariable(name: "l", arg: 4, scope: !15, file: !1, line: 6, type: !21)
+  !27 = !DILocalVariable(name: "m", scope: !15, file: !1, line: 7, type: !7)
+  !28 = !DILocalVariable(name: "n", scope: !15, file: !1, line: 7, type: !7)
+  !29 = !DILocalVariable(name: "clipval", scope: !15, file: !1, line: 7, type: !7)
+  !30 = !DILocalVariable(name: "i", scope: !15, file: !1, line: 9, type: !18)
+  !31 = !DILocalVariable(name: "j", scope: !15, file: !1, line: 9, type: !18)
+  !32 = !DILocation(line: 0, scope: !15)
+  !33 = !DILocation(line: 8, column: 7, scope: !15)
+  !34 = !DILocation(line: 10, column: 17, scope: !35)
+  !35 = distinct !DILexicalBlock(scope: !36, file: !1, line: 10, column: 3)
+  !36 = distinct !DILexicalBlock(scope: !15, file: !1, line: 10, column: 3)
+  !37 = !DILocation(line: 10, column: 3, scope: !36)
+  !38 = !DILocation(line: 0, scope: !39)
+  !39 = distinct !DILexicalBlock(scope: !40, file: !1, line: 11, column: 5)
+  !40 = distinct !DILexicalBlock(scope: !35, file: !1, line: 11, column: 5)
+  !41 = !DILocation(line: 12, column: 12, scope: !39)
+  !42 = !{!43, !43, i64 0}
+  !43 = !{!"int", !44, i64 0}
+  !44 = !{!"omnipotent char", !45, i64 0}
+  !45 = !{!"Simple C/C++ TBAA"}
+  !46 = !DILocation(line: 11, column: 5, scope: !40)
+  !47 = !DILocation(line: 12, column: 15, scope: !39)
+  !48 = !{!49, !49, i64 0}
+  !49 = !{!"short", !44, i64 0}
+  !50 = !DILocation(line: 12, column: 30, scope: !39)
+  !51 = !DILocation(line: 12, column: 28, scope: !39)
+  !52 = !DILocation(line: 11, column: 19, scope: !39)
+  !53 = distinct !{!53, !46, !54}
+  !54 = !DILocation(line: 12, column: 33, scope: !40)
+  !55 = !DILocation(line: 10, column: 23, scope: !35)
+  !56 = distinct !{!56, !37, !57}
+  !57 = !DILocation(line: 12, column: 33, scope: !36)
+  !58 = !DILocation(line: 13, column: 1, scope: !15)
+
+...
+---
+name:            test_debug
+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:       32
+  offsetAdjustment: -24
+  maxAlignment:    4
+  adjustsStack:    true
+  hasCalls:        true
+  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: '' }
+  - { id: 2, name: '', type: spill-slot, offset: -12, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r6', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 3, name: '', type: spill-slot, offset: -16, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r5', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 4, name: '', type: spill-slot, offset: -20, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r4', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 5, name: '', type: spill-slot, offset: -24, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r10', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 6, name: '', type: spill-slot, offset: -28, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r9', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 7, name: '', type: spill-slot, offset: -32, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r8', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+callSites:       []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  ; CHECK-LABEL: name: test_debug
+  ; CHECK: bb.0.entry:
+  ; CHECK:   successors: %bb.1(0x50000000), %bb.5(0x30000000)
+  ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r4, $r5, $r6, $lr, $r8, $r9, $r10
+  ; CHECK:   DBG_VALUE $r0, $noreg, !23, !DIExpression(), debug-location !32
+  ; CHECK:   DBG_VALUE $r1, $noreg, !24, !DIExpression(), debug-location !32
+  ; CHECK:   DBG_VALUE $r2, $noreg, !25, !DIExpression(), debug-location !32
+  ; CHECK:   DBG_VALUE $r3, $noreg, !26, !DIExpression(), debug-location !32
+  ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r4, killed $r5, killed $r6, killed $lr, implicit-def $sp, implicit $sp
+  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 20
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r6, -12
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r5, -16
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r4, -20
+  ; CHECK:   $r7 = frame-setup tADDrSPi $sp, 3, 14, $noreg
+  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa $r7, 8
+  ; CHECK:   $sp = frame-setup t2STMDB_UPD $sp, 14, $noreg, killed $r8, killed $r9, killed $r10
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r10, -24
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r9, -28
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r8, -32
+  ; CHECK:   $r5 = tMOVr killed $r2, 14, $noreg
+  ; CHECK:   DBG_VALUE $r5, $noreg, !25, !DIExpression(), debug-location !32
+  ; CHECK:   $r2, dead $cpsr = tMOVi8 0, 14, $noreg, debug-location !33
+  ; CHECK:   $r8 = tMOVr killed $r3, 14, $noreg
+  ; CHECK:   DBG_VALUE $r8, $noreg, !26, !DIExpression(), debug-location !32
+  ; CHECK:   $r9 = tMOVr $r1, 14, $noreg
+  ; CHECK:   DBG_VALUE $r9, $noreg, !24, !DIExpression(), debug-location !32
+  ; CHECK:   $r10 = tMOVr $r0, 14, $noreg
+  ; CHECK:   DBG_VALUE 0, $noreg, !29, !DIExpression(), debug-location !32
+  ; CHECK:   DBG_VALUE $r10, $noreg, !23, !DIExpression(), debug-location !32
+  ; CHECK:   tBL 14, $noreg, @get_input, csr_aapcs, implicit-def dead $lr, implicit $sp, implicit killed $r0, implicit killed $r1, implicit killed $r2, implicit-def $sp, implicit-def dead $r0, debug-location !33
+  ; CHECK:   DBG_VALUE 0, $noreg, !30, !DIExpression(), debug-location !32
+  ; CHECK:   DBG_VALUE $noreg, $noreg, !28, !DIExpression(), debug-location !32
+  ; CHECK:   t2CMPri renamable $r10, 1, 14, $noreg, implicit-def $cpsr, debug-location !37
+  ; CHECK:   tBcc %bb.5, 11, killed $cpsr, debug-location !37
+  ; CHECK: bb.1.for.cond1.preheader.us.preheader:
+  ; CHECK:   successors: %bb.2(0x80000000)
+  ; CHECK:   liveins: $r5, $r8, $r9, $r10
+  ; CHECK:   renamable $r12 = t2LSLri renamable $r10, 1, 14, $noreg, $noreg, debug-location !37
+  ; CHECK:   renamable $r1, dead $cpsr = tMOVi8 0, 14, $noreg
+  ; CHECK: bb.2.for.cond1.preheader.us:
+  ; CHECK:   successors: %bb.3(0x80000000)
+  ; CHECK:   liveins: $r1, $r5, $r8, $r9, $r10, $r12
+  ; CHECK:   DBG_VALUE $r1, $noreg, !30, !DIExpression(), debug-location !32
+  ; CHECK:   DBG_VALUE 0, $noreg, !31, !DIExpression(), debug-location !32
+  ; CHECK:   renamable $r2 = t2LDRs renamable $r9, renamable $r1, 2, 14, $noreg, debug-location !41 :: (load 4 from %ir.arrayidx7.us)
+  ; CHECK:   $r3 = tMOVr $r5, 14, $noreg, debug-location !32
+  ; CHECK:   $r0 = tMOVr $r8, 14, $noreg, debug-location !32
+  ; CHECK:   $lr = t2DLS renamable $r10, debug-location !32
+  ; CHECK: bb.3.for.body3.us:
+  ; CHECK:   successors: %bb.3(0x7c000000), %bb.4(0x04000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r5, $r8, $r9, $r10, $r12
+  ; CHECK:   DBG_VALUE $noreg, $noreg, !31, !DIExpression(), debug-location !32
+  ; CHECK:   renamable $r6, renamable $r3 = t2LDRSH_POST killed renamable $r3, 2, 14, $noreg, debug-location !43 :: (load 2 from %ir.lsr.iv5)
+  ; CHECK:   renamable $r4, renamable $r0 = t2LDRSH_POST killed renamable $r0, 2, 14, $noreg, debug-location !44 :: (load 2 from %ir.lsr.iv1)
+  ; CHECK:   renamable $r2 = nsw t2SMLABB killed renamable $r4, killed renamable $r6, killed renamable $r2, 14, $noreg, debug-location !41
+  ; CHECK:   DBG_VALUE $noreg, $noreg, !31, !DIExpression(DW_OP_plus_uconst, 1, DW_OP_stack_value), debug-location !32
+  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.3, debug-location !42
+  ; CHECK: bb.4.for.cond1.for.inc9_crit_edge.us:
+  ; CHECK:   successors: %bb.5(0x04000000), %bb.2(0x7c000000)
+  ; CHECK:   liveins: $r1, $r2, $r5, $r8, $r9, $r10, $r12
+  ; CHECK:   t2STRs killed renamable $r2, renamable $r9, renamable $r1, 2, 14, $noreg, debug-location !41 :: (store 4 into %ir.8)
+  ; CHECK:   renamable $r1, dead $cpsr = nuw nsw tADDi8 killed renamable $r1, 1, 14, $noreg, debug-location !49
+  ; CHECK:   DBG_VALUE $r1, $noreg, !30, !DIExpression(), debug-location !32
+  ; CHECK:   renamable $r5 = tADDhirr killed renamable $r5, renamable $r12, 14, $noreg, debug-location !37
+  ; CHECK:   tCMPhir renamable $r1, renamable $r10, 14, $noreg, implicit-def $cpsr, debug-location !37
+  ; CHECK:   tBcc %bb.2, 1, killed $cpsr, debug-location !37
+  ; CHECK: bb.5.for.end11:
+  ; CHECK:   $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r8, def $r9, def $r10, debug-location !52
+  ; CHECK:   tPOP_RET 14, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc, debug-location !52
+  bb.0.entry:
+    successors: %bb.1(0x50000000), %bb.5(0x30000000)
+    liveins: $r0, $r1, $r2, $r3, $r4, $r5, $r6, $lr, $r8, $r9, $r10
+
+    DBG_VALUE $r0, $noreg, !23, !DIExpression(), debug-location !32
+    DBG_VALUE $r1, $noreg, !24, !DIExpression(), debug-location !32
+    DBG_VALUE $r2, $noreg, !25, !DIExpression(), debug-location !32
+    DBG_VALUE $r3, $noreg, !26, !DIExpression(), debug-location !32
+    frame-setup tPUSH 14, $noreg, killed $r4, killed $r5, killed $r6, killed $lr, implicit-def $sp, implicit $sp
+    frame-setup CFI_INSTRUCTION def_cfa_offset 20
+    frame-setup CFI_INSTRUCTION offset $lr, -4
+    frame-setup CFI_INSTRUCTION offset $r7, -8
+    frame-setup CFI_INSTRUCTION offset $r6, -12
+    frame-setup CFI_INSTRUCTION offset $r5, -16
+    frame-setup CFI_INSTRUCTION offset $r4, -20
+    $r7 = frame-setup tADDrSPi $sp, 3, 14, $noreg
+    frame-setup CFI_INSTRUCTION def_cfa $r7, 8
+    $sp = frame-setup t2STMDB_UPD $sp, 14, $noreg, killed $r8, killed $r9, killed $r10
+    frame-setup CFI_INSTRUCTION offset $r10, -24
+    frame-setup CFI_INSTRUCTION offset $r9, -28
+    frame-setup CFI_INSTRUCTION offset $r8, -32
+    $r5 = tMOVr killed $r2, 14, $noreg
+    DBG_VALUE $r5, $noreg, !25, !DIExpression(), debug-location !32
+    $r2, dead $cpsr = tMOVi8 0, 14, $noreg, debug-location !33
+    $r8 = tMOVr killed $r3, 14, $noreg
+    DBG_VALUE $r8, $noreg, !26, !DIExpression(), debug-location !32
+    $r9 = tMOVr $r1, 14, $noreg
+    DBG_VALUE $r9, $noreg, !24, !DIExpression(), debug-location !32
+    $r10 = tMOVr $r0, 14, $noreg
+    DBG_VALUE 0, $noreg, !29, !DIExpression(), debug-location !32
+    DBG_VALUE $r10, $noreg, !23, !DIExpression(), debug-location !32
+    tBL 14, $noreg, @get_input, csr_aapcs, implicit-def dead $lr, implicit $sp, implicit killed $r0, implicit killed $r1, implicit killed $r2, implicit-def $sp, implicit-def dead $r0, debug-location !33
+    DBG_VALUE 0, $noreg, !30, !DIExpression(), debug-location !32
+    DBG_VALUE $noreg, $noreg, !28, !DIExpression(), debug-location !32
+    t2CMPri renamable $r10, 1, 14, $noreg, implicit-def $cpsr, debug-location !37
+    tBcc %bb.5, 11, killed $cpsr, debug-location !37
+
+  bb.1.for.cond1.preheader.us.preheader:
+    successors: %bb.2(0x80000000)
+    liveins: $r5, $r8, $r9, $r10
+
+    renamable $r12 = t2LSLri renamable $r10, 1, 14, $noreg, $noreg, debug-location !37
+    renamable $r1, dead $cpsr = tMOVi8 0, 14, $noreg
+
+  bb.2.for.cond1.preheader.us:
+    successors: %bb.3(0x80000000)
+    liveins: $r1, $r5, $r8, $r9, $r10, $r12
+
+    DBG_VALUE $r1, $noreg, !30, !DIExpression(), debug-location !32
+    DBG_VALUE 0, $noreg, !31, !DIExpression(), debug-location !32
+    renamable $r2 = t2LDRs renamable $r9, renamable $r1, 2, 14, $noreg, debug-location !41 :: (load 4 from %ir.arrayidx7.us)
+    $r3 = tMOVr $r5, 14, $noreg, debug-location !32
+    $r0 = tMOVr $r8, 14, $noreg, debug-location !32
+    $lr = tMOVr $r10, 14, $noreg, debug-location !32
+    t2DoLoopStart renamable $r10, debug-location !46
+
+  bb.3.for.body3.us:
+    successors: %bb.3(0x7c000000), %bb.4(0x04000000)
+    liveins: $lr, $r0, $r1, $r2, $r3, $r5, $r8, $r9, $r10, $r12
+
+    DBG_VALUE $noreg, $noreg, !31, !DIExpression(), debug-location !32
+    renamable $r6, renamable $r3 = t2LDRSH_POST killed renamable $r3, 2, 14, $noreg, debug-location !47 :: (load 2 from %ir.lsr.iv5)
+    renamable $lr = t2LoopDec killed renamable $lr, 1, debug-location !46
+    renamable $r4, renamable $r0 = t2LDRSH_POST killed renamable $r0, 2, 14, $noreg, debug-location !50 :: (load 2 from %ir.lsr.iv1)
+    renamable $r2 = nsw t2SMLABB killed renamable $r4, killed renamable $r6, killed renamable $r2, 14, $noreg, debug-location !41
+    DBG_VALUE $noreg, $noreg, !31, !DIExpression(DW_OP_plus_uconst, 1, DW_OP_stack_value), debug-location !32
+    t2LoopEnd renamable $lr, %bb.3, implicit-def dead $cpsr, debug-location !46
+    tB %bb.4, 14, $noreg, debug-location !46
+
+  bb.4.for.cond1.for.inc9_crit_edge.us:
+    successors: %bb.5(0x04000000), %bb.2(0x7c000000)
+    liveins: $r1, $r2, $r5, $r8, $r9, $r10, $r12
+
+    t2STRs killed renamable $r2, renamable $r9, renamable $r1, 2, 14, $noreg, debug-location !41 :: (store 4 into %ir.8)
+    renamable $r1, dead $cpsr = nuw nsw tADDi8 killed renamable $r1, 1, 14, $noreg, debug-location !55
+    DBG_VALUE $r1, $noreg, !30, !DIExpression(), debug-location !32
+    renamable $r5 = tADDhirr killed renamable $r5, renamable $r12, 14, $noreg, debug-location !37
+    tCMPhir renamable $r1, renamable $r10, 14, $noreg, implicit-def $cpsr, debug-location !37
+    tBcc %bb.2, 1, killed $cpsr, debug-location !37
+
+  bb.5.for.end11:
+    $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r8, def $r9, def $r10, debug-location !58
+    tPOP_RET 14, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc, debug-location !58
+
+...