# RUN: llc %s -run-pass x86-avoid-SFB -mtriple=x86_64-unknown-linux-gnu -o - | FileCheck %s
#
# This was generated from:
#
# using alpha = float __attribute__((ext_vector_type(4)));
#
# void bravo(alpha * __restrict__ p1, alpha * __restrict__ p2) {
#   char *p3 = (char *)p1;
#   if (p1) {
#     *p3 = 0;
#     alpha t = *p1;
#     *p2 = t;
#   }
# }
#
# Using the command line:
# clang -g -c 1.cpp -O2 -S -emit-llvm -fno-strict-aliasing --target=x86_64-unknown-unknown -o test.ll
# llc -stop-before=x86-avoid-SFB test.ll -o before.mir
#
# The IR has been modified to include a number of debug/meta instructions between the initial store and load.
# If the code treats debug/meta instructions as normal instructions, the separation between the store and load 
# will be too great to enable the optimization.

--- |
  ; ModuleID = 'test.ll'
  source_filename = "1.cpp"
  target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
  target triple = "x86_64-unknown-unknown"
  
  ; Function Attrs: norecurse nounwind uwtable
  define dso_local void @debug(<4 x float>* noalias %p1, <4 x float>* noalias nocapture %p2) local_unnamed_addr #0 !dbg !10 {
  entry:
    call void @llvm.dbg.value(metadata <4 x float>* %p1, metadata !21, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata <4 x float>* %p2, metadata !22, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata <4 x float>* %p1, metadata !23, metadata !DIExpression()), !dbg !27
    %tobool = icmp eq <4 x float>* %p1, null, !dbg !28
    %0 = bitcast <4 x float>* %p1 to i8*, !dbg !29
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    store i8 0, i8* %0, align 1, !dbg !30
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    call void @llvm.dbg.value(metadata i8* %0, metadata !23, metadata !DIExpression()), !dbg !27
    br i1 %tobool, label %if.end, label %if.then, !dbg !31
  
  if.then:                                          ; preds = %entry
    %1 = load <4 x float>, <4 x float>* %p1, align 16, !dbg !32
    call void @llvm.dbg.value(metadata <4 x float> %1, metadata !24, metadata !DIExpression()), !dbg !33
    store <4 x float> %1, <4 x float>* %p2, align 16, !dbg !34
    br label %if.end, !dbg !35
  
  if.end:                                           ; preds = %if.then, %entry
    ret void, !dbg !36
  }

  ; Function Attrs: nounwind readnone speculatable
  declare void @llvm.dbg.value(metadata, metadata, metadata) #1
  
  ; Function Attrs: nounwind
  declare void @llvm.stackprotector(i8*, i8**) #2
  
  attributes #0 = { norecurse nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
  attributes #1 = { nounwind readnone speculatable }
  attributes #2 = { nounwind }
  
  !llvm.dbg.cu = !{!0}
  !llvm.module.flags = !{!6, !7, !8}
  !llvm.ident = !{!9}
  
  !0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "clang version 9.0.0 (https://github.com/llvm/llvm-project.git 1a0312ca0b20d16edb859065bbace75f6701c92e)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, retainedTypes: !3, nameTableKind: None)
  !1 = !DIFile(filename: "1.cpp", directory: "/mnt/c/Users/gbdawsoc/Documents/llvm/bg40969")
  !2 = !{}
  !3 = !{!4}
  !4 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !5, size: 64)
  !5 = !DIBasicType(name: "char", size: 8, encoding: DW_ATE_signed_char)
  !6 = !{i32 2, !"Dwarf Version", i32 4}
  !7 = !{i32 2, !"Debug Info Version", i32 3}
  !8 = !{i32 1, !"wchar_size", i32 4}
  !9 = !{!"clang version 9.0.0 (https://github.com/llvm/llvm-project.git 1a0312ca0b20d16edb859065bbace75f6701c92e)"}
  !10 = distinct !DISubprogram(name: "bravo", linkageName: "debug", scope: !1, file: !1, line: 4, type: !11, scopeLine: 4, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !20)
  !11 = !DISubroutineType(types: !12)
  !12 = !{null, !13, !13}
  !13 = !DIDerivedType(tag: DW_TAG_restrict_type, baseType: !14)
  !14 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !15, size: 64)
  !15 = !DIDerivedType(tag: DW_TAG_typedef, name: "alpha", file: !1, line: 2, baseType: !16)
  !16 = !DICompositeType(tag: DW_TAG_array_type, baseType: !17, size: 128, flags: DIFlagVector, elements: !18)
  !17 = !DIBasicType(name: "float", size: 32, encoding: DW_ATE_float)
  !18 = !{!19}
  !19 = !DISubrange(count: 4)
  !20 = !{!21, !22, !23, !24}
  !21 = !DILocalVariable(name: "p1", arg: 1, scope: !10, file: !1, line: 4, type: !13)
  !22 = !DILocalVariable(name: "p2", arg: 2, scope: !10, file: !1, line: 4, type: !13)
  !23 = !DILocalVariable(name: "p3", scope: !10, file: !1, line: 5, type: !4)
  !24 = !DILocalVariable(name: "t", scope: !25, file: !1, line: 8, type: !15)
  !25 = distinct !DILexicalBlock(scope: !26, file: !1, line: 6, column: 11)
  !26 = distinct !DILexicalBlock(scope: !10, file: !1, line: 6, column: 7)
  !27 = !DILocation(line: 0, scope: !10)
  !28 = !DILocation(line: 6, column: 7, scope: !26)
  !29 = !DILocation(line: 5, column: 14, scope: !10)
  !30 = !DILocation(line: 7, column: 9, scope: !25)
  !31 = !DILocation(line: 6, column: 7, scope: !10)
  !32 = !DILocation(line: 8, column: 15, scope: !25)
  !33 = !DILocation(line: 0, scope: !25)
  !34 = !DILocation(line: 9, column: 9, scope: !25)
  !35 = !DILocation(line: 10, column: 3, scope: !25)
  !36 = !DILocation(line: 11, column: 1, scope: !10)

...
---
name:            debug
alignment:       16
exposesReturnsTwice: false
legalized:       false
regBankSelected: false
selected:        false
failedISel:      false
tracksRegLiveness: true
hasWinCFI:       false
registers:       
  - { id: 0, class: gr64, preferred-register: '' }
  - { id: 1, class: gr64, preferred-register: '' }
  - { id: 2, class: vr128, preferred-register: '' }
liveins:         
  - { reg: '$rdi', virtual-reg: '%0' }
  - { reg: '$rsi', virtual-reg: '%1' }
frameInfo:       
  isFrameAddressTaken: false
  isReturnAddressTaken: false
  hasStackMap:     false
  hasPatchPoint:   false
  stackSize:       0
  offsetAdjustment: 0
  maxAlignment:    0
  adjustsStack:    false
  hasCalls:        false
  stackProtector:  ''
  maxCallFrameSize: 4294967295
  cvBytesOfCalleeSavedRegisters: 0
  hasOpaqueSPAdjustment: false
  hasVAStart:      false
  hasMustTailInVarArgFunc: false
  localFrameSize:  0
  savePoint:       ''
  restorePoint:    ''
fixedStack:      []
stack:           []
constants:       []
machineFunctionInfo: {}
body:             |
  bb.0.entry:
    successors: %bb.2(0x30000000), %bb.1(0x50000000)
    liveins: $rdi, $rsi
  
    DBG_VALUE $rdi, $noreg, !21, !DIExpression(), debug-location !27
    DBG_VALUE $rsi, $noreg, !22, !DIExpression(), debug-location !27
    DBG_VALUE $rdi, $noreg, !23, !DIExpression(), debug-location !27
    %1:gr64 = COPY $rsi
    DBG_VALUE %1, $noreg, !22, !DIExpression(), debug-location !27
    %0:gr64 = COPY $rdi
    DBG_VALUE %0, $noreg, !21, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !23, !DIExpression(), debug-location !27
    TEST64rr %0, %0, implicit-def $eflags, debug-location !28
    DBG_VALUE %0, $noreg, !23, !DIExpression(), debug-location !27
    MOV8mi %0, 1, $noreg, 0, $noreg, 0, debug-location !30 :: (store 1 into %ir.0)
    CFI_INSTRUCTION offset $r13, -123
    DBG_VALUE %0, $noreg, !21, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !23, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !21, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !23, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !21, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !23, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !21, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !23, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !21, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !23, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !21, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !23, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !21, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !23, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !21, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !23, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !21, !DIExpression(), debug-location !27
    DBG_VALUE %0, $noreg, !23, !DIExpression(), debug-location !27
    JCC_1 %bb.2, 4, implicit $eflags, debug-location !31
    JMP_1 %bb.1, debug-location !31
  
  bb.1.if.then:
    successors: %bb.2(0x80000000)
  
    %2:vr128 = MOVAPSrm %0, 1, $noreg, 0, $noreg, debug-location !32 :: (load 16 from %ir.p1)
    DBG_VALUE %2, $noreg, !24, !DIExpression(), debug-location !33
    MOVAPSmr %1, 1, $noreg, 0, $noreg, killed %2, debug-location !34 :: (store 16 into %ir.p2)
  
  bb.2.if.end:
    RET 0, debug-location !36

    ; CHECK-LABEL: name: debug
    ; CHECK: %3:gr8 = MOV8rm
    ; CHECK: MOV8mr
    ; CHECK: %4:gr64 = MOV64rm
    ; CHECK: MOV64mr
    ; CHECK: %5:gr32 = MOV32rm
    ; CHECK: MOV32mr
    ; CHECK: %6:gr16 = MOV16rm
    ; CHECK: MOV16mr
    ; CHECK: %7:gr8 = MOV8rm
    ; CHECK: MOV8mr
    ; CHECK: RET 0
...