; RUN: opt < %s -passes=loop-vectorize,transform-warning -force-vector-width=4 -S 2>&1 | FileCheck %s
; RUN: opt < %s -passes=loop-vectorize,transform-warning -force-vector-width=1 -S 2>&1 | FileCheck %s -check-prefix=NOANALYSIS
; RUN: opt < %s -passes=loop-vectorize,transform-warning -force-vector-width=4 -pass-remarks-missed='loop-vectorize' -S 2>&1 | FileCheck %s -check-prefix=MOREINFO

; CHECK-NOT: loop not vectorized: loop contains a switch statement
; CHECK-NOT: loop not vectorized: the optimizer was unable to perform the requested transformation; the transformation might be disabled or specified as part of an unsupported transformation ordering

; NOANALYSIS-NOT: remark: {{.*}}
; NOANALYSIS: loop not vectorized: the optimizer was unable to perform the requested transformation; the transformation might be disabled or specified as part of an unsupported transformation ordering

; MOREINFO-NOT: remark

; CHECK: _Z11test_switchPii
; CHECK: vector.body:
; CHECK: ret

target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"

define void @_Z11test_switchPii(ptr nocapture %A, i32 %Length) !dbg !4 {
entry:
  %cmp18 = icmp sgt i32 %Length, 0, !dbg !10
  br i1 %cmp18, label %for.body.preheader, label %for.end, !dbg !10, !llvm.loop !12

for.body.preheader:
  br label %for.body, !dbg !14

for.body:
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %for.body.preheader ]
  %arrayidx = getelementptr inbounds i32, ptr %A, i64 %indvars.iv, !dbg !14
  %0 = load i32, ptr %arrayidx, align 4, !dbg !14, !tbaa !16
  switch i32 %0, label %for.inc [
    i32 0, label %sw.bb
    i32 1, label %sw.bb3
  ], !dbg !14

sw.bb:
  %1 = trunc i64 %indvars.iv to i32, !dbg !20
  %mul = shl nsw i32 %1, 1, !dbg !20
  br label %for.inc, !dbg !22

sw.bb3:
  %2 = trunc i64 %indvars.iv to i32, !dbg !23
  store i32 %2, ptr %arrayidx, align 4, !dbg !23, !tbaa !16
  br label %for.inc, !dbg !23

for.inc:
  %storemerge = phi i32 [ %mul, %sw.bb ], [ 0, %for.body ], [ 0, %sw.bb3 ]
  store i32 %storemerge, ptr %arrayidx, align 4, !dbg !20, !tbaa !16
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !10
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !10
  %exitcond = icmp eq i32 %lftr.wideiv, %Length, !dbg !10
  br i1 %exitcond, label %for.end.loopexit, label %for.body, !dbg !10, !llvm.loop !12

for.end.loopexit:
  br label %for.end

for.end:
  ret void, !dbg !24
}

!llvm.dbg.cu = !{!0}
!llvm.module.flags = !{!7, !8}

!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, producer: "clang version 3.5.0", isOptimized: true, runtimeVersion: 6, emissionKind: LineTablesOnly, file: !1, enums: !2, retainedTypes: !2, globals: !2, imports: !2)
!1 = !DIFile(filename: "source.cpp", directory: ".")
!2 = !{}
!4 = distinct !DISubprogram(name: "test_switch", line: 1, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: true, unit: !0, scopeLine: 1, file: !1, scope: !5, type: !6, retainedNodes: !2)
!5 = !DIFile(filename: "source.cpp", directory: ".")
!6 = !DISubroutineType(types: !2)
!7 = !{i32 2, !"Dwarf Version", i32 2}
!8 = !{i32 2, !"Debug Info Version", i32 3}
!10 = !DILocation(line: 3, column: 8, scope: !11)
!11 = distinct !DILexicalBlock(line: 3, column: 3, file: !1, scope: !4)
!12 = !{!12, !13, !13}
!13 = !{!"llvm.loop.vectorize.enable", i1 true}
!14 = !DILocation(line: 4, column: 5, scope: !15)
!15 = distinct !DILexicalBlock(line: 3, column: 36, file: !1, scope: !11)
!16 = !{!17, !17, i64 0}
!17 = !{!"int", !18, i64 0}
!18 = !{!"omnipotent char", !19, i64 0}
!19 = !{!"Simple C/C++ TBAA"}
!20 = !DILocation(line: 6, column: 7, scope: !21)
!21 = distinct !DILexicalBlock(line: 4, column: 18, file: !1, scope: !15)
!22 = !DILocation(line: 7, column: 5, scope: !21)
!23 = !DILocation(line: 9, column: 7, scope: !21)
!24 = !DILocation(line: 14, column: 1, scope: !4)