validate_ascii.ll

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

%struct.__loadu_si128 = type { <2 x i64> }

define i32 @validate_ascii(i8*, i64, i8*, i64*) #4 {
  %5 = icmp ule i64 16, %1
  br i1 %5, label %6, label %30

  %7 = sub i64 %1, 16
  br label %8

  %.0 = phi i64 [ 0, %6 ], [ %25, %28 ]
  %9 = getelementptr inbounds i8, i8* %0, i64 %.0
  %10 = call <2 x i64> @load16_unaligned(i8* %9)
  %11 = call i32 @mask_ascii(<2 x i64> %10)
  %12 = icmp ne i32 %11, 0
  br i1 %12, label %13, label %24

  %14 = icmp ne i32 %11, 0
  br i1 %14, label %15, label %17

  %16 = call i32 @llvm.cttz.i32(i32 %11, i1 true) #7
  br label %18

  br label %18

  %19 = phi i32 [ %16, %15 ], [ 32, %17 ]
  %20 = zext i32 %19 to i64
  %21 = add i64 %.0, %20
  %22 = getelementptr inbounds i8, i8* %0, i64 %21
  %23 = load i8, i8* %22, align 1
  store i8 %23, i8* %2, align 1
  store i64 %21, i64* %3, align 8
  br label %42

  %25 = add i64 %.0, 16
  %26 = icmp ugt i64 %25, %7
  br i1 %26, label %27, label %28

  br label %29

  br label %8, !llvm.loop !3

  br label %30

  %.1 = phi i64 [ %25, %29 ], [ 0, %4 ]
  br label %31

  %.2 = phi i64 [ %.1, %30 ], [ %40, %39 ]
  %32 = icmp ult i64 %.2, %1
  br i1 %32, label %33, label %41

  %34 = getelementptr inbounds i8, i8* %0, i64 %.2
  %35 = load i8, i8* %34, align 1
  %36 = sext i8 %35 to i32
  %37 = icmp sgt i32 %36, 127
  br i1 %37, label %38, label %39

  store i8 %35, i8* %2, align 1
  store i64 %.2, i64* %3, align 8
  br label %42

  %40 = add i64 %.2, 1
  br label %31

  br label %42

  %.01 = phi i32 [ 1, %18 ], [ 1, %38 ], [ 0, %41 ]
  ret i32 %.01
}

define internal <2 x i64> @load16_unaligned(i8*) #4 {
  %2 = bitcast i8* %0 to <2 x i64>*
  %3 = bitcast <2 x i64>* %2 to %struct.__loadu_si128*
  %4 = getelementptr inbounds %struct.__loadu_si128, %struct.__loadu_si128* %3, i32 0, i32 0
  %5 = load <2 x i64>, <2 x i64>* %4, align 1
  ret <2 x i64> %5
}

define internal i32 @mask_ascii(<2 x i64>) #4 {
  %2 = bitcast <2 x i64> %0 to <16 x i8>
  %3 = call i32 @llvm.x86.sse2.pmovmskb.128(<16 x i8> %2) #7
  ret i32 %3
}

declare i32 @llvm.x86.sse2.pmovmskb.128(<16 x i8>) #5

declare i32 @llvm.cttz.i32(i32, i1) #6

attributes #0 = { noinline norecurse uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "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"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { nounwind "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="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"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #2 = { noinline nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "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"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #3 = { noinline }
attributes #4 = { uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "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"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #5 = { nounwind readnone }
attributes #6 = { nounwind readnone speculatable }
attributes #7 = { nounwind }

!llvm.module.flags = !{!0}
!llvm.ident = !{!1}

!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"clang version 7.0.0 (trunk 332192)"}
!2 = !{i32 1340}
!3 = distinct !{!3, !4}
!4 = !{!"llvm.loop.unroll.disable"}