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

@ptr = global i32 0, align 4
@outbuf = common global [16 x i32] zeroinitializer, align 16
@STATE = common global [16 x i32] zeroinitializer, align 16
@0 = private unnamed_addr constant [5 x i8] c"load\00"

; Function Attrs: nounwind uwtable
define void @salsa20(i32* %out, i32* %in) #0 {
entry:
  %x = alloca [16 x i32], align 16
  br label %for.cond

for.cond:                                         ; preds = %for.inc, %entry
  %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
  %cmp = icmp ult i32 %i.0, 16
  br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
  %idxprom = zext i32 %i.0 to i64
  %arrayidx = getelementptr inbounds [16 x i32], [16 x i32]* %x, i64 0, i64 %idxprom
  store i32 %i.0, i32* %arrayidx, align 4
  br label %for.inc

for.inc:                                          ; preds = %for.body
  %inc = add i32 %i.0, 1
  br label %for.cond

for.end:                                          ; preds = %for.cond
  %arrayidx1 = getelementptr inbounds [16 x i32], [16 x i32]* %x, i64 0, i64 0
  call void @count_instruction(i8* getelementptr inbounds ([5 x i8], [5 x i8]* @0, i32 0, i32 0))
  %0 = load i32, i32* %arrayidx1, align 16
  %arrayidx2 = getelementptr inbounds [16 x i32], [16 x i32]* %x, i64 0, i64 12
  call void @count_instruction(i8* getelementptr inbounds ([5 x i8], [5 x i8]* @0, i32 0, i32 0))
  %1 = load i32, i32* %arrayidx2, align 16
  %add = add i32 %0, %1
  %shl = shl i32 %add, 7
  %arrayidx3 = getelementptr inbounds [16 x i32], [16 x i32]* %x, i64 0, i64 0
  call void @count_instruction(i8* getelementptr inbounds ([5 x i8], [5 x i8]* @0, i32 0, i32 0))
  %2 = load i32, i32* %arrayidx3, align 16
  %arrayidx4 = getelementptr inbounds [16 x i32], [16 x i32]* %x, i64 0, i64 12
  call void @count_instruction(i8* getelementptr inbounds ([5 x i8], [5 x i8]* @0, i32 0, i32 0))
  %3 = load i32, i32* %arrayidx4, align 16
  %add5 = add i32 %2, %3
  %shr = lshr i32 %add5, 25
  %or = or i32 %shl, %shr
  %arrayidx6 = getelementptr inbounds [16 x i32], [16 x i32]* %x, i64 0, i64 4
  call void @count_instruction(i8* getelementptr inbounds ([5 x i8], [5 x i8]* @0, i32 0, i32 0))
  %4 = load i32, i32* %arrayidx6, align 16
  %xor = xor i32 %4, %or
  store i32 %xor, i32* %arrayidx6, align 16
  ret void
}

declare void @count_instruction(i8*)

; Function Attrs: nounwind uwtable
define i32 @salsa() #0 {
entry:
  %0 = load i32, i32* @ptr, align 4
  %cmp = icmp eq i32 %0, 0
  br i1 %cmp, label %if.then, label %if.end

if.then:                                          ; preds = %entry
  call void @salsa20(i32* getelementptr inbounds ([16 x i32], [16 x i32]* @outbuf, i32 0, i32 0), i32* getelementptr inbounds ([16 x i32], [16 x i32]* @STATE, i32 0, i32 0))
  %1 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @STATE, i64 0, i64 0), align 16
  %inc = add i32 %1, 1
  store i32 %inc, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @STATE, i64 0, i64 0), align 16
  %conv = zext i32 %1 to i64
  br label %if.end

if.end:                                           ; preds = %if.then, %entry
  %2 = load i32, i32* @ptr, align 4
  %add = add i32 %2, 1
  %and = and i32 %add, 15
  store i32 %and, i32* @ptr, align 4
  %3 = load i32, i32* @ptr, align 4
  %idxprom = zext i32 %3 to i64
  %arrayidx = getelementptr inbounds [16 x i32], [16 x i32]* @outbuf, i64 0, i64 %idxprom
  %4 = load i32, i32* %arrayidx, align 4
  ret i32 %4
}

; Function Attrs: nounwind uwtable
define i32 @main() #0 {
entry:
  call void @salsa20(i32* getelementptr inbounds ([16 x i32], [16 x i32]* @outbuf, i32 0, i32 0), i32* getelementptr inbounds ([16 x i32], [16 x i32]* @STATE, i32 0, i32 0))
  call void @dump_csv()
  ret i32 0
}

declare void @dump_csv()

attributes #0 = { nounwind uwtable "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" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }

!llvm.ident = !{!0}

!0 = !{!"clang version 3.8.0 (tags/RELEASE_380/final 337191)"}