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

%struct._IO_FILE = type { i32, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, %struct._IO_marker*, %struct._IO_FILE*, i32, i32, i64, i16, i8, [1 x i8], i8*, i64, i8*, i8*, i8*, i8*, i64, i32, [20 x i8] }
%struct._IO_marker = type { %struct._IO_marker*, %struct._IO_FILE*, i32 }

@A = common dso_local global [1536 x [1536 x float]] zeroinitializer, align 16
@B = common dso_local global [1536 x [1536 x float]] zeroinitializer, align 16
@stdout = external dso_local global %struct._IO_FILE*, align 8
@.str = private unnamed_addr constant [5 x i8] c"%lf \00", align 1
@C = common dso_local global [1536 x [1536 x float]] zeroinitializer, align 16
@.str.1 = private unnamed_addr constant [2 x i8] c"\0A\00", align 1

; Function Attrs: noinline nounwind uwtable
define dso_local void @init_array() #0 {
entry:
  %i = alloca i32, align 4
  %j = alloca i32, align 4
  store i32 0, i32* %i, align 4
  br label %for.cond

for.cond:                                         ; preds = %for.inc17, %entry
  %0 = load i32, i32* %i, align 4
  %cmp = icmp slt i32 %0, 1536
  br i1 %cmp, label %for.body, label %for.end19

for.body:                                         ; preds = %for.cond
  store i32 0, i32* %j, align 4
  br label %for.cond1

for.cond1:                                        ; preds = %for.inc, %for.body
  %1 = load i32, i32* %j, align 4
  %cmp2 = icmp slt i32 %1, 1536
  br i1 %cmp2, label %for.body3, label %for.end

for.body3:                                        ; preds = %for.cond1
  %2 = load i32, i32* %i, align 4
  %3 = load i32, i32* %j, align 4
  %mul = mul nsw i32 %2, %3
  %rem = srem i32 %mul, 1024
  %add = add nsw i32 1, %rem
  %conv = sitofp i32 %add to double
  %div = fdiv double %conv, 2.000000e+00
  %conv4 = fptrunc double %div to float
  %4 = load i32, i32* %i, align 4
  %idxprom = sext i32 %4 to i64
  %arrayidx = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @A, i64 0, i64 %idxprom
  %5 = load i32, i32* %j, align 4
  %idxprom5 = sext i32 %5 to i64
  %arrayidx6 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx, i64 0, i64 %idxprom5
  store float %conv4, float* %arrayidx6, align 4
  %6 = load i32, i32* %i, align 4
  %7 = load i32, i32* %j, align 4
  %mul7 = mul nsw i32 %6, %7
  %rem8 = srem i32 %mul7, 1024
  %add9 = add nsw i32 1, %rem8
  %conv10 = sitofp i32 %add9 to double
  %div11 = fdiv double %conv10, 2.000000e+00
  %conv12 = fptrunc double %div11 to float
  %8 = load i32, i32* %i, align 4
  %idxprom13 = sext i32 %8 to i64
  %arrayidx14 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @B, i64 0, i64 %idxprom13
  %9 = load i32, i32* %j, align 4
  %idxprom15 = sext i32 %9 to i64
  %arrayidx16 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx14, i64 0, i64 %idxprom15
  store float %conv12, float* %arrayidx16, align 4
  br label %for.inc

for.inc:                                          ; preds = %for.body3
  %10 = load i32, i32* %j, align 4
  %inc = add nsw i32 %10, 1
  store i32 %inc, i32* %j, align 4
  br label %for.cond1

for.end:                                          ; preds = %for.cond1
  br label %for.inc17

for.inc17:                                        ; preds = %for.end
  %11 = load i32, i32* %i, align 4
  %inc18 = add nsw i32 %11, 1
  store i32 %inc18, i32* %i, align 4
  br label %for.cond

for.end19:                                        ; preds = %for.cond
  ret void
}

; Function Attrs: noinline nounwind uwtable
define dso_local void @print_array() #0 {
entry:
  %i = alloca i32, align 4
  %j = alloca i32, align 4
  store i32 0, i32* %i, align 4
  br label %for.cond

for.cond:                                         ; preds = %for.inc10, %entry
  %0 = load i32, i32* %i, align 4
  %cmp = icmp slt i32 %0, 1536
  br i1 %cmp, label %for.body, label %for.end12

for.body:                                         ; preds = %for.cond
  store i32 0, i32* %j, align 4
  br label %for.cond1

for.cond1:                                        ; preds = %for.inc, %for.body
  %1 = load i32, i32* %j, align 4
  %cmp2 = icmp slt i32 %1, 1536
  br i1 %cmp2, label %for.body3, label %for.end

for.body3:                                        ; preds = %for.cond1
  %2 = load %struct._IO_FILE*, %struct._IO_FILE** @stdout, align 8
  %3 = load i32, i32* %i, align 4
  %idxprom = sext i32 %3 to i64
  %arrayidx = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i64 0, i64 %idxprom
  %4 = load i32, i32* %j, align 4
  %idxprom4 = sext i32 %4 to i64
  %arrayidx5 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx, i64 0, i64 %idxprom4
  %5 = load float, float* %arrayidx5, align 4
  %conv = fpext float %5 to double
  %call = call i32 (%struct._IO_FILE*, i8*, ...) @fprintf(%struct._IO_FILE* %2, i8* getelementptr inbounds ([5 x i8], [5 x i8]* @.str, i32 0, i32 0), double %conv)
  %6 = load i32, i32* %j, align 4
  %rem = srem i32 %6, 80
  %cmp6 = icmp eq i32 %rem, 79
  br i1 %cmp6, label %if.then, label %if.end

if.then:                                          ; preds = %for.body3
  %7 = load %struct._IO_FILE*, %struct._IO_FILE** @stdout, align 8
  %call8 = call i32 (%struct._IO_FILE*, i8*, ...) @fprintf(%struct._IO_FILE* %7, i8* getelementptr inbounds ([2 x i8], [2 x i8]* @.str.1, i32 0, i32 0))
  br label %if.end

if.end:                                           ; preds = %if.then, %for.body3
  br label %for.inc

for.inc:                                          ; preds = %if.end
  %8 = load i32, i32* %j, align 4
  %inc = add nsw i32 %8, 1
  store i32 %inc, i32* %j, align 4
  br label %for.cond1

for.end:                                          ; preds = %for.cond1
  %9 = load %struct._IO_FILE*, %struct._IO_FILE** @stdout, align 8
  %call9 = call i32 (%struct._IO_FILE*, i8*, ...) @fprintf(%struct._IO_FILE* %9, i8* getelementptr inbounds ([2 x i8], [2 x i8]* @.str.1, i32 0, i32 0))
  br label %for.inc10

for.inc10:                                        ; preds = %for.end
  %10 = load i32, i32* %i, align 4
  %inc11 = add nsw i32 %10, 1
  store i32 %inc11, i32* %i, align 4
  br label %for.cond

for.end12:                                        ; preds = %for.cond
  ret void
}

declare dso_local i32 @fprintf(%struct._IO_FILE*, i8*, ...) #1

; Function Attrs: noinline nounwind uwtable
define dso_local i32 @main() #0 {
entry:
  %retval = alloca i32, align 4
  %i = alloca i32, align 4
  %j = alloca i32, align 4
  %k = alloca i32, align 4
  %t_start = alloca double, align 8
  %t_end = alloca double, align 8
  store i32 0, i32* %retval, align 4
  call void @init_array()
  store i32 0, i32* %i, align 4
  br label %for.cond

for.cond:                                         ; preds = %for.inc28, %entry
  %0 = load i32, i32* %i, align 4
  %cmp = icmp slt i32 %0, 1536
  br i1 %cmp, label %for.body, label %for.end30

for.body:                                         ; preds = %for.cond
  store i32 0, i32* %j, align 4
  br label %for.cond1

for.cond1:                                        ; preds = %for.inc25, %for.body
  %1 = load i32, i32* %j, align 4
  %cmp2 = icmp slt i32 %1, 1536
  br i1 %cmp2, label %for.body3, label %for.end27

for.body3:                                        ; preds = %for.cond1
  %2 = load i32, i32* %i, align 4
  %idxprom = sext i32 %2 to i64
  %arrayidx = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i64 0, i64 %idxprom
  %3 = load i32, i32* %j, align 4
  %idxprom4 = sext i32 %3 to i64
  %arrayidx5 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx, i64 0, i64 %idxprom4
  store float 0.000000e+00, float* %arrayidx5, align 4
  store i32 0, i32* %k, align 4
  br label %for.cond6

for.cond6:                                        ; preds = %for.inc, %for.body3
  %4 = load i32, i32* %k, align 4
  %cmp7 = icmp slt i32 %4, 1536
  br i1 %cmp7, label %for.body8, label %for.end

for.body8:                                        ; preds = %for.cond6
  %5 = load i32, i32* %i, align 4
  %idxprom9 = sext i32 %5 to i64
  %arrayidx10 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i64 0, i64 %idxprom9
  %6 = load i32, i32* %j, align 4
  %idxprom11 = sext i32 %6 to i64
  %arrayidx12 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx10, i64 0, i64 %idxprom11
  %7 = load float, float* %arrayidx12, align 4
  %8 = load i32, i32* %i, align 4
  %idxprom13 = sext i32 %8 to i64
  %arrayidx14 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @A, i64 0, i64 %idxprom13
  %9 = load i32, i32* %k, align 4
  %idxprom15 = sext i32 %9 to i64
  %arrayidx16 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx14, i64 0, i64 %idxprom15
  %10 = load float, float* %arrayidx16, align 4
  %11 = load i32, i32* %k, align 4
  %idxprom17 = sext i32 %11 to i64
  %arrayidx18 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @B, i64 0, i64 %idxprom17
  %12 = load i32, i32* %j, align 4
  %idxprom19 = sext i32 %12 to i64
  %arrayidx20 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx18, i64 0, i64 %idxprom19
  %13 = load float, float* %arrayidx20, align 4
  %mul = fmul float %10, %13
  %add = fadd float %7, %mul
  %14 = load i32, i32* %i, align 4
  %idxprom21 = sext i32 %14 to i64
  %arrayidx22 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i64 0, i64 %idxprom21
  %15 = load i32, i32* %j, align 4
  %idxprom23 = sext i32 %15 to i64
  %arrayidx24 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx22, i64 0, i64 %idxprom23
  store float %add, float* %arrayidx24, align 4
  br label %for.inc

for.inc:                                          ; preds = %for.body8
  %16 = load i32, i32* %k, align 4
  %inc = add nsw i32 %16, 1
  store i32 %inc, i32* %k, align 4
  br label %for.cond6

for.end:                                          ; preds = %for.cond6
  br label %for.inc25

for.inc25:                                        ; preds = %for.end
  %17 = load i32, i32* %j, align 4
  %inc26 = add nsw i32 %17, 1
  store i32 %inc26, i32* %j, align 4
  br label %for.cond1

for.end27:                                        ; preds = %for.cond1
  br label %for.inc28

for.inc28:                                        ; preds = %for.end27
  %18 = load i32, i32* %i, align 4
  %inc29 = add nsw i32 %18, 1
  store i32 %inc29, i32* %i, align 4
  br label %for.cond

for.end30:                                        ; preds = %for.cond
  ret i32 0
}

attributes #0 = { noinline nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "frame-pointer"="all" "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 = { "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "frame-pointer"="all" "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" }

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

!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"clang version 8.0.0 (trunk 342834) (llvm/trunk 342856)"}