llvm-project/polly/docs/experiments/matmul/matmul.ll

272 lines
12 KiB
LLVM

; 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)"}