| ; ModuleID = 'matmul.s' |
| 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 global [1536 x [1536 x float]] zeroinitializer, align 16 |
| @B = common global [1536 x [1536 x float]] zeroinitializer, align 16 |
| @stdout = external global %struct._IO_FILE*, align 8 |
| @.str = private unnamed_addr constant [5 x i8] c"%lf \00", align 1 |
| @C = common 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: nounwind uwtable |
| define void @init_array() #0 { |
| entry: |
| br label %entry.split |
| |
| entry.split: ; preds = %entry |
| br label %for.cond1.preheader |
| |
| for.cond1.preheader: ; preds = %entry.split, %for.inc17 |
| %indvars.iv5 = phi i64 [ 0, %entry.split ], [ %indvars.iv.next6, %for.inc17 ] |
| br label %for.body3 |
| |
| for.body3: ; preds = %for.cond1.preheader, %for.body3 |
| %indvars.iv = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next, %for.body3 ] |
| %0 = mul nuw nsw i64 %indvars.iv, %indvars.iv5 |
| %1 = trunc i64 %0 to i32 |
| %rem = srem i32 %1, 1024 |
| %add = add nsw i32 %rem, 1 |
| %conv = sitofp i32 %add to double |
| %div = fmul double %conv, 5.000000e-01 |
| %conv4 = fptrunc double %div to float |
| %arrayidx6 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @A, i64 0, i64 %indvars.iv5, i64 %indvars.iv |
| store float %conv4, float* %arrayidx6, align 4 |
| %2 = mul nuw nsw i64 %indvars.iv, %indvars.iv5 |
| %3 = trunc i64 %2 to i32 |
| %rem8 = srem i32 %3, 1024 |
| %add9 = add nsw i32 %rem8, 1 |
| %conv10 = sitofp i32 %add9 to double |
| %div11 = fmul double %conv10, 5.000000e-01 |
| %conv12 = fptrunc double %div11 to float |
| %arrayidx16 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @B, i64 0, i64 %indvars.iv5, i64 %indvars.iv |
| store float %conv12, float* %arrayidx16, align 4 |
| %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 |
| %exitcond = icmp ne i64 %indvars.iv.next, 1536 |
| br i1 %exitcond, label %for.body3, label %for.inc17 |
| |
| for.inc17: ; preds = %for.body3 |
| %indvars.iv.next6 = add nuw nsw i64 %indvars.iv5, 1 |
| %exitcond7 = icmp ne i64 %indvars.iv.next6, 1536 |
| br i1 %exitcond7, label %for.cond1.preheader, label %for.end19 |
| |
| for.end19: ; preds = %for.inc17 |
| ret void |
| } |
| |
| ; Function Attrs: nounwind uwtable |
| define void @print_array() #0 { |
| entry: |
| br label %entry.split |
| |
| entry.split: ; preds = %entry |
| br label %for.cond1.preheader |
| |
| for.cond1.preheader: ; preds = %entry.split, %for.end |
| %indvars.iv6 = phi i64 [ 0, %entry.split ], [ %indvars.iv.next7, %for.end ] |
| %0 = load %struct._IO_FILE*, %struct._IO_FILE** @stdout, align 8 |
| br label %for.body3 |
| |
| for.body3: ; preds = %for.cond1.preheader, %for.inc |
| %indvars.iv = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next, %for.inc ] |
| %1 = phi %struct._IO_FILE* [ %0, %for.cond1.preheader ], [ %5, %for.inc ] |
| %arrayidx5 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i64 0, i64 %indvars.iv6, i64 %indvars.iv |
| %2 = load float, float* %arrayidx5, align 4 |
| %conv = fpext float %2 to double |
| %call = tail call i32 (%struct._IO_FILE*, i8*, ...) @fprintf(%struct._IO_FILE* %1, i8* getelementptr inbounds ([5 x i8], [5 x i8]* @.str, i64 0, i64 0), double %conv) #2 |
| %3 = trunc i64 %indvars.iv to i32 |
| %rem = srem i32 %3, 80 |
| %cmp6 = icmp eq i32 %rem, 79 |
| br i1 %cmp6, label %if.then, label %for.inc |
| |
| if.then: ; preds = %for.body3 |
| %4 = load %struct._IO_FILE*, %struct._IO_FILE** @stdout, align 8 |
| %fputc3 = tail call i32 @fputc(i32 10, %struct._IO_FILE* %4) |
| br label %for.inc |
| |
| for.inc: ; preds = %for.body3, %if.then |
| %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 |
| %5 = load %struct._IO_FILE*, %struct._IO_FILE** @stdout, align 8 |
| %exitcond = icmp ne i64 %indvars.iv.next, 1536 |
| br i1 %exitcond, label %for.body3, label %for.end |
| |
| for.end: ; preds = %for.inc |
| %.lcssa = phi %struct._IO_FILE* [ %5, %for.inc ] |
| %fputc = tail call i32 @fputc(i32 10, %struct._IO_FILE* %.lcssa) |
| %indvars.iv.next7 = add nuw nsw i64 %indvars.iv6, 1 |
| %exitcond8 = icmp ne i64 %indvars.iv.next7, 1536 |
| br i1 %exitcond8, label %for.cond1.preheader, label %for.end12 |
| |
| for.end12: ; preds = %for.end |
| ret void |
| } |
| |
| declare i32 @fprintf(%struct._IO_FILE*, i8*, ...) #1 |
| |
| ; Function Attrs: nounwind uwtable |
| define i32 @main() #0 { |
| entry: |
| br label %entry.split |
| |
| entry.split: ; preds = %entry |
| tail call void @init_array() |
| br label %for.cond1.preheader |
| |
| for.cond1.preheader: ; preds = %entry.split, %for.inc28 |
| %indvars.iv7 = phi i64 [ 0, %entry.split ], [ %indvars.iv.next8, %for.inc28 ] |
| br label %for.body3 |
| |
| for.body3: ; preds = %for.cond1.preheader, %for.inc25 |
| %indvars.iv4 = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next5, %for.inc25 ] |
| %arrayidx5 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i64 0, i64 %indvars.iv7, i64 %indvars.iv4 |
| store float 0.000000e+00, float* %arrayidx5, align 4 |
| br label %for.body8 |
| |
| for.body8: ; preds = %for.body3, %for.body8 |
| %indvars.iv = phi i64 [ 0, %for.body3 ], [ %indvars.iv.next, %for.body8 ] |
| %arrayidx12 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i64 0, i64 %indvars.iv7, i64 %indvars.iv4 |
| %0 = load float, float* %arrayidx12, align 4 |
| %arrayidx16 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @A, i64 0, i64 %indvars.iv7, i64 %indvars.iv |
| %1 = load float, float* %arrayidx16, align 4 |
| %arrayidx20 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @B, i64 0, i64 %indvars.iv, i64 %indvars.iv4 |
| %2 = load float, float* %arrayidx20, align 4 |
| %mul = fmul float %1, %2 |
| %add = fadd float %0, %mul |
| %arrayidx24 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i64 0, i64 %indvars.iv7, i64 %indvars.iv4 |
| store float %add, float* %arrayidx24, align 4 |
| %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 |
| %exitcond = icmp ne i64 %indvars.iv.next, 1536 |
| br i1 %exitcond, label %for.body8, label %for.inc25 |
| |
| for.inc25: ; preds = %for.body8 |
| %indvars.iv.next5 = add nuw nsw i64 %indvars.iv4, 1 |
| %exitcond6 = icmp ne i64 %indvars.iv.next5, 1536 |
| br i1 %exitcond6, label %for.body3, label %for.inc28 |
| |
| for.inc28: ; preds = %for.inc25 |
| %indvars.iv.next8 = add nuw nsw i64 %indvars.iv7, 1 |
| %exitcond9 = icmp ne i64 %indvars.iv.next8, 1536 |
| br i1 %exitcond9, label %for.cond1.preheader, label %for.end30 |
| |
| for.end30: ; preds = %for.inc28 |
| ret i32 0 |
| } |
| |
| ; Function Attrs: nounwind |
| declare i64 @fwrite(i8* nocapture, i64, i64, %struct._IO_FILE* nocapture) #2 |
| |
| ; Function Attrs: nounwind |
| declare i32 @fputc(i32, %struct._IO_FILE* nocapture) #2 |
| |
| attributes #0 = { 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 #1 = { "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 = { nounwind } |
| |
| !llvm.ident = !{!0} |
| |
| !0 = !{!"clang version 4.0.0 (http://llvm.org/git/clang.git 081569d9a29c7bc827b2d41f8e62891bbc895e2f) (http://llvm.org/git/llvm.git e117e506536626352e8e47f6c72cd6e2a276622c)"} |
