forked from OSchip/llvm-project
172 lines
8.6 KiB
LLVM
172 lines
8.6 KiB
LLVM
; 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)"}
|