1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -instcombine -S -data-layout="e-m:e-i64:64-f80:128-n8:16:32:64-S128" | FileCheck %s
@a = global [1000 x float] zeroinitializer, align 16
@b = global [1000 x float] zeroinitializer, align 16
define void @_Z3foov() {
; CHECK-LABEL: @_Z3foov(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_COND:%.*]]
; CHECK: for.cond:
; CHECK-NEXT: [[I_0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY:%.*]] ]
; CHECK-NEXT: [[CMP:%.*]] = icmp ult i32 [[I_0]], 1000
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret void
; CHECK: for.body:
; CHECK-NEXT: [[TMP0:%.*]] = zext i32 [[I_0]] to i64
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [1000 x float], [1000 x float]* @a, i64 0, i64 [[TMP0]]
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [1000 x float], [1000 x float]* @b, i64 0, i64 [[TMP0]]
; CHECK-NEXT: [[TMP1:%.*]] = load float, float* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = load float, float* [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[CMP_I:%.*]] = fcmp fast olt float [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[__B___A_I:%.*]] = select i1 [[CMP_I]], float* [[ARRAYIDX2]], float* [[ARRAYIDX]]
; CHECK-NEXT: [[TMP3:%.*]] = bitcast float* [[__B___A_I]] to i32*
; CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 4
; CHECK-NEXT: [[TMP5:%.*]] = bitcast float* [[ARRAYIDX]] to i32*
; CHECK-NEXT: store i32 [[TMP4]], i32* [[TMP5]], align 4
; CHECK-NEXT: [[INC]] = add nuw nsw i32 [[I_0]], 1
; CHECK-NEXT: br label [[FOR_COND]]
;
entry:
br label %for.cond
for.cond: ; preds = %for.body, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%cmp = icmp ult i32 %i.0, 1000
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond
ret void
for.body: ; preds = %for.cond
%0 = zext i32 %i.0 to i64
%arrayidx = getelementptr inbounds [1000 x float], [1000 x float]* @a, i64 0, i64 %0
%arrayidx2 = getelementptr inbounds [1000 x float], [1000 x float]* @b, i64 0, i64 %0
%1 = load float, float* %arrayidx, align 4
%2 = load float, float* %arrayidx2, align 4
%cmp.i = fcmp fast olt float %1, %2
%__b.__a.i = select i1 %cmp.i, float* %arrayidx2, float* %arrayidx
%3 = bitcast float* %__b.__a.i to i32*
%4 = load i32, i32* %3, align 4
%5 = bitcast float* %arrayidx to i32*
store i32 %4, i32* %5, align 4
%inc = add nuw nsw i32 %i.0, 1
br label %for.cond
}
define i32 @store_bitcasted_load(i1 %cond, float* dereferenceable(4) %addr1, float* dereferenceable(4) %addr2) {
; CHECK-LABEL: @store_bitcasted_load(
; CHECK-NEXT: [[SEL:%.*]] = select i1 [[COND:%.*]], float* [[ADDR1:%.*]], float* [[ADDR2:%.*]]
; CHECK-NEXT: [[BC1:%.*]] = bitcast float* [[SEL]] to i32*
; CHECK-NEXT: [[LD:%.*]] = load i32, i32* [[BC1]], align 4
; CHECK-NEXT: ret i32 [[LD]]
;
%sel = select i1 %cond, float* %addr1, float* %addr2
%bc1 = bitcast float* %sel to i32*
%ld = load i32, i32* %bc1
ret i32 %ld
}
|
