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
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -basic-aa -slp-vectorizer -S -mtriple=i386-apple-macosx10.9.0 -mcpu=corei7-avx | FileCheck %s
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
@a = common global i64* null, align 8
; Function Attrs: nounwind ssp uwtable
define i32 @fn1() {
; CHECK-LABEL: @fn1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load i64*, i64** @a, align 8
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i64*> poison, i64* [[TMP0]], i32 0
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x i64*> [[TMP1]], i64* [[TMP0]], i32 1
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr i64, <2 x i64*> [[TMP2]], <2 x i64> <i64 11, i64 56>
; CHECK-NEXT: [[TMP4:%.*]] = ptrtoint <2 x i64*> [[TMP3]] to <2 x i64>
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i64, i64* [[TMP0]], i64 12
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <2 x i64*> [[TMP3]], i32 0
; CHECK-NEXT: [[TMP6:%.*]] = bitcast i64* [[TMP5]] to <2 x i64>*
; CHECK-NEXT: store <2 x i64> [[TMP4]], <2 x i64>* [[TMP6]], align 8
; CHECK-NEXT: ret i32 undef
;
entry:
%0 = load i64*, i64** @a, align 8
%add.ptr = getelementptr inbounds i64, i64* %0, i64 11
%1 = ptrtoint i64* %add.ptr to i64
store i64 %1, i64* %add.ptr, align 8
%add.ptr1 = getelementptr inbounds i64, i64* %0, i64 56
%2 = ptrtoint i64* %add.ptr1 to i64
%arrayidx2 = getelementptr inbounds i64, i64* %0, i64 12
store i64 %2, i64* %arrayidx2, align 8
ret i32 undef
}
declare float @llvm.powi.f32.i32(float, i32)
define void @fn2(i32* %a, i32* %b, float* %c) {
; CHECK-LABEL: @fn2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 1
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i32 1
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 2
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 2
; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 3
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[A]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 3
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = add <4 x i32> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = sitofp <4 x i32> [[TMP4]] to <4 x float>
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <4 x i32> [[TMP4]], i32 0
; CHECK-NEXT: [[TMP7:%.*]] = call <4 x float> @llvm.powi.v4f32.i32(<4 x float> [[TMP5]], i32 [[TMP6]])
; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds float, float* [[C:%.*]], i32 1
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds float, float* [[C]], i32 2
; CHECK-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds float, float* [[C]], i32 3
; CHECK-NEXT: [[TMP8:%.*]] = bitcast float* [[C]] to <4 x float>*
; CHECK-NEXT: store <4 x float> [[TMP7]], <4 x float>* [[TMP8]], align 4
; CHECK-NEXT: ret void
;
entry:
%i0 = load i32, i32* %a, align 4
%i1 = load i32, i32* %b, align 4
%add1 = add i32 %i0, %i1
%fp1 = sitofp i32 %add1 to float
%call1 = tail call float @llvm.powi.f32.i32(float %fp1,i32 %add1) nounwind readnone
%arrayidx2 = getelementptr inbounds i32, i32* %a, i32 1
%i2 = load i32, i32* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i32 1
%i3 = load i32, i32* %arrayidx3, align 4
%add2 = add i32 %i2, %i3
%fp2 = sitofp i32 %add2 to float
%call2 = tail call float @llvm.powi.f32.i32(float %fp2,i32 %add1) nounwind readnone
%arrayidx4 = getelementptr inbounds i32, i32* %a, i32 2
%i4 = load i32, i32* %arrayidx4, align 4
%arrayidx5 = getelementptr inbounds i32, i32* %b, i32 2
%i5 = load i32, i32* %arrayidx5, align 4
%add3 = add i32 %i4, %i5
%fp3 = sitofp i32 %add3 to float
%call3 = tail call float @llvm.powi.f32.i32(float %fp3,i32 %add1) nounwind readnone
%arrayidx6 = getelementptr inbounds i32, i32* %a, i32 3
%i6 = load i32, i32* %arrayidx6, align 4
%arrayidx7 = getelementptr inbounds i32, i32* %b, i32 3
%i7 = load i32, i32* %arrayidx7, align 4
%add4 = add i32 %i6, %i7
%fp4 = sitofp i32 %add4 to float
%call4 = tail call float @llvm.powi.f32.i32(float %fp4,i32 %add1) nounwind readnone
store float %call1, float* %c, align 4
%arrayidx8 = getelementptr inbounds float, float* %c, i32 1
store float %call2, float* %arrayidx8, align 4
%arrayidx9 = getelementptr inbounds float, float* %c, i32 2
store float %call3, float* %arrayidx9, align 4
%arrayidx10 = getelementptr inbounds float, float* %c, i32 3
store float %call4, float* %arrayidx10, align 4
ret void
}
define void @externally_used_ptrs() {
; CHECK-LABEL: @externally_used_ptrs(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load i64*, i64** @a, align 8
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i64*> poison, i64* [[TMP0]], i32 0
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x i64*> [[TMP1]], i64* [[TMP0]], i32 1
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr i64, <2 x i64*> [[TMP2]], <2 x i64> <i64 56, i64 11>
; CHECK-NEXT: [[TMP4:%.*]] = ptrtoint <2 x i64*> [[TMP3]] to <2 x i64>
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i64, i64* [[TMP0]], i64 12
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <2 x i64*> [[TMP3]], i32 1
; CHECK-NEXT: [[TMP6:%.*]] = bitcast i64* [[TMP5]] to <2 x i64>*
; CHECK-NEXT: [[TMP7:%.*]] = load <2 x i64>, <2 x i64>* [[TMP6]], align 8
; CHECK-NEXT: [[TMP8:%.*]] = add <2 x i64> [[TMP4]], [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = bitcast i64* [[TMP5]] to <2 x i64>*
; CHECK-NEXT: store <2 x i64> [[TMP8]], <2 x i64>* [[TMP9]], align 8
; CHECK-NEXT: ret void
;
entry:
%0 = load i64*, i64** @a, align 8
%add.ptr = getelementptr inbounds i64, i64* %0, i64 11
%1 = ptrtoint i64* %add.ptr to i64
%add.ptr1 = getelementptr inbounds i64, i64* %0, i64 56
%2 = ptrtoint i64* %add.ptr1 to i64
%arrayidx2 = getelementptr inbounds i64, i64* %0, i64 12
%3 = load i64, i64* %arrayidx2, align 8
%4 = load i64, i64* %add.ptr, align 8
%5 = add i64 %1, %3
%6 = add i64 %2, %4
store i64 %6, i64* %add.ptr, align 8
store i64 %5, i64* %arrayidx2, align 8
ret void
}
|
