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
134
135
136
137
138
139
140
141
142
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=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 ptr null, align 8
; Function Attrs: nounwind ssp uwtable
define void @fn1() {
; CHECK-LABEL: @fn1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr @a, align 8
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x ptr> poison, ptr [[TMP0]], i32 0
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x ptr> [[TMP1]], <2 x ptr> poison, <2 x i32> zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr i64, <2 x ptr> [[TMP2]], <2 x i64> <i64 11, i64 56>
; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i64, ptr [[TMP0]], i64 11
; CHECK-NEXT: [[TMP4:%.*]] = ptrtoint <2 x ptr> [[TMP3]] to <2 x i64>
; CHECK-NEXT: store <2 x i64> [[TMP4]], ptr [[ADD_PTR]], align 8
; CHECK-NEXT: ret void
;
entry:
%0 = load ptr, ptr @a, align 8
%add.ptr = getelementptr inbounds i64, ptr %0, i64 11
%1 = ptrtoint ptr %add.ptr to i64
store i64 %1, ptr %add.ptr, align 8
%add.ptr1 = getelementptr inbounds i64, ptr %0, i64 56
%2 = ptrtoint ptr %add.ptr1 to i64
%arrayidx2 = getelementptr inbounds i64, ptr %0, i64 12
store i64 %2, ptr %arrayidx2, align 8
ret void
}
declare float @llvm.powi.f32.i32(float, i32)
define void @fn2(ptr %a, ptr %b, ptr %c) {
; CHECK-LABEL: @fn2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[I0:%.*]] = load i32, ptr [[A:%.*]], align 4
; CHECK-NEXT: [[I1:%.*]] = load i32, ptr [[B:%.*]], align 4
; CHECK-NEXT: [[ADD1:%.*]] = add i32 [[I0]], [[I1]]
; CHECK-NEXT: [[FP1:%.*]] = sitofp i32 [[ADD1]] to float
; CHECK-NEXT: [[CALL1:%.*]] = tail call float @llvm.powi.f32.i32(float [[FP1]], i32 [[ADD1]]) #[[ATTR2:[0-9]+]]
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, ptr [[A]], i32 1
; CHECK-NEXT: [[I2:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, ptr [[B]], i32 1
; CHECK-NEXT: [[I3:%.*]] = load i32, ptr [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[ADD2:%.*]] = add i32 [[I2]], [[I3]]
; CHECK-NEXT: [[FP2:%.*]] = sitofp i32 [[ADD2]] to float
; CHECK-NEXT: [[CALL2:%.*]] = tail call float @llvm.powi.f32.i32(float [[FP2]], i32 [[ADD1]]) #[[ATTR2]]
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, ptr [[A]], i32 2
; CHECK-NEXT: [[I4:%.*]] = load i32, ptr [[ARRAYIDX4]], align 4
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, ptr [[B]], i32 2
; CHECK-NEXT: [[I5:%.*]] = load i32, ptr [[ARRAYIDX5]], align 4
; CHECK-NEXT: [[ADD3:%.*]] = add i32 [[I4]], [[I5]]
; CHECK-NEXT: [[FP3:%.*]] = sitofp i32 [[ADD3]] to float
; CHECK-NEXT: [[CALL3:%.*]] = tail call float @llvm.powi.f32.i32(float [[FP3]], i32 [[ADD1]]) #[[ATTR2]]
; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, ptr [[A]], i32 3
; CHECK-NEXT: [[I6:%.*]] = load i32, ptr [[ARRAYIDX6]], align 4
; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds i32, ptr [[B]], i32 3
; CHECK-NEXT: [[I7:%.*]] = load i32, ptr [[ARRAYIDX7]], align 4
; CHECK-NEXT: [[ADD4:%.*]] = add i32 [[I6]], [[I7]]
; CHECK-NEXT: [[FP4:%.*]] = sitofp i32 [[ADD4]] to float
; CHECK-NEXT: [[CALL4:%.*]] = tail call float @llvm.powi.f32.i32(float [[FP4]], i32 [[ADD1]]) #[[ATTR2]]
; CHECK-NEXT: store float [[CALL1]], ptr [[C:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds float, ptr [[C]], i32 1
; CHECK-NEXT: store float [[CALL2]], ptr [[ARRAYIDX8]], align 4
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds float, ptr [[C]], i32 2
; CHECK-NEXT: store float [[CALL3]], ptr [[ARRAYIDX9]], align 4
; CHECK-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds float, ptr [[C]], i32 3
; CHECK-NEXT: store float [[CALL4]], ptr [[ARRAYIDX10]], align 4
; CHECK-NEXT: ret void
;
entry:
%i0 = load i32, ptr %a, align 4
%i1 = load i32, ptr %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, ptr %a, i32 1
%i2 = load i32, ptr %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds i32, ptr %b, i32 1
%i3 = load i32, ptr %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, ptr %a, i32 2
%i4 = load i32, ptr %arrayidx4, align 4
%arrayidx5 = getelementptr inbounds i32, ptr %b, i32 2
%i5 = load i32, ptr %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, ptr %a, i32 3
%i6 = load i32, ptr %arrayidx6, align 4
%arrayidx7 = getelementptr inbounds i32, ptr %b, i32 3
%i7 = load i32, ptr %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, ptr %c, align 4
%arrayidx8 = getelementptr inbounds float, ptr %c, i32 1
store float %call2, ptr %arrayidx8, align 4
%arrayidx9 = getelementptr inbounds float, ptr %c, i32 2
store float %call3, ptr %arrayidx9, align 4
%arrayidx10 = getelementptr inbounds float, ptr %c, i32 3
store float %call4, ptr %arrayidx10, align 4
ret void
}
define void @externally_used_ptrs() {
; CHECK-LABEL: @externally_used_ptrs(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr @a, align 8
; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i64, ptr [[TMP0]], i64 11
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x ptr> poison, ptr [[TMP0]], i32 0
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x ptr> [[TMP1]], <2 x ptr> poison, <2 x i32> zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr i64, <2 x ptr> [[TMP2]], <2 x i64> <i64 56, i64 11>
; CHECK-NEXT: [[TMP4:%.*]] = ptrtoint <2 x ptr> [[TMP3]] to <2 x i64>
; CHECK-NEXT: [[TMP5:%.*]] = load <2 x i64>, ptr [[ADD_PTR]], align 8
; CHECK-NEXT: [[TMP6:%.*]] = add <2 x i64> [[TMP4]], [[TMP5]]
; CHECK-NEXT: store <2 x i64> [[TMP6]], ptr [[ADD_PTR]], align 8
; CHECK-NEXT: ret void
;
entry:
%0 = load ptr, ptr @a, align 8
%add.ptr = getelementptr inbounds i64, ptr %0, i64 11
%1 = ptrtoint ptr %add.ptr to i64
%add.ptr1 = getelementptr inbounds i64, ptr %0, i64 56
%2 = ptrtoint ptr %add.ptr1 to i64
%arrayidx2 = getelementptr inbounds i64, ptr %0, i64 12
%3 = load i64, ptr %arrayidx2, align 8
%4 = load i64, ptr %add.ptr, align 8
%5 = add i64 %1, %3
%6 = add i64 %2, %4
store i64 %6, ptr %add.ptr, align 8
store i64 %5, ptr %arrayidx2, align 8
ret void
}
|
