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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -basic-aa -slp-vectorizer -S -mtriple=x86_64-unknown-linux-gnu -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE
; RUN: opt < %s -basic-aa -slp-vectorizer -S -mtriple=x86_64-unknown-linux-gnu -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX
; RUN: opt < %s -basic-aa -slp-vectorizer -S -mtriple=x86_64-unknown-linux-gnu -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX
define void @powof2div_uniform(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* noalias nocapture readonly %c){
; CHECK-LABEL: @powof2div_uniform(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[C:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = add nsw <4 x i32> [[TMP3]], [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = sdiv <4 x i32> [[TMP4]], <i32 2, i32 2, i32 2, i32 2>
; CHECK-NEXT: [[TMP6:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP6]], align 4
; CHECK-NEXT: ret void
;
entry:
%0 = load i32, i32* %b, align 4
%1 = load i32, i32* %c, align 4
%add = add nsw i32 %1, %0
%div = sdiv i32 %add, 2
store i32 %div, i32* %a, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 1
%2 = load i32, i32* %arrayidx3, align 4
%arrayidx4 = getelementptr inbounds i32, i32* %c, i64 1
%3 = load i32, i32* %arrayidx4, align 4
%add5 = add nsw i32 %3, %2
%div6 = sdiv i32 %add5, 2
%arrayidx7 = getelementptr inbounds i32, i32* %a, i64 1
store i32 %div6, i32* %arrayidx7, align 4
%arrayidx8 = getelementptr inbounds i32, i32* %b, i64 2
%4 = load i32, i32* %arrayidx8, align 4
%arrayidx9 = getelementptr inbounds i32, i32* %c, i64 2
%5 = load i32, i32* %arrayidx9, align 4
%add10 = add nsw i32 %5, %4
%div11 = sdiv i32 %add10, 2
%arrayidx12 = getelementptr inbounds i32, i32* %a, i64 2
store i32 %div11, i32* %arrayidx12, align 4
%arrayidx13 = getelementptr inbounds i32, i32* %b, i64 3
%6 = load i32, i32* %arrayidx13, align 4
%arrayidx14 = getelementptr inbounds i32, i32* %c, i64 3
%7 = load i32, i32* %arrayidx14, align 4
%add15 = add nsw i32 %7, %6
%div16 = sdiv i32 %add15, 2
%arrayidx17 = getelementptr inbounds i32, i32* %a, i64 3
store i32 %div16, i32* %arrayidx17, align 4
ret void
}
define void @powof2div_nonuniform(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* noalias nocapture readonly %c){
; SSE-LABEL: @powof2div_nonuniform(
; SSE-NEXT: entry:
; SSE-NEXT: [[TMP0:%.*]] = load i32, i32* [[B:%.*]], align 4
; SSE-NEXT: [[TMP1:%.*]] = load i32, i32* [[C:%.*]], align 4
; SSE-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP1]], [[TMP0]]
; SSE-NEXT: [[DIV:%.*]] = sdiv i32 [[ADD]], 2
; SSE-NEXT: store i32 [[DIV]], i32* [[A:%.*]], align 4
; SSE-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 1
; SSE-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; SSE-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 1
; SSE-NEXT: [[TMP3:%.*]] = load i32, i32* [[ARRAYIDX4]], align 4
; SSE-NEXT: [[ADD5:%.*]] = add nsw i32 [[TMP3]], [[TMP2]]
; SSE-NEXT: [[DIV6:%.*]] = sdiv i32 [[ADD5]], 4
; SSE-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 1
; SSE-NEXT: store i32 [[DIV6]], i32* [[ARRAYIDX7]], align 4
; SSE-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2
; SSE-NEXT: [[TMP4:%.*]] = load i32, i32* [[ARRAYIDX8]], align 4
; SSE-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 2
; SSE-NEXT: [[TMP5:%.*]] = load i32, i32* [[ARRAYIDX9]], align 4
; SSE-NEXT: [[ADD10:%.*]] = add nsw i32 [[TMP5]], [[TMP4]]
; SSE-NEXT: [[DIV11:%.*]] = sdiv i32 [[ADD10]], 8
; SSE-NEXT: [[ARRAYIDX12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 2
; SSE-NEXT: store i32 [[DIV11]], i32* [[ARRAYIDX12]], align 4
; SSE-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; SSE-NEXT: [[TMP6:%.*]] = load i32, i32* [[ARRAYIDX13]], align 4
; SSE-NEXT: [[ARRAYIDX14:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 3
; SSE-NEXT: [[TMP7:%.*]] = load i32, i32* [[ARRAYIDX14]], align 4
; SSE-NEXT: [[ADD15:%.*]] = add nsw i32 [[TMP7]], [[TMP6]]
; SSE-NEXT: [[DIV16:%.*]] = sdiv i32 [[ADD15]], 16
; SSE-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 3
; SSE-NEXT: store i32 [[DIV16]], i32* [[ARRAYIDX17]], align 4
; SSE-NEXT: ret void
;
; AVX-LABEL: @powof2div_nonuniform(
; AVX-NEXT: entry:
; AVX-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>*
; AVX-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; AVX-NEXT: [[TMP2:%.*]] = bitcast i32* [[C:%.*]] to <4 x i32>*
; AVX-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4
; AVX-NEXT: [[TMP4:%.*]] = add nsw <4 x i32> [[TMP3]], [[TMP1]]
; AVX-NEXT: [[TMP5:%.*]] = sdiv <4 x i32> [[TMP4]], <i32 2, i32 4, i32 8, i32 16>
; AVX-NEXT: [[TMP6:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>*
; AVX-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP6]], align 4
; AVX-NEXT: ret void
;
entry:
%0 = load i32, i32* %b, align 4
%1 = load i32, i32* %c, align 4
%add = add nsw i32 %1, %0
%div = sdiv i32 %add, 2
store i32 %div, i32* %a, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 1
%2 = load i32, i32* %arrayidx3, align 4
%arrayidx4 = getelementptr inbounds i32, i32* %c, i64 1
%3 = load i32, i32* %arrayidx4, align 4
%add5 = add nsw i32 %3, %2
%div6 = sdiv i32 %add5, 4
%arrayidx7 = getelementptr inbounds i32, i32* %a, i64 1
store i32 %div6, i32* %arrayidx7, align 4
%arrayidx8 = getelementptr inbounds i32, i32* %b, i64 2
%4 = load i32, i32* %arrayidx8, align 4
%arrayidx9 = getelementptr inbounds i32, i32* %c, i64 2
%5 = load i32, i32* %arrayidx9, align 4
%add10 = add nsw i32 %5, %4
%div11 = sdiv i32 %add10, 8
%arrayidx12 = getelementptr inbounds i32, i32* %a, i64 2
store i32 %div11, i32* %arrayidx12, align 4
%arrayidx13 = getelementptr inbounds i32, i32* %b, i64 3
%6 = load i32, i32* %arrayidx13, align 4
%arrayidx14 = getelementptr inbounds i32, i32* %c, i64 3
%7 = load i32, i32* %arrayidx14, align 4
%add15 = add nsw i32 %7, %6
%div16 = sdiv i32 %add15, 16
%arrayidx17 = getelementptr inbounds i32, i32* %a, i64 3
store i32 %div16, i32* %arrayidx17, align 4
ret void
}
|
