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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -slp-vectorizer -slp-threshold=-200 -mtriple=x86_64-unknown-linux -mcpu=core-avx2 -S | FileCheck %s
define void @test_add_sdiv(i32 *%arr1, i32 *%arr2, i32 %a0, i32 %a1, i32 %a2, i32 %a3) {
; CHECK-LABEL: @test_add_sdiv(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[GEP1_0:%.*]] = getelementptr i32, i32* [[ARR1:%.*]], i32 0
; CHECK-NEXT: [[GEP1_1:%.*]] = getelementptr i32, i32* [[ARR1]], i32 1
; CHECK-NEXT: [[GEP1_2:%.*]] = getelementptr i32, i32* [[ARR1]], i32 2
; CHECK-NEXT: [[GEP1_3:%.*]] = getelementptr i32, i32* [[ARR1]], i32 3
; CHECK-NEXT: [[GEP2_0:%.*]] = getelementptr i32, i32* [[ARR2:%.*]], i32 0
; CHECK-NEXT: [[GEP2_1:%.*]] = getelementptr i32, i32* [[ARR2]], i32 1
; CHECK-NEXT: [[GEP2_2:%.*]] = getelementptr i32, i32* [[ARR2]], i32 2
; CHECK-NEXT: [[GEP2_3:%.*]] = getelementptr i32, i32* [[ARR2]], i32 3
; CHECK-NEXT: [[V0:%.*]] = load i32, i32* [[GEP1_0]]
; CHECK-NEXT: [[V1:%.*]] = load i32, i32* [[GEP1_1]]
; CHECK-NEXT: [[V2:%.*]] = load i32, i32* [[GEP1_2]]
; CHECK-NEXT: [[V3:%.*]] = load i32, i32* [[GEP1_3]]
; CHECK-NEXT: [[Y0:%.*]] = add nsw i32 [[A0:%.*]], 1146
; CHECK-NEXT: [[Y1:%.*]] = add nsw i32 [[A1:%.*]], 146
; CHECK-NEXT: [[Y2:%.*]] = add nsw i32 [[A2:%.*]], 42
; CHECK-NEXT: [[Y3:%.*]] = add nsw i32 [[A3:%.*]], 0
; CHECK-NEXT: [[RES0:%.*]] = add nsw i32 [[V0]], [[Y0]]
; CHECK-NEXT: [[RES1:%.*]] = add nsw i32 [[V1]], [[Y1]]
; CHECK-NEXT: [[RES2:%.*]] = sdiv i32 [[V2]], [[Y2]]
; CHECK-NEXT: [[RES3:%.*]] = add nsw i32 [[V3]], [[Y3]]
; CHECK-NEXT: store i32 [[RES0]], i32* [[GEP2_0]]
; CHECK-NEXT: store i32 [[RES1]], i32* [[GEP2_1]]
; CHECK-NEXT: store i32 [[RES2]], i32* [[GEP2_2]]
; CHECK-NEXT: store i32 [[RES3]], i32* [[GEP2_3]]
; CHECK-NEXT: ret void
;
entry:
%gep1.0 = getelementptr i32, i32* %arr1, i32 0
%gep1.1 = getelementptr i32, i32* %arr1, i32 1
%gep1.2 = getelementptr i32, i32* %arr1, i32 2
%gep1.3 = getelementptr i32, i32* %arr1, i32 3
%gep2.0 = getelementptr i32, i32* %arr2, i32 0
%gep2.1 = getelementptr i32, i32* %arr2, i32 1
%gep2.2 = getelementptr i32, i32* %arr2, i32 2
%gep2.3 = getelementptr i32, i32* %arr2, i32 3
%v0 = load i32, i32* %gep1.0
%v1 = load i32, i32* %gep1.1
%v2 = load i32, i32* %gep1.2
%v3 = load i32, i32* %gep1.3
%y0 = add nsw i32 %a0, 1146
%y1 = add nsw i32 %a1, 146
%y2 = add nsw i32 %a2, 42
;; %y3 is zero if %a3 is zero
%y3 = add nsw i32 %a3, 0
%res0 = add nsw i32 %v0, %y0
%res1 = add nsw i32 %v1, %y1
;; As such, doing alternate shuffling would be incorrect:
;; %vadd = add nsw %v[0-3], %y[0-3]
;; %vsdiv = sdiv %v[0-3], %y[0-3]
;; %result = shuffle %vadd, %vsdiv, <mask>
;; would be illegal.
%res2 = sdiv i32 %v2, %y2
%res3 = add nsw i32 %v3, %y3
store i32 %res0, i32* %gep2.0
store i32 %res1, i32* %gep2.1
store i32 %res2, i32* %gep2.2
store i32 %res3, i32* %gep2.3
ret void
}
;; Similar test, but now div/rem is main opcode and not the alternate one. Same issue.
define void @test_urem_add(i32 *%arr1, i32 *%arr2, i32 %a0, i32 %a1, i32 %a2, i32 %a3) {
; CHECK-LABEL: @test_urem_add(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[GEP1_0:%.*]] = getelementptr i32, i32* [[ARR1:%.*]], i32 0
; CHECK-NEXT: [[GEP1_1:%.*]] = getelementptr i32, i32* [[ARR1]], i32 1
; CHECK-NEXT: [[GEP1_2:%.*]] = getelementptr i32, i32* [[ARR1]], i32 2
; CHECK-NEXT: [[GEP1_3:%.*]] = getelementptr i32, i32* [[ARR1]], i32 3
; CHECK-NEXT: [[GEP2_0:%.*]] = getelementptr i32, i32* [[ARR2:%.*]], i32 0
; CHECK-NEXT: [[GEP2_1:%.*]] = getelementptr i32, i32* [[ARR2]], i32 1
; CHECK-NEXT: [[GEP2_2:%.*]] = getelementptr i32, i32* [[ARR2]], i32 2
; CHECK-NEXT: [[GEP2_3:%.*]] = getelementptr i32, i32* [[ARR2]], i32 3
; CHECK-NEXT: [[V0:%.*]] = load i32, i32* [[GEP1_0]]
; CHECK-NEXT: [[V1:%.*]] = load i32, i32* [[GEP1_1]]
; CHECK-NEXT: [[V2:%.*]] = load i32, i32* [[GEP1_2]]
; CHECK-NEXT: [[V3:%.*]] = load i32, i32* [[GEP1_3]]
; CHECK-NEXT: [[Y0:%.*]] = add nsw i32 [[A0:%.*]], 1146
; CHECK-NEXT: [[Y1:%.*]] = add nsw i32 [[A1:%.*]], 146
; CHECK-NEXT: [[Y2:%.*]] = add nsw i32 [[A2:%.*]], 42
; CHECK-NEXT: [[Y3:%.*]] = add nsw i32 [[A3:%.*]], 0
; CHECK-NEXT: [[RES0:%.*]] = urem i32 [[V0]], [[Y0]]
; CHECK-NEXT: [[RES1:%.*]] = urem i32 [[V1]], [[Y1]]
; CHECK-NEXT: [[RES2:%.*]] = urem i32 [[V2]], [[Y2]]
; CHECK-NEXT: [[RES3:%.*]] = add nsw i32 [[V3]], [[Y3]]
; CHECK-NEXT: store i32 [[RES0]], i32* [[GEP2_0]]
; CHECK-NEXT: store i32 [[RES1]], i32* [[GEP2_1]]
; CHECK-NEXT: store i32 [[RES2]], i32* [[GEP2_2]]
; CHECK-NEXT: store i32 [[RES3]], i32* [[GEP2_3]]
; CHECK-NEXT: ret void
;
entry:
%gep1.0 = getelementptr i32, i32* %arr1, i32 0
%gep1.1 = getelementptr i32, i32* %arr1, i32 1
%gep1.2 = getelementptr i32, i32* %arr1, i32 2
%gep1.3 = getelementptr i32, i32* %arr1, i32 3
%gep2.0 = getelementptr i32, i32* %arr2, i32 0
%gep2.1 = getelementptr i32, i32* %arr2, i32 1
%gep2.2 = getelementptr i32, i32* %arr2, i32 2
%gep2.3 = getelementptr i32, i32* %arr2, i32 3
%v0 = load i32, i32* %gep1.0
%v1 = load i32, i32* %gep1.1
%v2 = load i32, i32* %gep1.2
%v3 = load i32, i32* %gep1.3
%y0 = add nsw i32 %a0, 1146
%y1 = add nsw i32 %a1, 146
%y2 = add nsw i32 %a2, 42
;; %y3 is zero if %a3 is zero
%y3 = add nsw i32 %a3, 0
%res0 = urem i32 %v0, %y0
%res1 = urem i32 %v1, %y1
%res2 = urem i32 %v2, %y2
;; As such, doing alternate shuffling would be incorrect:
;; %vurem = urem %v[0-3], %y[0-3]
;; %vadd = add nsw %v[0-3], %y[0-3]
;; %result = shuffle %vurem, %vadd, <mask>
;; would be illegal.
%res3 = add nsw i32 %v3, %y3
store i32 %res0, i32* %gep2.0
store i32 %res1, i32* %gep2.1
store i32 %res2, i32* %gep2.2
store i32 %res3, i32* %gep2.3
ret void
}
|
