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
143
144
145
146
147
|
; RUN: llc -O3 -mcpu=pwr8 -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
; RUN: llc -O3 -mcpu=pwr8 -disable-ppc-vsx-swap-removal -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck -check-prefix=NOOPTSWAP %s
; This test was generated from the following source:
;
; #define N 4096
; int ca[N] __attribute__((aligned(16)));
; int cb[N] __attribute__((aligned(16)));
; int cc[N] __attribute__((aligned(16)));
; int cd[N] __attribute__((aligned(16)));
;
; void foo ()
; {
; int i;
; for (i = 0; i < N; i++) {
; ca[i] = (cb[i] + cc[i]) * cd[i];
; }
; }
@cb = common global [4096 x i32] zeroinitializer, align 16
@cc = common global [4096 x i32] zeroinitializer, align 16
@cd = common global [4096 x i32] zeroinitializer, align 16
@ca = common global [4096 x i32] zeroinitializer, align 16
define void @foo() {
entry:
br label %vector.body
vector.body:
%index = phi i64 [ 0, %entry ], [ %index.next.3, %vector.body ]
%0 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cb, i64 0, i64 %index
%1 = bitcast i32* %0 to <4 x i32>*
%wide.load = load <4 x i32>, <4 x i32>* %1, align 16
%2 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cc, i64 0, i64 %index
%3 = bitcast i32* %2 to <4 x i32>*
%wide.load13 = load <4 x i32>, <4 x i32>* %3, align 16
%4 = add nsw <4 x i32> %wide.load13, %wide.load
%5 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cd, i64 0, i64 %index
%6 = bitcast i32* %5 to <4 x i32>*
%wide.load14 = load <4 x i32>, <4 x i32>* %6, align 16
%7 = mul nsw <4 x i32> %4, %wide.load14
%8 = getelementptr inbounds [4096 x i32], [4096 x i32]* @ca, i64 0, i64 %index
%9 = bitcast i32* %8 to <4 x i32>*
store <4 x i32> %7, <4 x i32>* %9, align 16
%index.next = add nuw nsw i64 %index, 4
%10 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cb, i64 0, i64 %index.next
%11 = bitcast i32* %10 to <4 x i32>*
%wide.load.1 = load <4 x i32>, <4 x i32>* %11, align 16
%12 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cc, i64 0, i64 %index.next
%13 = bitcast i32* %12 to <4 x i32>*
%wide.load13.1 = load <4 x i32>, <4 x i32>* %13, align 16
%14 = add nsw <4 x i32> %wide.load13.1, %wide.load.1
%15 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cd, i64 0, i64 %index.next
%16 = bitcast i32* %15 to <4 x i32>*
%wide.load14.1 = load <4 x i32>, <4 x i32>* %16, align 16
%17 = mul nsw <4 x i32> %14, %wide.load14.1
%18 = getelementptr inbounds [4096 x i32], [4096 x i32]* @ca, i64 0, i64 %index.next
%19 = bitcast i32* %18 to <4 x i32>*
store <4 x i32> %17, <4 x i32>* %19, align 16
%index.next.1 = add nuw nsw i64 %index.next, 4
%20 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cb, i64 0, i64 %index.next.1
%21 = bitcast i32* %20 to <4 x i32>*
%wide.load.2 = load <4 x i32>, <4 x i32>* %21, align 16
%22 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cc, i64 0, i64 %index.next.1
%23 = bitcast i32* %22 to <4 x i32>*
%wide.load13.2 = load <4 x i32>, <4 x i32>* %23, align 16
%24 = add nsw <4 x i32> %wide.load13.2, %wide.load.2
%25 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cd, i64 0, i64 %index.next.1
%26 = bitcast i32* %25 to <4 x i32>*
%wide.load14.2 = load <4 x i32>, <4 x i32>* %26, align 16
%27 = mul nsw <4 x i32> %24, %wide.load14.2
%28 = getelementptr inbounds [4096 x i32], [4096 x i32]* @ca, i64 0, i64 %index.next.1
%29 = bitcast i32* %28 to <4 x i32>*
store <4 x i32> %27, <4 x i32>* %29, align 16
%index.next.2 = add nuw nsw i64 %index.next.1, 4
%30 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cb, i64 0, i64 %index.next.2
%31 = bitcast i32* %30 to <4 x i32>*
%wide.load.3 = load <4 x i32>, <4 x i32>* %31, align 16
%32 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cc, i64 0, i64 %index.next.2
%33 = bitcast i32* %32 to <4 x i32>*
%wide.load13.3 = load <4 x i32>, <4 x i32>* %33, align 16
%34 = add nsw <4 x i32> %wide.load13.3, %wide.load.3
%35 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cd, i64 0, i64 %index.next.2
%36 = bitcast i32* %35 to <4 x i32>*
%wide.load14.3 = load <4 x i32>, <4 x i32>* %36, align 16
%37 = mul nsw <4 x i32> %34, %wide.load14.3
%38 = getelementptr inbounds [4096 x i32], [4096 x i32]* @ca, i64 0, i64 %index.next.2
%39 = bitcast i32* %38 to <4 x i32>*
store <4 x i32> %37, <4 x i32>* %39, align 16
%index.next.3 = add nuw nsw i64 %index.next.2, 4
%40 = icmp eq i64 %index.next.3, 4096
br i1 %40, label %for.end, label %vector.body
for.end:
ret void
}
; CHECK-LABEL: @foo
; CHECK-NOT: xxpermdi
; CHECK-NOT: xxswapd
; CHECK: lxvd2x
; CHECK: lxvd2x
; CHECK-DAG: lxvd2x
; CHECK-DAG: vadduwm
; CHECK: vmuluwm
; CHECK: stxvd2x
; CHECK: lxvd2x
; CHECK: lxvd2x
; CHECK-DAG: lxvd2x
; CHECK-DAG: vadduwm
; CHECK: vmuluwm
; CHECK: stxvd2x
; CHECK: lxvd2x
; CHECK: lxvd2x
; CHECK-DAG: lxvd2x
; CHECK-DAG: vadduwm
; CHECK: vmuluwm
; CHECK: stxvd2x
; CHECK: lxvd2x
; CHECK: lxvd2x
; CHECK-DAG: lxvd2x
; CHECK-DAG: vadduwm
; CHECK: vmuluwm
; CHECK: stxvd2x
; NOOPTSWAP-LABEL: @foo
; NOOPTSWAP: lxvd2x
; NOOPTSWAP-DAG: lxvd2x
; NOOPTSWAP-DAG: lxvd2x
; NOOPTSWAP-DAG: xxswapd
; NOOPTSWAP-DAG: xxswapd
; NOOPTSWAP-DAG: xxswapd
; NOOPTSWAP-DAG: vadduwm
; NOOPTSWAP: vmuluwm
; NOOPTSWAP: xxswapd
; NOOPTSWAP-DAG: xxswapd
; NOOPTSWAP-DAG: xxswapd
; NOOPTSWAP-DAG: stxvd2x
; NOOPTSWAP-DAG: stxvd2x
; NOOPTSWAP: stxvd2x
|
