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
| ; REQUIRES: asserts
; RUN: opt -loop-vectorize -S -mattr=avx512bw --debug-only=loop-vectorize < %s 2>&1| FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = global [10240 x i16] zeroinitializer, align 16
@B = global [10240 x i16] zeroinitializer, align 16
; Function Attrs: nounwind uwtable
define void @load_i16_stride2() {
;CHECK-LABEL: load_i16_stride2
;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 2 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 4 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 8 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 16 For instruction: %1 = load
;CHECK: Found an estimated cost of 2 for VF 32 For instruction: %1 = load
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%0 = shl nsw i64 %indvars.iv, 1
%arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
%1 = load i16, i16* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv
store i16 %1, i16* %arrayidx2, align 2
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 1024
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
define void @load_i16_stride3() {
;CHECK-LABEL: load_i16_stride3
;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 2 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 4 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 8 For instruction: %1 = load
;CHECK: Found an estimated cost of 2 for VF 16 For instruction: %1 = load
;CHECK: Found an estimated cost of 3 for VF 32 For instruction: %1 = load
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%0 = mul nsw i64 %indvars.iv, 3
%arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
%1 = load i16, i16* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv
store i16 %1, i16* %arrayidx2, align 2
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 1024
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
define void @load_i16_stride4() {
;CHECK-LABEL: load_i16_stride4
;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 2 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 4 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 8 For instruction: %1 = load
;CHECK: Found an estimated cost of 2 for VF 16 For instruction: %1 = load
;CHECK: Found an estimated cost of 5 for VF 32 For instruction: %1 = load
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%0 = shl nsw i64 %indvars.iv, 2
%arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
%1 = load i16, i16* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv
store i16 %1, i16* %arrayidx2, align 2
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 1024
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
define void @load_i16_stride5() {
;CHECK-LABEL: load_i16_stride5
;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 2 For instruction: %1 = load
;CHECK: Found an estimated cost of 1 for VF 4 For instruction: %1 = load
;CHECK: Found an estimated cost of 2 for VF 8 For instruction: %1 = load
;CHECK: Found an estimated cost of 3 for VF 16 For instruction: %1 = load
;CHECK: Found an estimated cost of 6 for VF 32 For instruction: %1 = load
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%0 = mul nsw i64 %indvars.iv, 5
%arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
%1 = load i16, i16* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv
store i16 %1, i16* %arrayidx2, align 2
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 1024
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
|