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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
|
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 3
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=aarch64--linux-gnu -mattr=+sve < %s | FileCheck %s
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
define void @scalable_loads() {
; CHECK-LABEL: 'scalable_loads'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %res.nxv8i8 = load <vscale x 8 x i8>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %res.nxv16i8 = load <vscale x 16 x i8>, ptr undef, align 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %res.nxv32i8 = load <vscale x 32 x i8>, ptr undef, align 32
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %res.nxv1i64 = load <vscale x 1 x i64>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %res.nxv32i1 = load <vscale x 32 x i1>, ptr undef, align 4
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %res.nxv16i1 = load <vscale x 16 x i1>, ptr undef, align 2
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %res.nxv4i1 = load <vscale x 4 x i1>, ptr undef, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%res.nxv8i8 = load <vscale x 8 x i8>, ptr undef
%res.nxv16i8 = load <vscale x 16 x i8>, ptr undef
%res.nxv32i8 = load <vscale x 32 x i8>, ptr undef
%res.nxv1i64 = load <vscale x 1 x i64>, ptr undef
%res.nxv32i1 = load <vscale x 32 x i1>, ptr undef
%res.nxv16i1 = load <vscale x 16 x i1>, ptr undef
%res.nxv4i1 = load <vscale x 4 x i1>, ptr undef
ret void
}
define void @scalable_stores() {
; CHECK-LABEL: 'scalable_stores'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i8> undef, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 16 x i8> undef, ptr undef, align 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 32 x i8> undef, ptr undef, align 32
; CHECK-NEXT: Cost Model: Invalid cost for instruction: store <vscale x 1 x i64> undef, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 32 x i1> undef, ptr undef, align 4
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 16 x i1> undef, ptr undef, align 2
; CHECK-NEXT: Cost Model: Invalid cost for instruction: store <vscale x 4 x i1> undef, ptr undef, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
store <vscale x 8 x i8> undef, ptr undef
store <vscale x 16 x i8> undef, ptr undef
store <vscale x 32 x i8> undef, ptr undef
store <vscale x 1 x i64> undef, ptr undef
store <vscale x 32 x i1> undef, ptr undef
store <vscale x 16 x i1> undef, ptr undef
store <vscale x 4 x i1> undef, ptr undef
ret void
}
define void @scalable_ext_loads() {
; CHECK-LABEL: 'scalable_ext_loads'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv16i8 = load <vscale x 16 x i8>, ptr undef, align 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %zext.nxv16i8to16 = zext <vscale x 16 x i8> %load.nxv16i8 to <vscale x 16 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv8i8 = load <vscale x 8 x i8>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %zext.nxv8i8to16 = zext <vscale x 8 x i8> %load.nxv8i8 to <vscale x 8 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv4i8 = load <vscale x 4 x i8>, ptr undef, align 4
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %zext.nxv4i8to32 = zext <vscale x 4 x i8> %load.nxv4i8 to <vscale x 4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv2i8 = load <vscale x 2 x i8>, ptr undef, align 2
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %zext.nxv2i8to64 = zext <vscale x 2 x i8> %load.nxv2i8 to <vscale x 2 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv8i16 = load <vscale x 8 x i16>, ptr undef, align 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %zext.nxv8i16to32 = zext <vscale x 8 x i16> %load.nxv8i16 to <vscale x 8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv4i16 = load <vscale x 4 x i16>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %zext.nxv4i16to32 = zext <vscale x 4 x i16> %load.nxv4i16 to <vscale x 4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv2i16 = load <vscale x 2 x i16>, ptr undef, align 4
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %zext.nxv2i16to64 = zext <vscale x 2 x i16> %load.nxv2i16 to <vscale x 2 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv4i32 = load <vscale x 4 x i32>, ptr undef, align 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %zext.nxv4i32to64 = zext <vscale x 4 x i32> %load.nxv4i32 to <vscale x 4 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv2i32 = load <vscale x 2 x i32>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %zext.nxv2i32to64 = zext <vscale x 2 x i32> %load.nxv2i32 to <vscale x 2 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv4i8.2 = load <vscale x 4 x i8>, ptr undef, align 4
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %zext.nxv4i8to64 = zext <vscale x 4 x i8> %load.nxv4i8.2 to <vscale x 4 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv4i16.2 = load <vscale x 4 x i16>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %zext.nxv4i16to64 = zext <vscale x 4 x i16> %load.nxv4i16.2 to <vscale x 4 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv8i8.2 = load <vscale x 8 x i8>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %zext.nxv8i8to32 = zext <vscale x 8 x i8> %load.nxv8i8.2 to <vscale x 8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load.nxv8i8.3 = load <vscale x 8 x i8>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %zext.nxv8i8to64 = zext <vscale x 8 x i8> %load.nxv8i8.3 to <vscale x 8 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv16i8 = load <vscale x 16 x i8>, ptr undef, align 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %sext.nxv16i8to16 = sext <vscale x 16 x i8> %load2.nxv16i8 to <vscale x 16 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv8i8 = load <vscale x 8 x i8>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %sext.nxv8i8to16 = sext <vscale x 8 x i8> %load2.nxv8i8 to <vscale x 8 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv4i8 = load <vscale x 4 x i8>, ptr undef, align 4
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %sext.nxv4i8to32 = sext <vscale x 4 x i8> %load2.nxv4i8 to <vscale x 4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv2i8 = load <vscale x 2 x i8>, ptr undef, align 2
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %sext.nxv2i8to64 = sext <vscale x 2 x i8> %load2.nxv2i8 to <vscale x 2 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv8i16 = load <vscale x 8 x i16>, ptr undef, align 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %sext.nxv8i16to32 = sext <vscale x 8 x i16> %load2.nxv8i16 to <vscale x 8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv4i16 = load <vscale x 4 x i16>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %sext.nxv4i16to32 = sext <vscale x 4 x i16> %load2.nxv4i16 to <vscale x 4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv2i16 = load <vscale x 2 x i16>, ptr undef, align 4
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %sext.nxv2i16to64 = sext <vscale x 2 x i16> %load2.nxv2i16 to <vscale x 2 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv4i32 = load <vscale x 4 x i32>, ptr undef, align 16
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %sext.nxv4i32to64 = sext <vscale x 4 x i32> %load2.nxv4i32 to <vscale x 4 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv2i32 = load <vscale x 2 x i32>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %sext.nxv2i32to64 = sext <vscale x 2 x i32> %load2.nxv2i32 to <vscale x 2 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv4i8.2 = load <vscale x 4 x i8>, ptr undef, align 4
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sext.nxv4i8to64 = sext <vscale x 4 x i8> %load2.nxv4i8.2 to <vscale x 4 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv4i16.2 = load <vscale x 4 x i16>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sext.nxv4i16to64 = sext <vscale x 4 x i16> %load2.nxv4i16.2 to <vscale x 4 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv8i8.2 = load <vscale x 8 x i8>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sext.nxv8i8to32 = sext <vscale x 8 x i8> %load2.nxv8i8.2 to <vscale x 8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %load2.nxv8i8.3 = load <vscale x 8 x i8>, ptr undef, align 8
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %sext.nxv8i8to64 = sext <vscale x 8 x i8> %load2.nxv8i8.3 to <vscale x 8 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%load.nxv16i8 = load <vscale x 16 x i8>, ptr undef
%zext.nxv16i8to16 = zext <vscale x 16 x i8> %load.nxv16i8 to <vscale x 16 x i16>
%load.nxv8i8 = load <vscale x 8 x i8>, ptr undef
%zext.nxv8i8to16 = zext <vscale x 8 x i8> %load.nxv8i8 to <vscale x 8 x i16>
%load.nxv4i8 = load <vscale x 4 x i8>, ptr undef
%zext.nxv4i8to32 = zext <vscale x 4 x i8> %load.nxv4i8 to <vscale x 4 x i32>
%load.nxv2i8 = load <vscale x 2 x i8>, ptr undef
%zext.nxv2i8to64 = zext <vscale x 2 x i8> %load.nxv2i8 to <vscale x 2 x i64>
%load.nxv8i16 = load <vscale x 8 x i16>, ptr undef
%zext.nxv8i16to32 = zext <vscale x 8 x i16> %load.nxv8i16 to <vscale x 8 x i32>
%load.nxv4i16 = load <vscale x 4 x i16>, ptr undef
%zext.nxv4i16to32 = zext <vscale x 4 x i16> %load.nxv4i16 to <vscale x 4 x i32>
%load.nxv2i16 = load <vscale x 2 x i16>, ptr undef
%zext.nxv2i16to64 = zext <vscale x 2 x i16> %load.nxv2i16 to <vscale x 2 x i64>
%load.nxv4i32 = load <vscale x 4 x i32>, ptr undef
%zext.nxv4i32to64 = zext <vscale x 4 x i32> %load.nxv4i32 to <vscale x 4 x i64>
%load.nxv2i32 = load <vscale x 2 x i32>, ptr undef
%zext.nxv2i32to64 = zext <vscale x 2 x i32> %load.nxv2i32 to <vscale x 2 x i64>
%load.nxv4i8.2 = load <vscale x 4 x i8>, ptr undef
%zext.nxv4i8to64 = zext <vscale x 4 x i8> %load.nxv4i8.2 to <vscale x 4 x i64>
%load.nxv4i16.2 = load <vscale x 4 x i16>, ptr undef
%zext.nxv4i16to64 = zext <vscale x 4 x i16> %load.nxv4i16.2 to <vscale x 4 x i64>
%load.nxv8i8.2 = load <vscale x 8 x i8>, ptr undef
%zext.nxv8i8to32 = zext <vscale x 8 x i8> %load.nxv8i8.2 to <vscale x 8 x i32>
%load.nxv8i8.3 = load <vscale x 8 x i8>, ptr undef
%zext.nxv8i8to64 = zext <vscale x 8 x i8> %load.nxv8i8.3 to <vscale x 8 x i64>
%load2.nxv16i8 = load <vscale x 16 x i8>, ptr undef
%sext.nxv16i8to16 = sext <vscale x 16 x i8> %load2.nxv16i8 to <vscale x 16 x i16>
%load2.nxv8i8 = load <vscale x 8 x i8>, ptr undef
%sext.nxv8i8to16 = sext <vscale x 8 x i8> %load2.nxv8i8 to <vscale x 8 x i16>
%load2.nxv4i8 = load <vscale x 4 x i8>, ptr undef
%sext.nxv4i8to32 = sext <vscale x 4 x i8> %load2.nxv4i8 to <vscale x 4 x i32>
%load2.nxv2i8 = load <vscale x 2 x i8>, ptr undef
%sext.nxv2i8to64 = sext <vscale x 2 x i8> %load2.nxv2i8 to <vscale x 2 x i64>
%load2.nxv8i16 = load <vscale x 8 x i16>, ptr undef
%sext.nxv8i16to32 = sext <vscale x 8 x i16> %load2.nxv8i16 to <vscale x 8 x i32>
%load2.nxv4i16 = load <vscale x 4 x i16>, ptr undef
%sext.nxv4i16to32 = sext <vscale x 4 x i16> %load2.nxv4i16 to <vscale x 4 x i32>
%load2.nxv2i16 = load <vscale x 2 x i16>, ptr undef
%sext.nxv2i16to64 = sext <vscale x 2 x i16> %load2.nxv2i16 to <vscale x 2 x i64>
%load2.nxv4i32 = load <vscale x 4 x i32>, ptr undef
%sext.nxv4i32to64 = sext <vscale x 4 x i32> %load2.nxv4i32 to <vscale x 4 x i64>
%load2.nxv2i32 = load <vscale x 2 x i32>, ptr undef
%sext.nxv2i32to64 = sext <vscale x 2 x i32> %load2.nxv2i32 to <vscale x 2 x i64>
%load2.nxv4i8.2 = load <vscale x 4 x i8>, ptr undef
%sext.nxv4i8to64 = sext <vscale x 4 x i8> %load2.nxv4i8.2 to <vscale x 4 x i64>
%load2.nxv4i16.2 = load <vscale x 4 x i16>, ptr undef
%sext.nxv4i16to64 = sext <vscale x 4 x i16> %load2.nxv4i16.2 to <vscale x 4 x i64>
%load2.nxv8i8.2 = load <vscale x 8 x i8>, ptr undef
%sext.nxv8i8to32 = sext <vscale x 8 x i8> %load2.nxv8i8.2 to <vscale x 8 x i32>
%load2.nxv8i8.3 = load <vscale x 8 x i8>, ptr undef
%sext.nxv8i8to64 = sext <vscale x 8 x i8> %load2.nxv8i8.3 to <vscale x 8 x i64>
ret void
}
|
