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
163
164
165
166
167
168
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+v,+m -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -mtriple=riscv64 -mattr=+v,+m -verify-machineinstrs < %s | FileCheck %s
define <512 x i8> @vadd_v512i8_zvl128(<512 x i8> %a, <512 x i8> %b) #0 {
; CHECK-LABEL: vadd_v512i8_zvl128:
; CHECK: # %bb.0:
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a2, vlenb
; CHECK-NEXT: li a4, 40
; CHECK-NEXT: mul a2, a2, a4
; CHECK-NEXT: sub sp, sp, a2
; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x28, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 40 * vlenb
; CHECK-NEXT: csrr a2, vlenb
; CHECK-NEXT: li a4, 24
; CHECK-NEXT: mul a2, a2, a4
; CHECK-NEXT: add a2, sp, a2
; CHECK-NEXT: addi a2, a2, 16
; CHECK-NEXT: vs8r.v v16, (a2) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a2, vlenb
; CHECK-NEXT: slli a2, a2, 5
; CHECK-NEXT: add a2, sp, a2
; CHECK-NEXT: addi a2, a2, 16
; CHECK-NEXT: vs8r.v v8, (a2) # Unknown-size Folded Spill
; CHECK-NEXT: li a2, 128
; CHECK-NEXT: vsetvli zero, a2, e8, m8, ta, ma
; CHECK-NEXT: addi a2, a3, 128
; CHECK-NEXT: addi a4, a3, 384
; CHECK-NEXT: vle8.v v8, (a4)
; CHECK-NEXT: csrr a4, vlenb
; CHECK-NEXT: slli a4, a4, 4
; CHECK-NEXT: add a4, sp, a4
; CHECK-NEXT: addi a4, a4, 16
; CHECK-NEXT: vs8r.v v8, (a4) # Unknown-size Folded Spill
; CHECK-NEXT: addi a4, a1, 128
; CHECK-NEXT: vle8.v v8, (a1)
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: addi a1, a3, 256
; CHECK-NEXT: vle8.v v8, (a1)
; CHECK-NEXT: vle8.v v16, (a4)
; CHECK-NEXT: vle8.v v24, (a2)
; CHECK-NEXT: vle8.v v0, (a3)
; CHECK-NEXT: addi a1, sp, 16
; CHECK-NEXT: vs8r.v v0, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vl8r.v v0, (a1) # Unknown-size Folded Reload
; CHECK-NEXT: vadd.vv v8, v0, v8
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 4
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
; CHECK-NEXT: vadd.vv v16, v16, v8
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: li a2, 24
; CHECK-NEXT: mul a1, a1, a2
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
; CHECK-NEXT: vadd.vv v8, v8, v24
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 5
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload
; CHECK-NEXT: addi a1, sp, 16
; CHECK-NEXT: vl8r.v v0, (a1) # Unknown-size Folded Reload
; CHECK-NEXT: vadd.vv v0, v24, v0
; CHECK-NEXT: vse8.v v0, (a0)
; CHECK-NEXT: addi a1, a0, 384
; CHECK-NEXT: vse8.v v16, (a1)
; CHECK-NEXT: addi a1, a0, 256
; CHECK-NEXT: csrr a2, vlenb
; CHECK-NEXT: slli a2, a2, 3
; CHECK-NEXT: add a2, sp, a2
; CHECK-NEXT: addi a2, a2, 16
; CHECK-NEXT: vl8r.v v16, (a2) # Unknown-size Folded Reload
; CHECK-NEXT: vse8.v v16, (a1)
; CHECK-NEXT: addi a0, a0, 128
; CHECK-NEXT: vse8.v v8, (a0)
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: li a1, 40
; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
%c = add <512 x i8> %a, %b
ret <512 x i8> %c
}
define <512 x i8> @vadd_v512i8_zvl256(<512 x i8> %a, <512 x i8> %b) #1 {
; CHECK-LABEL: vadd_v512i8_zvl256:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a1, a0, 256
; CHECK-NEXT: li a2, 256
; CHECK-NEXT: vsetvli zero, a2, e8, m8, ta, ma
; CHECK-NEXT: vle8.v v24, (a0)
; CHECK-NEXT: vle8.v v0, (a1)
; CHECK-NEXT: vadd.vv v8, v8, v24
; CHECK-NEXT: vadd.vv v16, v16, v0
; CHECK-NEXT: ret
%c = add <512 x i8> %a, %b
ret <512 x i8> %c
}
define <512 x i8> @vadd_v512i8_zvl512(<512 x i8> %a, <512 x i8> %b) #2 {
; CHECK-LABEL: vadd_v512i8_zvl512:
; CHECK: # %bb.0:
; CHECK-NEXT: li a0, 512
; CHECK-NEXT: vsetvli zero, a0, e8, m8, ta, ma
; CHECK-NEXT: vadd.vv v8, v8, v16
; CHECK-NEXT: ret
%c = add <512 x i8> %a, %b
ret <512 x i8> %c
}
define <512 x i8> @vadd_v512i8_zvl1024(<512 x i8> %a, <512 x i8> %b) #3 {
; CHECK-LABEL: vadd_v512i8_zvl1024:
; CHECK: # %bb.0:
; CHECK-NEXT: li a0, 512
; CHECK-NEXT: vsetvli zero, a0, e8, m4, ta, ma
; CHECK-NEXT: vadd.vv v8, v8, v12
; CHECK-NEXT: ret
%c = add <512 x i8> %a, %b
ret <512 x i8> %c
}
define <512 x i8> @vadd_v512i8_zvl2048(<512 x i8> %a, <512 x i8> %b) #4 {
; CHECK-LABEL: vadd_v512i8_zvl2048:
; CHECK: # %bb.0:
; CHECK-NEXT: li a0, 512
; CHECK-NEXT: vsetvli zero, a0, e8, m2, ta, ma
; CHECK-NEXT: vadd.vv v8, v8, v10
; CHECK-NEXT: ret
%c = add <512 x i8> %a, %b
ret <512 x i8> %c
}
define <512 x i8> @vadd_v512i8_zvl4096(<512 x i8> %a, <512 x i8> %b) #5 {
; CHECK-LABEL: vadd_v512i8_zvl4096:
; CHECK: # %bb.0:
; CHECK-NEXT: li a0, 512
; CHECK-NEXT: vsetvli zero, a0, e8, m1, ta, ma
; CHECK-NEXT: vadd.vv v8, v8, v9
; CHECK-NEXT: ret
%c = add <512 x i8> %a, %b
ret <512 x i8> %c
}
attributes #0 = { vscale_range(2,1024) }
attributes #1 = { vscale_range(4,1024) }
attributes #2 = { vscale_range(8,1024) }
attributes #3 = { vscale_range(16,1024) }
attributes #4 = { vscale_range(32,1024) }
attributes #5 = { vscale_range(64,1024) }
|
