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
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv64 -mattr=+v,+d -mattr=+d -O0 < %s \
; RUN: | FileCheck --check-prefix=SPILL-O0 %s
; RUN: llc -mtriple=riscv64 -mattr=+v,+d -mattr=+d -O2 < %s \
; RUN: | FileCheck --check-prefix=SPILL-O2 %s
; RUN: llc -mtriple=riscv64 -mattr=+v,+d -mattr=+d -riscv-v-vector-bits-max=128 -O2 < %s \
; RUN: | FileCheck --check-prefix=SPILL-O2-VLEN128 %s
; RUN: llc -mtriple=riscv64 -mattr=+v,+d,+zcmp -O2 < %s \
; RUN: | FileCheck --check-prefix=SPILL-O2-ZCMP %s
; RUN: llc -mtriple=riscv64 -mattr=+v,+d,+prefer-vsetvli-over-read-vlenb -O0 < %s \
; RUN: | FileCheck --check-prefix=SPILL-O0-VSETVLI %s
; RUN: llc -mtriple=riscv64 -mattr=+v,+d,+prefer-vsetvli-over-read-vlenb -O2 < %s \
; RUN: | FileCheck --check-prefix=SPILL-O2-VSETVLI %s
; RUN: llc -mtriple=riscv64 -mattr=+v,+d,+zcmp,+prefer-vsetvli-over-read-vlenb -O2 < %s \
; RUN: | FileCheck --check-prefix=SPILL-O2-ZCMP-VSETVLI %s
@.str = private unnamed_addr constant [6 x i8] c"hello\00", align 1
define <vscale x 1 x double> @foo(<vscale x 1 x double> %a, <vscale x 1 x double> %b, <vscale x 1 x double> %c, i64 %gvl) nounwind
; SPILL-O0-LABEL: foo:
; SPILL-O0: # %bb.0:
; SPILL-O0-NEXT: addi sp, sp, -48
; SPILL-O0-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; SPILL-O0-NEXT: csrr a1, vlenb
; SPILL-O0-NEXT: slli a1, a1, 1
; SPILL-O0-NEXT: sub sp, sp, a1
; SPILL-O0-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
; SPILL-O0-NEXT: vsetivli zero, 1, e8, m1, ta, ma
; SPILL-O0-NEXT: vmv1r.v v10, v9
; SPILL-O0-NEXT: vmv1r.v v9, v8
; SPILL-O0-NEXT: csrr a1, vlenb
; SPILL-O0-NEXT: add a1, sp, a1
; SPILL-O0-NEXT: addi a1, a1, 32
; SPILL-O0-NEXT: vs1r.v v9, (a1) # vscale x 8-byte Folded Spill
; SPILL-O0-NEXT: # implicit-def: $v8
; SPILL-O0-NEXT: vsetvli zero, a0, e64, m1, tu, ma
; SPILL-O0-NEXT: vfadd.vv v8, v9, v10
; SPILL-O0-NEXT: addi a0, sp, 32
; SPILL-O0-NEXT: vs1r.v v8, (a0) # vscale x 8-byte Folded Spill
; SPILL-O0-NEXT: lui a0, %hi(.L.str)
; SPILL-O0-NEXT: addi a0, a0, %lo(.L.str)
; SPILL-O0-NEXT: call puts
; SPILL-O0-NEXT: addi a1, sp, 32
; SPILL-O0-NEXT: vl1r.v v10, (a1) # vscale x 8-byte Folded Reload
; SPILL-O0-NEXT: csrr a1, vlenb
; SPILL-O0-NEXT: add a1, sp, a1
; SPILL-O0-NEXT: addi a1, a1, 32
; SPILL-O0-NEXT: vl1r.v v9, (a1) # vscale x 8-byte Folded Reload
; SPILL-O0-NEXT: # kill: def $x11 killed $x10
; SPILL-O0-NEXT: ld a0, 16(sp) # 8-byte Folded Reload
; SPILL-O0-NEXT: # implicit-def: $v8
; SPILL-O0-NEXT: vsetvli zero, a0, e64, m1, tu, ma
; SPILL-O0-NEXT: vfadd.vv v8, v9, v10
; SPILL-O0-NEXT: csrr a0, vlenb
; SPILL-O0-NEXT: slli a0, a0, 1
; SPILL-O0-NEXT: add sp, sp, a0
; SPILL-O0-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; SPILL-O0-NEXT: addi sp, sp, 48
; SPILL-O0-NEXT: ret
;
; SPILL-O2-LABEL: foo:
; SPILL-O2: # %bb.0:
; SPILL-O2-NEXT: addi sp, sp, -32
; SPILL-O2-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; SPILL-O2-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; SPILL-O2-NEXT: csrr a1, vlenb
; SPILL-O2-NEXT: slli a1, a1, 1
; SPILL-O2-NEXT: sub sp, sp, a1
; SPILL-O2-NEXT: mv s0, a0
; SPILL-O2-NEXT: addi a1, sp, 16
; SPILL-O2-NEXT: vs1r.v v8, (a1) # vscale x 8-byte Folded Spill
; SPILL-O2-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; SPILL-O2-NEXT: vfadd.vv v9, v8, v9
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: add a0, sp, a0
; SPILL-O2-NEXT: addi a0, a0, 16
; SPILL-O2-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
; SPILL-O2-NEXT: lui a0, %hi(.L.str)
; SPILL-O2-NEXT: addi a0, a0, %lo(.L.str)
; SPILL-O2-NEXT: call puts
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: add a0, sp, a0
; SPILL-O2-NEXT: addi a0, a0, 16
; SPILL-O2-NEXT: vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
; SPILL-O2-NEXT: addi a0, sp, 16
; SPILL-O2-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
; SPILL-O2-NEXT: vsetvli zero, s0, e64, m1, ta, ma
; SPILL-O2-NEXT: vfadd.vv v8, v9, v8
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: slli a0, a0, 1
; SPILL-O2-NEXT: add sp, sp, a0
; SPILL-O2-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; SPILL-O2-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; SPILL-O2-NEXT: addi sp, sp, 32
; SPILL-O2-NEXT: ret
;
; SPILL-O2-VLEN128-LABEL: foo:
; SPILL-O2-VLEN128: # %bb.0:
; SPILL-O2-VLEN128-NEXT: addi sp, sp, -32
; SPILL-O2-VLEN128-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; SPILL-O2-VLEN128-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; SPILL-O2-VLEN128-NEXT: addi sp, sp, -32
; SPILL-O2-VLEN128-NEXT: mv s0, a0
; SPILL-O2-VLEN128-NEXT: addi a1, sp, 16
; SPILL-O2-VLEN128-NEXT: vs1r.v v8, (a1) # vscale x 8-byte Folded Spill
; SPILL-O2-VLEN128-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; SPILL-O2-VLEN128-NEXT: vfadd.vv v9, v8, v9
; SPILL-O2-VLEN128-NEXT: addi a0, sp, 32
; SPILL-O2-VLEN128-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
; SPILL-O2-VLEN128-NEXT: lui a0, %hi(.L.str)
; SPILL-O2-VLEN128-NEXT: addi a0, a0, %lo(.L.str)
; SPILL-O2-VLEN128-NEXT: call puts
; SPILL-O2-VLEN128-NEXT: addi a0, sp, 32
; SPILL-O2-VLEN128-NEXT: vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
; SPILL-O2-VLEN128-NEXT: addi a0, sp, 16
; SPILL-O2-VLEN128-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
; SPILL-O2-VLEN128-NEXT: vsetvli zero, s0, e64, m1, ta, ma
; SPILL-O2-VLEN128-NEXT: vfadd.vv v8, v9, v8
; SPILL-O2-VLEN128-NEXT: addi sp, sp, 32
; SPILL-O2-VLEN128-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; SPILL-O2-VLEN128-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; SPILL-O2-VLEN128-NEXT: addi sp, sp, 32
; SPILL-O2-VLEN128-NEXT: ret
;
; SPILL-O2-ZCMP-LABEL: foo:
; SPILL-O2-ZCMP: # %bb.0:
; SPILL-O2-ZCMP-NEXT: cm.push {ra, s0}, -32
; SPILL-O2-ZCMP-NEXT: csrr a1, vlenb
; SPILL-O2-ZCMP-NEXT: slli a1, a1, 1
; SPILL-O2-ZCMP-NEXT: sub sp, sp, a1
; SPILL-O2-ZCMP-NEXT: mv s0, a0
; SPILL-O2-ZCMP-NEXT: addi a1, sp, 16
; SPILL-O2-ZCMP-NEXT: vs1r.v v8, (a1) # vscale x 8-byte Folded Spill
; SPILL-O2-ZCMP-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; SPILL-O2-ZCMP-NEXT: vfadd.vv v9, v8, v9
; SPILL-O2-ZCMP-NEXT: csrr a0, vlenb
; SPILL-O2-ZCMP-NEXT: add a0, a0, sp
; SPILL-O2-ZCMP-NEXT: addi a0, a0, 16
; SPILL-O2-ZCMP-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
; SPILL-O2-ZCMP-NEXT: lui a0, %hi(.L.str)
; SPILL-O2-ZCMP-NEXT: addi a0, a0, %lo(.L.str)
; SPILL-O2-ZCMP-NEXT: call puts
; SPILL-O2-ZCMP-NEXT: csrr a0, vlenb
; SPILL-O2-ZCMP-NEXT: add a0, a0, sp
; SPILL-O2-ZCMP-NEXT: addi a0, a0, 16
; SPILL-O2-ZCMP-NEXT: vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
; SPILL-O2-ZCMP-NEXT: addi a0, sp, 16
; SPILL-O2-ZCMP-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
; SPILL-O2-ZCMP-NEXT: vsetvli zero, s0, e64, m1, ta, ma
; SPILL-O2-ZCMP-NEXT: vfadd.vv v8, v9, v8
; SPILL-O2-ZCMP-NEXT: csrr a0, vlenb
; SPILL-O2-ZCMP-NEXT: slli a0, a0, 1
; SPILL-O2-ZCMP-NEXT: add sp, sp, a0
; SPILL-O2-ZCMP-NEXT: cm.popret {ra, s0}, 32
;
; SPILL-O0-VSETVLI-LABEL: foo:
; SPILL-O0-VSETVLI: # %bb.0:
; SPILL-O0-VSETVLI-NEXT: addi sp, sp, -48
; SPILL-O0-VSETVLI-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; SPILL-O0-VSETVLI-NEXT: vsetvli a1, zero, e8, m2, ta, ma
; SPILL-O0-VSETVLI-NEXT: sub sp, sp, a1
; SPILL-O0-VSETVLI-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
; SPILL-O0-VSETVLI-NEXT: vsetivli zero, 1, e8, m1, ta, ma
; SPILL-O0-VSETVLI-NEXT: vmv1r.v v10, v9
; SPILL-O0-VSETVLI-NEXT: vmv1r.v v9, v8
; SPILL-O0-VSETVLI-NEXT: csrr a1, vlenb
; SPILL-O0-VSETVLI-NEXT: add a1, sp, a1
; SPILL-O0-VSETVLI-NEXT: addi a1, a1, 32
; SPILL-O0-VSETVLI-NEXT: vs1r.v v9, (a1) # vscale x 8-byte Folded Spill
; SPILL-O0-VSETVLI-NEXT: # implicit-def: $v8
; SPILL-O0-VSETVLI-NEXT: vsetvli zero, a0, e64, m1, tu, ma
; SPILL-O0-VSETVLI-NEXT: vfadd.vv v8, v9, v10
; SPILL-O0-VSETVLI-NEXT: addi a0, sp, 32
; SPILL-O0-VSETVLI-NEXT: vs1r.v v8, (a0) # vscale x 8-byte Folded Spill
; SPILL-O0-VSETVLI-NEXT: lui a0, %hi(.L.str)
; SPILL-O0-VSETVLI-NEXT: addi a0, a0, %lo(.L.str)
; SPILL-O0-VSETVLI-NEXT: call puts
; SPILL-O0-VSETVLI-NEXT: addi a1, sp, 32
; SPILL-O0-VSETVLI-NEXT: vl1r.v v10, (a1) # vscale x 8-byte Folded Reload
; SPILL-O0-VSETVLI-NEXT: csrr a1, vlenb
; SPILL-O0-VSETVLI-NEXT: add a1, sp, a1
; SPILL-O0-VSETVLI-NEXT: addi a1, a1, 32
; SPILL-O0-VSETVLI-NEXT: vl1r.v v9, (a1) # vscale x 8-byte Folded Reload
; SPILL-O0-VSETVLI-NEXT: # kill: def $x11 killed $x10
; SPILL-O0-VSETVLI-NEXT: ld a0, 16(sp) # 8-byte Folded Reload
; SPILL-O0-VSETVLI-NEXT: # implicit-def: $v8
; SPILL-O0-VSETVLI-NEXT: vsetvli zero, a0, e64, m1, tu, ma
; SPILL-O0-VSETVLI-NEXT: vfadd.vv v8, v9, v10
; SPILL-O0-VSETVLI-NEXT: vsetvli a0, zero, e8, m2, ta, ma
; SPILL-O0-VSETVLI-NEXT: add sp, sp, a0
; SPILL-O0-VSETVLI-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; SPILL-O0-VSETVLI-NEXT: addi sp, sp, 48
; SPILL-O0-VSETVLI-NEXT: ret
;
; SPILL-O2-VSETVLI-LABEL: foo:
; SPILL-O2-VSETVLI: # %bb.0:
; SPILL-O2-VSETVLI-NEXT: addi sp, sp, -32
; SPILL-O2-VSETVLI-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; SPILL-O2-VSETVLI-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; SPILL-O2-VSETVLI-NEXT: vsetvli a1, zero, e8, m2, ta, ma
; SPILL-O2-VSETVLI-NEXT: sub sp, sp, a1
; SPILL-O2-VSETVLI-NEXT: mv s0, a0
; SPILL-O2-VSETVLI-NEXT: addi a1, sp, 16
; SPILL-O2-VSETVLI-NEXT: vs1r.v v8, (a1) # vscale x 8-byte Folded Spill
; SPILL-O2-VSETVLI-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; SPILL-O2-VSETVLI-NEXT: vfadd.vv v9, v8, v9
; SPILL-O2-VSETVLI-NEXT: csrr a0, vlenb
; SPILL-O2-VSETVLI-NEXT: add a0, sp, a0
; SPILL-O2-VSETVLI-NEXT: addi a0, a0, 16
; SPILL-O2-VSETVLI-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
; SPILL-O2-VSETVLI-NEXT: lui a0, %hi(.L.str)
; SPILL-O2-VSETVLI-NEXT: addi a0, a0, %lo(.L.str)
; SPILL-O2-VSETVLI-NEXT: call puts
; SPILL-O2-VSETVLI-NEXT: csrr a0, vlenb
; SPILL-O2-VSETVLI-NEXT: add a0, sp, a0
; SPILL-O2-VSETVLI-NEXT: addi a0, a0, 16
; SPILL-O2-VSETVLI-NEXT: vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
; SPILL-O2-VSETVLI-NEXT: addi a0, sp, 16
; SPILL-O2-VSETVLI-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
; SPILL-O2-VSETVLI-NEXT: vsetvli zero, s0, e64, m1, ta, ma
; SPILL-O2-VSETVLI-NEXT: vfadd.vv v8, v9, v8
; SPILL-O2-VSETVLI-NEXT: vsetvli a0, zero, e8, m2, ta, ma
; SPILL-O2-VSETVLI-NEXT: add sp, sp, a0
; SPILL-O2-VSETVLI-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; SPILL-O2-VSETVLI-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; SPILL-O2-VSETVLI-NEXT: addi sp, sp, 32
; SPILL-O2-VSETVLI-NEXT: ret
;
; SPILL-O2-ZCMP-VSETVLI-LABEL: foo:
; SPILL-O2-ZCMP-VSETVLI: # %bb.0:
; SPILL-O2-ZCMP-VSETVLI-NEXT: cm.push {ra, s0}, -32
; SPILL-O2-ZCMP-VSETVLI-NEXT: vsetvli a1, zero, e8, m2, ta, ma
; SPILL-O2-ZCMP-VSETVLI-NEXT: sub sp, sp, a1
; SPILL-O2-ZCMP-VSETVLI-NEXT: mv s0, a0
; SPILL-O2-ZCMP-VSETVLI-NEXT: addi a1, sp, 16
; SPILL-O2-ZCMP-VSETVLI-NEXT: vs1r.v v8, (a1) # vscale x 8-byte Folded Spill
; SPILL-O2-ZCMP-VSETVLI-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; SPILL-O2-ZCMP-VSETVLI-NEXT: vfadd.vv v9, v8, v9
; SPILL-O2-ZCMP-VSETVLI-NEXT: csrr a0, vlenb
; SPILL-O2-ZCMP-VSETVLI-NEXT: add a0, a0, sp
; SPILL-O2-ZCMP-VSETVLI-NEXT: addi a0, a0, 16
; SPILL-O2-ZCMP-VSETVLI-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
; SPILL-O2-ZCMP-VSETVLI-NEXT: lui a0, %hi(.L.str)
; SPILL-O2-ZCMP-VSETVLI-NEXT: addi a0, a0, %lo(.L.str)
; SPILL-O2-ZCMP-VSETVLI-NEXT: call puts
; SPILL-O2-ZCMP-VSETVLI-NEXT: csrr a0, vlenb
; SPILL-O2-ZCMP-VSETVLI-NEXT: add a0, a0, sp
; SPILL-O2-ZCMP-VSETVLI-NEXT: addi a0, a0, 16
; SPILL-O2-ZCMP-VSETVLI-NEXT: vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
; SPILL-O2-ZCMP-VSETVLI-NEXT: addi a0, sp, 16
; SPILL-O2-ZCMP-VSETVLI-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
; SPILL-O2-ZCMP-VSETVLI-NEXT: vsetvli zero, s0, e64, m1, ta, ma
; SPILL-O2-ZCMP-VSETVLI-NEXT: vfadd.vv v8, v9, v8
; SPILL-O2-ZCMP-VSETVLI-NEXT: vsetvli a0, zero, e8, m2, ta, ma
; SPILL-O2-ZCMP-VSETVLI-NEXT: add sp, sp, a0
; SPILL-O2-ZCMP-VSETVLI-NEXT: cm.popret {ra, s0}, 32
{
%x = call <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> %a, <vscale x 1 x double> %b, i64 7, i64 %gvl)
%call = call signext i32 @puts(ptr @.str)
%z = call <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> %a, <vscale x 1 x double> %x, i64 7, i64 %gvl)
ret <vscale x 1 x double> %z
}
declare <vscale x 1 x double> @llvm.riscv.vfadd.nxv1f64.nxv1f64(<vscale x 1 x double> %passthru, <vscale x 1 x double> %a, <vscale x 1 x double> %b, i64, i64 %gvl)
declare i32 @puts(ptr);
|
