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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s | FileCheck %s
target triple = "aarch64-unknown-linux-gnu"
; SCALABLE INSERTED INTO SCALABLE TESTS
define <vscale x 8 x i8> @vec_scalable_subvec_scalable_idx_zero_i8(<vscale x 8 x i8>* %a, <vscale x 4 x i8>* %b) #0 {
; CHECK-LABEL: vec_scalable_subvec_scalable_idx_zero_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: ld1b { z0.h }, p0/z, [x0]
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: ld1b { z1.s }, p0/z, [x1]
; CHECK-NEXT: uunpkhi z0.s, z0.h
; CHECK-NEXT: uzp1 z0.h, z1.h, z0.h
; CHECK-NEXT: ret
%vec = load <vscale x 8 x i8>, <vscale x 8 x i8>* %a
%subvec = load <vscale x 4 x i8>, <vscale x 4 x i8>* %b
%ins = call <vscale x 8 x i8> @llvm.experimental.vector.insert.nxv8i8.nxv4i8(<vscale x 8 x i8> %vec, <vscale x 4 x i8> %subvec, i64 0)
ret <vscale x 8 x i8> %ins
}
define <vscale x 8 x i8> @vec_scalable_subvec_scalable_idx_nonzero_i8(<vscale x 8 x i8>* %a, <vscale x 4 x i8>* %b) #0 {
; CHECK-LABEL: vec_scalable_subvec_scalable_idx_nonzero_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: ld1b { z0.h }, p0/z, [x0]
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: ld1b { z1.s }, p0/z, [x1]
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: uzp1 z0.h, z0.h, z1.h
; CHECK-NEXT: ret
%vec = load <vscale x 8 x i8>, <vscale x 8 x i8>* %a
%subvec = load <vscale x 4 x i8>, <vscale x 4 x i8>* %b
%ins = call <vscale x 8 x i8> @llvm.experimental.vector.insert.nxv8i8.nxv4i8(<vscale x 8 x i8> %vec, <vscale x 4 x i8> %subvec, i64 4)
ret <vscale x 8 x i8> %ins
}
define <vscale x 4 x i16> @vec_scalable_subvec_scalable_idx_zero_i16(<vscale x 4 x i16>* %a, <vscale x 2 x i16>* %b) #0 {
; CHECK-LABEL: vec_scalable_subvec_scalable_idx_zero_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: ld1h { z0.s }, p0/z, [x0]
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: ld1h { z1.d }, p0/z, [x1]
; CHECK-NEXT: uunpkhi z0.d, z0.s
; CHECK-NEXT: uzp1 z0.s, z1.s, z0.s
; CHECK-NEXT: ret
%vec = load <vscale x 4 x i16>, <vscale x 4 x i16>* %a
%subvec = load <vscale x 2 x i16>, <vscale x 2 x i16>* %b
%ins = call <vscale x 4 x i16> @llvm.experimental.vector.insert.nxv4i16.nxv2i16(<vscale x 4 x i16> %vec, <vscale x 2 x i16> %subvec, i64 0)
ret <vscale x 4 x i16> %ins
}
define <vscale x 4 x i16> @vec_scalable_subvec_scalable_idx_nonzero_i16(<vscale x 4 x i16>* %a, <vscale x 2 x i16>* %b) #0 {
; CHECK-LABEL: vec_scalable_subvec_scalable_idx_nonzero_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: ld1h { z0.s }, p0/z, [x0]
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: ld1h { z1.d }, p0/z, [x1]
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: uzp1 z0.s, z0.s, z1.s
; CHECK-NEXT: ret
%vec = load <vscale x 4 x i16>, <vscale x 4 x i16>* %a
%subvec = load <vscale x 2 x i16>, <vscale x 2 x i16>* %b
%ins = call <vscale x 4 x i16> @llvm.experimental.vector.insert.nxv4i16.nxv2i16(<vscale x 4 x i16> %vec, <vscale x 2 x i16> %subvec, i64 2)
ret <vscale x 4 x i16> %ins
}
; FIXED INSERTED INTO SCALABLE TESTS
define <vscale x 8 x i8> @vec_scalable_subvec_fixed_idx_zero_i8(<vscale x 8 x i8>* %a, <8 x i8>* %b) #0 {
; CHECK-LABEL: vec_scalable_subvec_fixed_idx_zero_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: ld1b { z0.h }, p0/z, [x0]
; CHECK-NEXT: ldr d1, [x1]
; CHECK-NEXT: ptrue p0.h, vl8
; CHECK-NEXT: ushll v1.8h, v1.8b, #0
; CHECK-NEXT: mov z0.h, p0/m, z1.h
; CHECK-NEXT: ret
%vec = load <vscale x 8 x i8>, <vscale x 8 x i8>* %a
%subvec = load <8 x i8>, <8 x i8>* %b
%ins = call <vscale x 8 x i8> @llvm.experimental.vector.insert.nxv8i8.v8i8(<vscale x 8 x i8> %vec, <8 x i8> %subvec, i64 0)
ret <vscale x 8 x i8> %ins
}
define <vscale x 8 x i8> @vec_scalable_subvec_fixed_idx_nonzero_i8(<vscale x 8 x i8>* %a, <8 x i8>* %b) #0 {
; CHECK-LABEL: vec_scalable_subvec_fixed_idx_nonzero_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: addvl sp, sp, #-1
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: cnth x8
; CHECK-NEXT: ld1b { z0.h }, p0/z, [x0]
; CHECK-NEXT: ldr d1, [x1]
; CHECK-NEXT: sub x8, x8, #8
; CHECK-NEXT: mov w9, #8
; CHECK-NEXT: cmp x8, #8
; CHECK-NEXT: csel x8, x8, x9, lo
; CHECK-NEXT: ushll v1.8h, v1.8b, #0
; CHECK-NEXT: lsl x8, x8, #1
; CHECK-NEXT: mov x9, sp
; CHECK-NEXT: st1h { z0.h }, p0, [sp]
; CHECK-NEXT: str q1, [x9, x8]
; CHECK-NEXT: ld1h { z0.h }, p0/z, [sp]
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%vec = load <vscale x 8 x i8>, <vscale x 8 x i8>* %a
%subvec = load <8 x i8>, <8 x i8>* %b
%ins = call <vscale x 8 x i8> @llvm.experimental.vector.insert.nxv8i8.v8i8(<vscale x 8 x i8> %vec, <8 x i8> %subvec, i64 8)
ret <vscale x 8 x i8> %ins
}
define <vscale x 4 x i16> @vec_scalable_subvec_fixed_idx_zero_i16(<vscale x 4 x i16>* %a, <4 x i16>* %b) #0 {
; CHECK-LABEL: vec_scalable_subvec_fixed_idx_zero_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: ld1h { z0.s }, p0/z, [x0]
; CHECK-NEXT: ldr d1, [x1]
; CHECK-NEXT: ptrue p0.s, vl4
; CHECK-NEXT: ushll v1.4s, v1.4h, #0
; CHECK-NEXT: mov z0.s, p0/m, z1.s
; CHECK-NEXT: ret
%vec = load <vscale x 4 x i16>, <vscale x 4 x i16>* %a
%subvec = load <4 x i16>, <4 x i16>* %b
%ins = call <vscale x 4 x i16> @llvm.experimental.vector.insert.nxv4i16.v4i16(<vscale x 4 x i16> %vec, <4 x i16> %subvec, i64 0)
ret <vscale x 4 x i16> %ins
}
define <vscale x 4 x i16> @vec_scalable_subvec_fixed_idx_nonzero_i16(<vscale x 4 x i16>* %a, <4 x i16>* %b) #0 {
; CHECK-LABEL: vec_scalable_subvec_fixed_idx_nonzero_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: addvl sp, sp, #-1
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: cntw x8
; CHECK-NEXT: ld1h { z0.s }, p0/z, [x0]
; CHECK-NEXT: ldr d1, [x1]
; CHECK-NEXT: sub x8, x8, #4
; CHECK-NEXT: mov w9, #4
; CHECK-NEXT: cmp x8, #4
; CHECK-NEXT: csel x8, x8, x9, lo
; CHECK-NEXT: ushll v1.4s, v1.4h, #0
; CHECK-NEXT: lsl x8, x8, #2
; CHECK-NEXT: mov x9, sp
; CHECK-NEXT: st1w { z0.s }, p0, [sp]
; CHECK-NEXT: str q1, [x9, x8]
; CHECK-NEXT: ld1w { z0.s }, p0/z, [sp]
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%vec = load <vscale x 4 x i16>, <vscale x 4 x i16>* %a
%subvec = load <4 x i16>, <4 x i16>* %b
%ins = call <vscale x 4 x i16> @llvm.experimental.vector.insert.nxv4i16.v4i16(<vscale x 4 x i16> %vec, <4 x i16> %subvec, i64 4)
ret <vscale x 4 x i16> %ins
}
define <vscale x 2 x i32> @vec_scalable_subvec_fixed_idx_zero_i32(<vscale x 2 x i32>* %a, <2 x i32>* %b) #0 {
; CHECK-LABEL: vec_scalable_subvec_fixed_idx_zero_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: ld1w { z0.d }, p0/z, [x0]
; CHECK-NEXT: ldr d1, [x1]
; CHECK-NEXT: ptrue p0.d, vl2
; CHECK-NEXT: ushll v1.2d, v1.2s, #0
; CHECK-NEXT: mov z0.d, p0/m, z1.d
; CHECK-NEXT: ret
%vec = load <vscale x 2 x i32>, <vscale x 2 x i32>* %a
%subvec = load <2 x i32>, <2 x i32>* %b
%ins = call <vscale x 2 x i32> @llvm.experimental.vector.insert.nxv2i32.v2i32(<vscale x 2 x i32> %vec, <2 x i32> %subvec, i64 0)
ret <vscale x 2 x i32> %ins
}
define <vscale x 2 x i32> @vec_scalable_subvec_fixed_idx_nonzero_i32(<vscale x 2 x i32>* %a, <2 x i32>* %b) #0 {
; CHECK-LABEL: vec_scalable_subvec_fixed_idx_nonzero_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: addvl sp, sp, #-1
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: cntd x8
; CHECK-NEXT: ld1w { z0.d }, p0/z, [x0]
; CHECK-NEXT: ldr d1, [x1]
; CHECK-NEXT: sub x8, x8, #2
; CHECK-NEXT: mov w9, #2
; CHECK-NEXT: cmp x8, #2
; CHECK-NEXT: csel x8, x8, x9, lo
; CHECK-NEXT: ushll v1.2d, v1.2s, #0
; CHECK-NEXT: lsl x8, x8, #3
; CHECK-NEXT: mov x9, sp
; CHECK-NEXT: st1d { z0.d }, p0, [sp]
; CHECK-NEXT: str q1, [x9, x8]
; CHECK-NEXT: ld1d { z0.d }, p0/z, [sp]
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%vec = load <vscale x 2 x i32>, <vscale x 2 x i32>* %a
%subvec = load <2 x i32>, <2 x i32>* %b
%ins = call <vscale x 2 x i32> @llvm.experimental.vector.insert.nxv2i32.v2i32(<vscale x 2 x i32> %vec, <2 x i32> %subvec, i64 2)
ret <vscale x 2 x i32> %ins
}
define <vscale x 2 x i32> @vec_scalable_subvec_fixed_idx_nonzero_large_i32(<vscale x 2 x i32>* %a, <8 x i32>* %b) #1 {
; CHECK-LABEL: vec_scalable_subvec_fixed_idx_nonzero_large_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: addvl sp, sp, #-1
; CHECK-NEXT: cntd x8
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: ptrue p1.s, vl8
; CHECK-NEXT: subs x8, x8, #8
; CHECK-NEXT: ld1w { z0.d }, p0/z, [x0]
; CHECK-NEXT: ld1w { z1.s }, p1/z, [x1]
; CHECK-NEXT: csel x8, xzr, x8, lo
; CHECK-NEXT: mov w9, #8
; CHECK-NEXT: cmp x8, #8
; CHECK-NEXT: csel x8, x8, x9, lo
; CHECK-NEXT: mov x9, sp
; CHECK-NEXT: uunpklo z1.d, z1.s
; CHECK-NEXT: st1d { z0.d }, p0, [sp]
; CHECK-NEXT: st1d { z1.d }, p0, [x9, x8, lsl #3]
; CHECK-NEXT: ld1d { z0.d }, p0/z, [sp]
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%vec = load <vscale x 2 x i32>, <vscale x 2 x i32>* %a
%subvec = load <8 x i32>, <8 x i32>* %b
%ins = call <vscale x 2 x i32> @llvm.experimental.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> %vec, <8 x i32> %subvec, i64 8)
ret <vscale x 2 x i32> %ins
}
declare <vscale x 8 x i8> @llvm.experimental.vector.insert.nxv8i8.nxv4i8(<vscale x 8 x i8>, <vscale x 4 x i8>, i64)
declare <vscale x 4 x i16> @llvm.experimental.vector.insert.nxv4i16.nxv2i16(<vscale x 4 x i16>, <vscale x 2 x i16>, i64)
declare <vscale x 8 x i8> @llvm.experimental.vector.insert.nxv8i8.v8i8(<vscale x 8 x i8>, <8 x i8>, i64)
declare <vscale x 4 x i16> @llvm.experimental.vector.insert.nxv4i16.v4i16(<vscale x 4 x i16>, <4 x i16>, i64)
declare <vscale x 2 x i32> @llvm.experimental.vector.insert.nxv2i32.v2i32(<vscale x 2 x i32>, <2 x i32>, i64)
declare <vscale x 2 x i32> @llvm.experimental.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32>, <8 x i32>, i64)
attributes #0 = { nounwind "target-features"="+sve" }
attributes #1 = { nounwind "target-features"="+sve" vscale_range(4,4) }
|
