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
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-none-eabi | FileCheck %s
; float16x4_t select_64(float16x4_t a, float16x4_t b, uint16x4_t c) { return vbsl_u16(c, a, b); }
define <4 x half> @select_64(<4 x half> %a, <4 x half> %b, <4 x i16> %c) #0 {
; CHECK-LABEL: select_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: bif v0.8b, v1.8b, v2.8b
; CHECK-NEXT: ret
entry:
%0 = bitcast <4 x half> %a to <4 x i16>
%1 = bitcast <4 x half> %b to <4 x i16>
%vbsl3.i = and <4 x i16> %0, %c
%2 = xor <4 x i16> %c, <i16 -1, i16 -1, i16 -1, i16 -1>
%vbsl4.i = and <4 x i16> %1, %2
%vbsl5.i = or <4 x i16> %vbsl3.i, %vbsl4.i
%3 = bitcast <4 x i16> %vbsl5.i to <4 x half>
ret <4 x half> %3
}
; float16x8_t select_128(float16x8_t a, float16x8_t b, uint16x8_t c) { return vbslq_u16(c, a, b); }
define <8 x half> @select_128(<8 x half> %a, <8 x half> %b, <8 x i16> %c) #0 {
; CHECK-LABEL: select_128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: bif v0.16b, v1.16b, v2.16b
; CHECK-NEXT: ret
entry:
%0 = bitcast <8 x half> %a to <8 x i16>
%1 = bitcast <8 x half> %b to <8 x i16>
%vbsl3.i = and <8 x i16> %0, %c
%2 = xor <8 x i16> %c, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
%vbsl4.i = and <8 x i16> %1, %2
%vbsl5.i = or <8 x i16> %vbsl3.i, %vbsl4.i
%3 = bitcast <8 x i16> %vbsl5.i to <8 x half>
ret <8 x half> %3
}
; float16x4_t lane_64_64(float16x4_t a, float16x4_t b) {
; return vcopy_lane_s16(a, 1, b, 2);
; }
define <4 x half> @lane_64_64(<4 x half> %a, <4 x half> %b) #0 {
; CHECK-LABEL: lane_64_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT: mov v0.h[1], v1.h[2]
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
entry:
%0 = shufflevector <4 x half> %a, <4 x half> %b, <4 x i32> <i32 0, i32 6, i32 2, i32 3>
ret <4 x half> %0
}
; float16x8_t lane_128_64(float16x8_t a, float16x4_t b) {
; return vcopyq_lane_s16(a, 1, b, 2);
; }
define <8 x half> @lane_128_64(<8 x half> %a, <4 x half> %b) #0 {
; CHECK-LABEL: lane_128_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT: mov v0.h[1], v1.h[2]
; CHECK-NEXT: ret
entry:
%0 = bitcast <4 x half> %b to <4 x i16>
%vget_lane = extractelement <4 x i16> %0, i32 2
%1 = bitcast <8 x half> %a to <8 x i16>
%vset_lane = insertelement <8 x i16> %1, i16 %vget_lane, i32 1
%2 = bitcast <8 x i16> %vset_lane to <8 x half>
ret <8 x half> %2
}
; float16x4_t lane_64_128(float16x4_t a, float16x8_t b) {
; return vcopy_laneq_s16(a, 3, b, 5);
; }
define <4 x half> @lane_64_128(<4 x half> %a, <8 x half> %b) #0 {
; CHECK-LABEL: lane_64_128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: mov v0.h[3], v1.h[5]
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
entry:
%0 = bitcast <8 x half> %b to <8 x i16>
%vgetq_lane = extractelement <8 x i16> %0, i32 5
%1 = bitcast <4 x half> %a to <4 x i16>
%vset_lane = insertelement <4 x i16> %1, i16 %vgetq_lane, i32 3
%2 = bitcast <4 x i16> %vset_lane to <4 x half>
ret <4 x half> %2
}
; float16x8_t lane_128_128(float16x8_t a, float16x8_t b) {
; return vcopyq_laneq_s16(a, 3, b, 5);
; }
define <8 x half> @lane_128_128(<8 x half> %a, <8 x half> %b) #0 {
; CHECK-LABEL: lane_128_128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov v0.h[3], v1.h[5]
; CHECK-NEXT: ret
entry:
%0 = shufflevector <8 x half> %a, <8 x half> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 13, i32 4, i32 5, i32 6, i32 7>
ret <8 x half> %0
}
; float16x4_t ext_64(float16x4_t a, float16x4_t b) {
; return vext_s16(a, b, 3);
; }
define <4 x half> @ext_64(<4 x half> %a, <4 x half> %b) #0 {
; CHECK-LABEL: ext_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ext v0.8b, v0.8b, v1.8b, #6
; CHECK-NEXT: ret
entry:
%0 = shufflevector <4 x half> %a, <4 x half> %b, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
ret <4 x half> %0
}
; float16x8_t ext_128(float16x8_t a, float16x8_t b) {
; return vextq_s16(a, b, 3);
; }
define <8 x half> @ext_128(<8 x half> %a, <8 x half> %b) #0 {
; CHECK-LABEL: ext_128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ext v0.16b, v0.16b, v1.16b, #6
; CHECK-NEXT: ret
entry:
%0 = shufflevector <8 x half> %a, <8 x half> %b, <8 x i32> <i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10>
ret <8 x half> %0
}
; float16x4_t rev32_64(float16x4_t a) {
; return vrev32_s16(a);
; }
define <4 x half> @rev32_64(<4 x half> %a) #0 {
; CHECK-LABEL: rev32_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rev32 v0.4h, v0.4h
; CHECK-NEXT: ret
entry:
%0 = shufflevector <4 x half> %a, <4 x half> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
ret <4 x half> %0
}
; float16x4_t rev64_64(float16x4_t a) {
; return vrev64_s16(a);
; }
define <4 x half> @rev64_64(<4 x half> %a) #0 {
; CHECK-LABEL: rev64_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rev64 v0.4h, v0.4h
; CHECK-NEXT: ret
entry:
%0 = shufflevector <4 x half> %a, <4 x half> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x half> %0
}
; float16x8_t rev32_128(float16x8_t a) {
; return vrev32q_s16(a);
; }
define <8 x half> @rev32_128(<8 x half> %a) #0 {
; CHECK-LABEL: rev32_128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rev32 v0.8h, v0.8h
; CHECK-NEXT: ret
entry:
%0 = shufflevector <8 x half> %a, <8 x half> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
ret <8 x half> %0
}
; float16x8_t rev64_128(float16x8_t a) {
; return vrev64q_s16(a);
; }
define <8 x half> @rev64_128(<8 x half> %a) #0 {
; CHECK-LABEL: rev64_128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rev64 v0.8h, v0.8h
; CHECK-NEXT: ret
entry:
%0 = shufflevector <8 x half> %a, <8 x half> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
ret <8 x half> %0
}
; float16x4_t create_64(long long a) { return vcreate_f16(a); }
define <4 x half> @create_64(i64 %a) #0 {
; CHECK-LABEL: create_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov d0, x0
; CHECK-NEXT: ret
entry:
%0 = bitcast i64 %a to <4 x half>
ret <4 x half> %0
}
; float16x4_t dup_64(__fp16 a) { return vdup_n_f16(a); }
define <4 x half> @dup_64(half %a) #0 {
; CHECK-LABEL: dup_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $h0 killed $h0 def $q0
; CHECK-NEXT: dup v0.4h, v0.h[0]
; CHECK-NEXT: ret
entry:
%vecinit = insertelement <4 x half> undef, half %a, i32 0
%vecinit1 = insertelement <4 x half> %vecinit, half %a, i32 1
%vecinit2 = insertelement <4 x half> %vecinit1, half %a, i32 2
%vecinit3 = insertelement <4 x half> %vecinit2, half %a, i32 3
ret <4 x half> %vecinit3
}
; float16x8_t dup_128(__fp16 a) { return vdupq_n_f16(a); }
define <8 x half> @dup_128(half %a) #0 {
; CHECK-LABEL: dup_128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $h0 killed $h0 def $q0
; CHECK-NEXT: dup v0.8h, v0.h[0]
; CHECK-NEXT: ret
entry:
%vecinit = insertelement <8 x half> undef, half %a, i32 0
%vecinit1 = insertelement <8 x half> %vecinit, half %a, i32 1
%vecinit2 = insertelement <8 x half> %vecinit1, half %a, i32 2
%vecinit3 = insertelement <8 x half> %vecinit2, half %a, i32 3
%vecinit4 = insertelement <8 x half> %vecinit3, half %a, i32 4
%vecinit5 = insertelement <8 x half> %vecinit4, half %a, i32 5
%vecinit6 = insertelement <8 x half> %vecinit5, half %a, i32 6
%vecinit7 = insertelement <8 x half> %vecinit6, half %a, i32 7
ret <8 x half> %vecinit7
}
; float16x4_t dup_lane_64(float16x4_t a) { return vdup_lane_f16(a, 2); }
define <4 x half> @dup_lane_64(<4 x half> %a) #0 {
; CHECK-LABEL: dup_lane_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: dup v0.4h, v0.h[2]
; CHECK-NEXT: ret
entry:
%shuffle = shufflevector <4 x half> %a, <4 x half> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
ret <4 x half> %shuffle
}
; float16x8_t dup_lane_128(float16x4_t a) { return vdupq_lane_f16(a, 2); }
define <8 x half> @dup_lane_128(<4 x half> %a) #0 {
; CHECK-LABEL: dup_lane_128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: dup v0.8h, v0.h[2]
; CHECK-NEXT: ret
entry:
%shuffle = shufflevector <4 x half> %a, <4 x half> undef, <8 x i32> <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
ret <8 x half> %shuffle
}
; float16x4_t dup_laneq_64(float16x8_t a) { return vdup_laneq_f16(a, 2); }
define <4 x half> @dup_laneq_64(<8 x half> %a) #0 {
; CHECK-LABEL: dup_laneq_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: dup v0.4h, v0.h[2]
; CHECK-NEXT: ret
entry:
%shuffle = shufflevector <8 x half> %a, <8 x half> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
ret <4 x half> %shuffle
}
; float16x8_t dup_laneq_128(float16x8_t a) { return vdupq_laneq_f16(a, 2); }
define <8 x half> @dup_laneq_128(<8 x half> %a) #0 {
; CHECK-LABEL: dup_laneq_128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: dup v0.8h, v0.h[2]
; CHECK-NEXT: ret
entry:
%shuffle = shufflevector <8 x half> %a, <8 x half> undef, <8 x i32> <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
ret <8 x half> %shuffle
}
; float16x8_t vcombine(float16x4_t a, float16x4_t b) { return vcombine_f16(a, b); }
define <8 x half> @vcombine(<4 x half> %a, <4 x half> %b) #0 {
; CHECK-LABEL: vcombine:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT: mov v0.d[1], v1.d[0]
; CHECK-NEXT: ret
entry:
%shuffle.i = shufflevector <4 x half> %a, <4 x half> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x half> %shuffle.i
}
; float16x4_t get_high(float16x8_t a) { return vget_high_f16(a); }
define <4 x half> @get_high(<8 x half> %a) #0 {
; CHECK-LABEL: get_high:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ext v0.16b, v0.16b, v0.16b, #8
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
entry:
%shuffle.i = shufflevector <8 x half> %a, <8 x half> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
ret <4 x half> %shuffle.i
}
; float16x4_t get_low(float16x8_t a) { return vget_low_f16(a); }
define <4 x half> @get_low(<8 x half> %a) #0 {
; CHECK-LABEL: get_low:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
entry:
%shuffle.i = shufflevector <8 x half> %a, <8 x half> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
ret <4 x half> %shuffle.i
}
; float16x4_t set_lane_64(float16x4_t a, __fp16 b) { return vset_lane_f16(b, a, 2); }
define <4 x half> @set_lane_64(<4 x half> %a, half %b) #0 {
; CHECK-LABEL: set_lane_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $h1 killed $h1 def $s1
; CHECK-NEXT: fmov w8, s1
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: mov v0.h[2], w8
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
entry:
%0 = bitcast half %b to i16
%1 = bitcast <4 x half> %a to <4 x i16>
%vset_lane = insertelement <4 x i16> %1, i16 %0, i32 2
%2 = bitcast <4 x i16> %vset_lane to <4 x half>
ret <4 x half> %2
}
; float16x8_t set_lane_128(float16x8_t a, __fp16 b) { return vsetq_lane_f16(b, a, 2); }
define <8 x half> @set_lane_128(<8 x half> %a, half %b) #0 {
; CHECK-LABEL: set_lane_128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $h1 killed $h1 def $s1
; CHECK-NEXT: fmov w8, s1
; CHECK-NEXT: mov v0.h[2], w8
; CHECK-NEXT: ret
entry:
%0 = bitcast half %b to i16
%1 = bitcast <8 x half> %a to <8 x i16>
%vset_lane = insertelement <8 x i16> %1, i16 %0, i32 2
%2 = bitcast <8 x i16> %vset_lane to <8 x half>
ret <8 x half> %2
}
; __fp16 get_lane_64(float16x4_t a) { return vget_lane_f16(a, 2); }
define half @get_lane_64(<4 x half> %a) #0 {
; CHECK-LABEL: get_lane_64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: umov w8, v0.h[2]
; CHECK-NEXT: fmov s0, w8
; CHECK-NEXT: // kill: def $h0 killed $h0 killed $s0
; CHECK-NEXT: ret
entry:
%0 = bitcast <4 x half> %a to <4 x i16>
%vget_lane = extractelement <4 x i16> %0, i32 2
%1 = bitcast i16 %vget_lane to half
ret half %1
}
; __fp16 get_lane_128(float16x8_t a) { return vgetq_lane_f16(a, 2); }
define half @get_lane_128(<8 x half> %a) #0 {
; CHECK-LABEL: get_lane_128:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: umov w8, v0.h[2]
; CHECK-NEXT: fmov s0, w8
; CHECK-NEXT: // kill: def $h0 killed $h0 killed $s0
; CHECK-NEXT: ret
entry:
%0 = bitcast <8 x half> %a to <8 x i16>
%vgetq_lane = extractelement <8 x i16> %0, i32 2
%1 = bitcast i16 %vgetq_lane to half
ret half %1
}
|
