Lines Matching full:4
73 CMP x0, 4 // if mr < 4
80 // if mr <= 4
87 LD2R {v30.4s, v31.4s}, [x8]
146 LDP q12, q13, [x5], 32 // Fetch 3 B (4th deferred)
157 # First group of 4 A. 40 FMA.
158 FMLA v20.4s, v12.4s, v0.s[0]
160 FMLA v22.4s, v12.4s, v2.s[0]
161 FMLA v24.4s, v12.4s, v4.s[0]
162 FMLA v26.4s, v12.4s, v6.s[0]
165 FMLA v28.4s, v12.4s, v8.s[0]
166 FMLA v21.4s, v13.4s, v0.s[0]
167 FMLA v23.4s, v13.4s, v2.s[0]
170 FMLA v25.4s, v13.4s, v4.s[0]
171 FMLA v27.4s, v13.4s, v6.s[0]
172 FMLA v29.4s, v13.4s, v8.s[0]
175 FMLA v20.4s, v14.4s, v0.s[1]
176 FMLA v22.4s, v14.4s, v2.s[1]
177 FMLA v24.4s, v14.4s, v4.s[1]
179 FMLA v26.4s, v14.4s, v6.s[1]
180 FMLA v28.4s, v14.4s, v8.s[1]
181 FMLA v21.4s, v15.4s, v0.s[1]
183 FMLA v23.4s, v15.4s, v2.s[1]
184 FMLA v25.4s, v15.4s, v4.s[1]
185 FMLA v27.4s, v15.4s, v6.s[1]
187 FMLA v29.4s, v15.4s, v8.s[1]
189 FMLA v20.4s, v16.4s, v0.s[2]
190 FMLA v22.4s, v16.4s, v2.s[2]
192 FMLA v24.4s, v16.4s, v4.s[2]
193 FMLA v26.4s, v16.4s, v6.s[2]
194 FMLA v28.4s, v16.4s, v8.s[2]
195 LDP q12, q13, [x5], 32 // Load 4 B
196 FMLA v21.4s, v17.4s, v0.s[2]
197 FMLA v23.4s, v17.4s, v2.s[2]
198 FMLA v25.4s, v17.4s, v4.s[2]
199 FMLA v27.4s, v17.4s, v6.s[2]
200 FMLA v29.4s, v17.4s, v8.s[2]
202 FMLA v20.4s, v18.4s, v0.s[3]
203 FMLA v22.4s, v18.4s, v2.s[3]
204 FMLA v24.4s, v18.4s, v4.s[3]
205 FMLA v26.4s, v18.4s, v6.s[3]
207 FMLA v28.4s, v18.4s, v8.s[3]
208 FMLA v21.4s, v19.4s, v0.s[3]
209 FMLA v23.4s, v19.4s, v2.s[3]
211 FMLA v25.4s, v19.4s, v4.s[3]
212 FMLA v27.4s, v19.4s, v6.s[3]
213 FMLA v29.4s, v19.4s, v8.s[3]
216 # Second group of 4 A. 40 FMA.
217 FMLA v20.4s, v12.4s, v1.s[0]
218 FMLA v22.4s, v12.4s, v3.s[0]
219 FMLA v24.4s, v12.4s, v5.s[0]
221 FMLA v26.4s, v12.4s, v7.s[0]
222 FMLA v28.4s, v12.4s, v9.s[0]
223 FMLA v21.4s, v13.4s, v1.s[0]
225 FMLA v23.4s, v13.4s, v3.s[0]
226 FMLA v25.4s, v13.4s, v5.s[0]
227 FMLA v27.4s, v13.4s, v7.s[0]
229 FMLA v29.4s, v13.4s, v9.s[0]
231 FMLA v20.4s, v14.4s, v1.s[1]
232 FMLA v22.4s, v14.4s, v3.s[1]
234 FMLA v24.4s, v14.4s, v5.s[1]
235 FMLA v26.4s, v14.4s, v7.s[1]
236 FMLA v28.4s, v14.4s, v9.s[1]
238 FMLA v21.4s, v15.4s, v1.s[1]
239 FMLA v23.4s, v15.4s, v3.s[1]
240 FMLA v25.4s, v15.4s, v5.s[1]
242 FMLA v27.4s, v15.4s, v7.s[1]
243 FMLA v29.4s, v15.4s, v9.s[1]
245 FMLA v20.4s, v16.4s, v1.s[2]
246 FMLA v22.4s, v16.4s, v3.s[2]
247 FMLA v24.4s, v16.4s, v5.s[2]
248 FMLA v26.4s, v16.4s, v7.s[2]
249 FMLA v28.4s, v16.4s, v9.s[2]
250 FMLA v21.4s, v17.4s, v1.s[2]
251 FMLA v23.4s, v17.4s, v3.s[2]
253 FMLA v25.4s, v17.4s, v5.s[2]
254 FMLA v27.4s, v17.4s, v7.s[2]
255 FMLA v29.4s, v17.4s, v9.s[2]
258 FMLA v20.4s, v18.4s, v1.s[3]
259 FMLA v22.4s, v18.4s, v3.s[3]
261 FMLA v24.4s, v18.4s, v5.s[3]
262 FMLA v26.4s, v18.4s, v7.s[3]
263 FMLA v28.4s, v18.4s, v9.s[3]
264 FMLA v21.4s, v19.4s, v1.s[3]
265 FMLA v23.4s, v19.4s, v3.s[3]
266 FMLA v25.4s, v19.4s, v5.s[3]
267 FMLA v27.4s, v19.4s, v7.s[3]
268 FMLA v29.4s, v19.4s, v9.s[3]
275 # First group of 4 A. 40 FMA.
276 FMLA v20.4s, v12.4s, v0.s[0]
278 FMLA v22.4s, v12.4s, v2.s[0]
279 FMLA v24.4s, v12.4s, v4.s[0]
280 FMLA v26.4s, v12.4s, v6.s[0]
283 FMLA v28.4s, v12.4s, v8.s[0]
284 FMLA v21.4s, v13.4s, v0.s[0]
285 FMLA v23.4s, v13.4s, v2.s[0]
288 FMLA v25.4s, v13.4s, v4.s[0]
289 FMLA v27.4s, v13.4s, v6.s[0]
290 FMLA v29.4s, v13.4s, v8.s[0]
293 FMLA v20.4s, v14.4s, v0.s[1]
294 FMLA v22.4s, v14.4s, v2.s[1]
295 FMLA v24.4s, v14.4s, v4.s[1]
297 FMLA v26.4s, v14.4s, v6.s[1]
298 FMLA v28.4s, v14.4s, v8.s[1]
299 FMLA v21.4s, v15.4s, v0.s[1]
301 FMLA v23.4s, v15.4s, v2.s[1]
302 FMLA v25.4s, v15.4s, v4.s[1]
303 FMLA v27.4s, v15.4s, v6.s[1]
305 FMLA v29.4s, v15.4s, v8.s[1]
307 FMLA v20.4s, v16.4s, v0.s[2]
308 FMLA v22.4s, v16.4s, v2.s[2]
310 FMLA v24.4s, v16.4s, v4.s[2]
311 FMLA v26.4s, v16.4s, v6.s[2]
312 FMLA v28.4s, v16.4s, v8.s[2]
313 LDP q12, q13, [x5], 32 // Load 4 B
314 FMLA v21.4s, v17.4s, v0.s[2]
315 FMLA v23.4s, v17.4s, v2.s[2]
316 FMLA v25.4s, v17.4s, v4.s[2]
317 FMLA v27.4s, v17.4s, v6.s[2]
318 FMLA v29.4s, v17.4s, v8.s[2]
320 FMLA v20.4s, v18.4s, v0.s[3]
321 FMLA v22.4s, v18.4s, v2.s[3]
322 FMLA v24.4s, v18.4s, v4.s[3]
323 FMLA v26.4s, v18.4s, v6.s[3]
325 FMLA v28.4s, v18.4s, v8.s[3]
326 FMLA v21.4s, v19.4s, v0.s[3]
327 FMLA v23.4s, v19.4s, v2.s[3]
329 FMLA v25.4s, v19.4s, v4.s[3]
330 FMLA v27.4s, v19.4s, v6.s[3]
331 FMLA v29.4s, v19.4s, v8.s[3]
334 # Second group of 4 A. 40 FMA.
335 FMLA v20.4s, v12.4s, v1.s[0]
336 FMLA v22.4s, v12.4s, v3.s[0]
337 FMLA v24.4s, v12.4s, v5.s[0]
338 FMLA v26.4s, v12.4s, v7.s[0]
339 FMLA v28.4s, v12.4s, v9.s[0]
340 FMLA v21.4s, v13.4s, v1.s[0]
341 FMLA v23.4s, v13.4s, v3.s[0]
342 FMLA v25.4s, v13.4s, v5.s[0]
343 FMLA v27.4s, v13.4s, v7.s[0]
344 FMLA v29.4s, v13.4s, v9.s[0]
346 FMLA v20.4s, v14.4s, v1.s[1]
347 FMLA v22.4s, v14.4s, v3.s[1]
348 FMLA v24.4s, v14.4s, v5.s[1]
349 FMLA v26.4s, v14.4s, v7.s[1]
350 FMLA v28.4s, v14.4s, v9.s[1]
351 FMLA v21.4s, v15.4s, v1.s[1]
352 FMLA v23.4s, v15.4s, v3.s[1]
353 FMLA v25.4s, v15.4s, v5.s[1]
354 FMLA v27.4s, v15.4s, v7.s[1]
355 FMLA v29.4s, v15.4s, v9.s[1]
357 FMLA v20.4s, v16.4s, v1.s[2]
358 FMLA v22.4s, v16.4s, v3.s[2]
359 FMLA v24.4s, v16.4s, v5.s[2]
360 FMLA v26.4s, v16.4s, v7.s[2]
361 FMLA v28.4s, v16.4s, v9.s[2]
362 FMLA v21.4s, v17.4s, v1.s[2]
363 FMLA v23.4s, v17.4s, v3.s[2]
364 FMLA v25.4s, v17.4s, v5.s[2]
365 FMLA v27.4s, v17.4s, v7.s[2]
366 FMLA v29.4s, v17.4s, v9.s[2]
368 FMLA v20.4s, v18.4s, v1.s[3]
369 FMLA v22.4s, v18.4s, v3.s[3]
370 FMLA v24.4s, v18.4s, v5.s[3]
371 FMLA v26.4s, v18.4s, v7.s[3]
372 FMLA v28.4s, v18.4s, v9.s[3]
373 FMLA v21.4s, v19.4s, v1.s[3]
374 FMLA v23.4s, v19.4s, v3.s[3]
375 FMLA v25.4s, v19.4s, v5.s[3]
376 FMLA v27.4s, v19.4s, v7.s[3]
377 FMLA v29.4s, v19.4s, v9.s[3]
378 # Is there a remainder?- 4 floats of A (16 bytes) or less
382 4:
388 FMAX v20.4s, v20.4s, v30.4s
389 FMAX v21.4s, v21.4s, v30.4s
390 FMAX v22.4s, v22.4s, v30.4s
391 FMAX v23.4s, v23.4s, v30.4s
392 FMAX v24.4s, v24.4s, v30.4s
393 FMAX v25.4s, v25.4s, v30.4s
394 FMAX v26.4s, v26.4s, v30.4s
395 FMAX v27.4s, v27.4s, v30.4s
396 FMAX v28.4s, v28.4s, v30.4s
397 FMAX v29.4s, v29.4s, v30.4s
398 FMIN v20.4s, v20.4s, v31.4s
399 FMIN v21.4s, v21.4s, v31.4s
400 FMIN v22.4s, v22.4s, v31.4s
401 FMIN v23.4s, v23.4s, v31.4s
402 FMIN v24.4s, v24.4s, v31.4s
403 FMIN v25.4s, v25.4s, v31.4s
404 FMIN v26.4s, v26.4s, v31.4s
405 FMIN v27.4s, v27.4s, v31.4s
406 FMIN v28.4s, v28.4s, v31.4s
407 FMIN v29.4s, v29.4s, v31.4s
439 # Is there a remainder?- 4 floats of A (16 bytes)
440 TBZ x0, 4, 6f
442 # Remainder- 4 floats of A (16 bytes)
455 FMLA v20.4s, v12.4s, v0.s[0]
456 FMLA v22.4s, v12.4s, v2.s[0]
457 FMLA v24.4s, v12.4s, v4.s[0]
458 FMLA v26.4s, v12.4s, v6.s[0]
459 FMLA v28.4s, v12.4s, v8.s[0]
460 FMLA v21.4s, v13.4s, v0.s[0]
461 FMLA v23.4s, v13.4s, v2.s[0]
462 FMLA v25.4s, v13.4s, v4.s[0]
463 FMLA v27.4s, v13.4s, v6.s[0]
464 FMLA v29.4s, v13.4s, v8.s[0]
466 FMLA v20.4s, v14.4s, v0.s[1]
467 FMLA v22.4s, v14.4s, v2.s[1]
468 FMLA v24.4s, v14.4s, v4.s[1]
469 FMLA v26.4s, v14.4s, v6.s[1]
470 FMLA v28.4s, v14.4s, v8.s[1]
471 FMLA v21.4s, v15.4s, v0.s[1]
472 FMLA v23.4s, v15.4s, v2.s[1]
473 FMLA v25.4s, v15.4s, v4.s[1]
474 FMLA v27.4s, v15.4s, v6.s[1]
475 FMLA v29.4s, v15.4s, v8.s[1]
477 FMLA v20.4s, v16.4s, v0.s[2]
478 FMLA v22.4s, v16.4s, v2.s[2]
479 FMLA v24.4s, v16.4s, v4.s[2]
480 FMLA v26.4s, v16.4s, v6.s[2]
481 FMLA v28.4s, v16.4s, v8.s[2]
482 FMLA v21.4s, v17.4s, v0.s[2]
483 FMLA v23.4s, v17.4s, v2.s[2]
484 FMLA v25.4s, v17.4s, v4.s[2]
485 FMLA v27.4s, v17.4s, v6.s[2]
486 FMLA v29.4s, v17.4s, v8.s[2]
488 FMLA v20.4s, v18.4s, v0.s[3]
489 FMLA v22.4s, v18.4s, v2.s[3]
490 FMLA v24.4s, v18.4s, v4.s[3]
491 FMLA v26.4s, v18.4s, v6.s[3]
492 FMLA v28.4s, v18.4s, v8.s[3]
493 FMLA v21.4s, v19.4s, v0.s[3]
494 FMLA v23.4s, v19.4s, v2.s[3]
495 FMLA v25.4s, v19.4s, v4.s[3]
496 FMLA v27.4s, v19.4s, v6.s[3]
497 FMLA v29.4s, v19.4s, v8.s[3]
514 FMLA v20.4s, v12.4s, v0.s[0]
515 FMLA v22.4s, v12.4s, v2.s[0]
516 FMLA v24.4s, v12.4s, v4.s[0]
517 FMLA v26.4s, v12.4s, v6.s[0]
518 FMLA v28.4s, v12.4s, v8.s[0]
519 FMLA v21.4s, v13.4s, v0.s[0]
520 FMLA v23.4s, v13.4s, v2.s[0]
521 FMLA v25.4s, v13.4s, v4.s[0]
522 FMLA v27.4s, v13.4s, v6.s[0]
523 FMLA v29.4s, v13.4s, v8.s[0]
525 FMLA v20.4s, v14.4s, v0.s[1]
526 FMLA v22.4s, v14.4s, v2.s[1]
527 FMLA v24.4s, v14.4s, v4.s[1]
528 FMLA v26.4s, v14.4s, v6.s[1]
529 FMLA v28.4s, v14.4s, v8.s[1]
530 FMLA v21.4s, v15.4s, v0.s[1]
531 FMLA v23.4s, v15.4s, v2.s[1]
532 FMLA v25.4s, v15.4s, v4.s[1]
533 FMLA v27.4s, v15.4s, v6.s[1]
534 FMLA v29.4s, v15.4s, v8.s[1]
536 # Is there a remainder?- 1 float of A (4 bytes)
538 TBZ x0, 2, 4b
540 # Remainder- 1 float of A (4 bytes)
542 LDR s0, [x14], 4
543 LDR s2, [x15], 4
544 LDR s4, [x20], 4
545 LDR s6, [x21], 4
546 LDR s8, [x8], 4
550 FMLA v20.4s, v12.4s, v0.s[0]
551 FMLA v22.4s, v12.4s, v2.s[0]
552 FMLA v24.4s, v12.4s, v4.s[0]
553 FMLA v26.4s, v12.4s, v6.s[0]
554 FMLA v28.4s, v12.4s, v8.s[0]
555 FMLA v21.4s, v13.4s, v0.s[0]
556 FMLA v23.4s, v13.4s, v2.s[0]
557 FMLA v25.4s, v13.4s, v4.s[0]
558 FMLA v27.4s, v13.4s, v6.s[0]
559 FMLA v29.4s, v13.4s, v8.s[0]
560 B 4b