Lines Matching +full:3 +full:- +full:d

2 …lvm-mca -mtriple=aarch64 -mcpu=neoverse-v2 -mattr=+sve2-aes,+sve2-sha3,+sve2-sm4 --instruction-inf…
4 # LLVM-MCA-BEGIN madd
9 # LLVM-MCA-END
11 # LLVM-MCA-BEGIN smaddl
16 # LLVM-MCA-END
18 # LLVM-MCA-BEGIN fmadd
25 # LLVM-MCA-END
27 # LLVM-MCA-BEGIN saba
32 # LLVM-MCA-END
34 # LLVM-MCA-BEGIN sdot
39 # LLVM-MCA-END
41 # LLVM-MCA-BEGIN smmla
46 # LLVM-MCA-END
48 # LLVM-MCA-BEGIN mla
53 # LLVM-MCA-END
55 # LLVM-MCA-BEGIN sqrdmlah
60 # LLVM-MCA-END
62 # LLVM-MCA-BEGIN smlal2
67 # LLVM-MCA-END
69 # LLVM-MCA-BEGIN sadalp
71 sadalp v0.2d, v1.4s
72 sadalp v0.2d, v1.4s
73 sadalp v0.2d, v0.4s
74 # LLVM-MCA-END
76 # LLVM-MCA-BEGIN ssra
78 ssra v0.2d, v1.2d, #1
79 ssra v0.2d, v1.2d, #1
80 ssra v0.2d, v0.2d, #1
81 # LLVM-MCA-END
83 # LLVM-MCA-BEGIN fcmla
85 fcmla v0.2d, v1.2d, v2.2d, #90
86 fcmla v0.2d, v1.2d, v2.2d, #90
87 fcmla v0.2d, v0.2d, v1.2d, #90
88 # LLVM-MCA-END
90 # LLVM-MCA-BEGIN fmla
91 fmul v0.2d, v0.2d, v0.2d
92 fmla v0.2d, v1.2d, v2.2d
93 fadd v0.2d, v0.2d, v0.2d
94 fmla v0.2d, v1.2d, v2.2d
95 fmla v0.2d, v1.2d, v2.2d
96 fmla v0.2d, v0.2d, v1.2d
97 # LLVM-MCA-END
99 # LLVM-MCA-BEGIN fmlal
100 fmul v0.2d, v0.2d, v0.2d
102 fadd v0.2d, v0.2d, v0.2d
106 # LLVM-MCA-END
108 # LLVM-MCA-BEGIN bfdot
109 fmul v0.2d, v0.2d, v0.2d
113 # LLVM-MCA-END
115 # LLVM-MCA-BEGIN bfmmla
116 fmul v0.2d, v0.2d, v0.2d
120 # LLVM-MCA-END
122 # LLVM-MCA-BEGIN bfmlalb
123 fmul v0.2d, v0.2d, v0.2d
127 # LLVM-MCA-END
129 # LLVM-MCA-BEGIN crc32b
134 # LLVM-MCA-END
136 # LLVM-MCA-BEGIN Z saba
137 mul z0.d, z0.d, z0.d
138 saba z0.d, z1.d, z2.d
139 saba z0.d, z1.d, z2.d
140 saba z0.d, z0.d, z1.d
141 # LLVM-MCA-END
143 # LLVM-MCA-BEGIN Z sadalp
144 mul z0.d, z0.d, z0.d
145 sadalp z0.d, p0/m, z1.s
146 sadalp z0.d, p0/m, z1.s
147 sadalp z0.d, p0/m, z0.s
148 # LLVM-MCA-END
150 # LLVM-MCA-BEGIN Z ssra
151 mul z0.d, z0.d, z0.d
152 ssra z0.d, z1.d, #1
153 ssra z0.d, z1.d, #1
154 ssra z0.d, z0.d, #1
155 # LLVM-MCA-END
157 # LLVM-MCA-BEGIN Z cdot.s
158 mul z0.d, z0.d, z0.d
162 # LLVM-MCA-END
164 # LLVM-MCA-BEGIN Z cdot.d
165 mul z0.d, z0.d, z0.d
166 cdot z0.d, z1.h, z2.h, #90
167 cdot z0.d, z1.h, z2.h, #90
168 cdot z0.d, z0.h, z1.h, #90
169 # LLVM-MCA-END
171 # LLVM-MCA-BEGIN Z cmla.b
172 mul z0.d, z0.d, z0.d
176 # LLVM-MCA-END
178 # LLVM-MCA-BEGIN Z cmla.d
179 mul z0.d, z0.d, z0.d
180 cmla z0.d, z1.d, z2.d, #90
181 cmla z0.d, z1.d, z2.d, #90
182 cmla z0.d, z0.d, z1.d, #90
183 # LLVM-MCA-END
185 # LLVM-MCA-BEGIN Z sdot.s
186 mul z0.d, z0.d, z0.d
190 # LLVM-MCA-END
192 # LLVM-MCA-BEGIN Z sudot
193 mul z0.d, z0.d, z0.d
197 # LLVM-MCA-END
199 # LLVM-MCA-BEGIN Z sdot.d
200 mul z0.d, z0.d, z0.d
201 sdot z0.d, z1.h, z2.h
202 sdot z0.d, z1.h, z2.h
203 sdot z0.d, z0.h, z1.h
204 # LLVM-MCA-END
206 # LLVM-MCA-BEGIN Z smmla
211 # LLVM-MCA-END
213 # LLVM-MCA-BEGIN Z mla.b
214 mul z0.d, z0.d, z0.d
218 # LLVM-MCA-END
220 # LLVM-MCA-BEGIN Z mla.d
221 mul z0.d, z0.d, z0.d
222 mla z0.d, p0/m, z1.d, z2.d
223 mla z0.d, p0/m, z1.d, z2.d
224 mla z0.d, p0/m, z0.d, z1.d
225 # LLVM-MCA-END
227 # LLVM-MCA-BEGIN Z smlalb
228 mul z0.d, z0.d, z0.d
229 smlalb z0.d, z1.s, z2.s
230 smlalb z0.d, z1.s, z2.s
231 smlalb z0.d, z0.s, z1.s
232 # LLVM-MCA-END
234 # LLVM-MCA-BEGIN Z sqdmlalb
235 mul z0.d, z0.d, z0.d
236 sqdmlalb z0.d, z1.s, z2.s
237 sqdmlalb z0.d, z1.s, z2.s
238 sqdmlalb z0.d, z0.s, z1.s
239 # LLVM-MCA-END
241 # LLVM-MCA-BEGIN Z sqrdmlah.b
242 mul z0.d, z0.d, z0.d
246 # LLVM-MCA-END
248 # LLVM-MCA-BEGIN Z sqrdmlah.d
249 mul z0.d, z0.d, z0.d
250 sqrdmlah z0.d, z1.d, z2.d
251 sqrdmlah z0.d, z1.d, z2.d
252 sqrdmlah z0.d, z0.d, z1.d
253 # LLVM-MCA-END
255 # LLVM-MCA-BEGIN Z fcmla ZPmZZ
256 fmul z0.d, z0.d, z0.d
257 fcmla z0.d, p0/m, z1.d, z2.d, 90
258 fcmla z0.d, p0/m, z1.d, z2.d, 90
259 fcmla z0.d, p0/m, z0.d, z1.d, 90
260 # LLVM-MCA-END
262 # LLVM-MCA-BEGIN Z fcmla ZZZI
263 fmul z0.d, z0.d, z0.d
267 # LLVM-MCA-END
269 # LLVM-MCA-BEGIN Z fmla ZPmZZ
270 fmul z0.d, z0.d, z0.d
271 fmla z0.d, p0/m, z1.d, z2.d
272 fmla z0.d, p0/m, z1.d, z2.d
273 fmla z0.d, p0/m, z0.d, z1.d
274 # LLVM-MCA-END
276 # LLVM-MCA-BEGIN Z fmla ZZZI
277 fmul z0.d, z0.d, z0.d
278 fmla z0.d, z1.d, z2.d[1]
279 fmla z0.d, z1.d, z2.d[1]
280 fmla z0.d, z0.d, z1.d[1]
281 # LLVM-MCA-END
283 # LLVM-MCA-BEGIN Z fmlalb ZZZ
284 fmul z0.d, z0.d, z0.d
288 # LLVM-MCA-END
290 # LLVM-MCA-BEGIN Z bfdot
291 fmul z0.d, z0.d, z0.d
295 # LLVM-MCA-END
297 # LLVM-MCA-BEGIN Z bfmmla
298 fmul z0.d, z0.d, z0.d
302 # LLVM-MCA-END
304 # LLVM-MCA-BEGIN bfmlalb
305 fmul z0.d, z0.d, z0.d
309 # LLVM-MCA-END
311 # CHECK: [0] Code Region - madd
314 # CHECK-NEXT: Instructions: 400
315 # CHECK-NEXT: Total Cycles: 703
316 # CHECK-NEXT: Total uOps: 400
319 # CHECK-NEXT: uOps Per Cycle: 0.57
320 # CHECK-NEXT: IPC: 0.57
321 # CHECK-NEXT: Block RThroughput: 3.0
324 # CHECK-NEXT: 0123456
325 # CHECK-NEXT: Index 0123456789
328 # CHECK-NEXT: [0,1] D==eeER . .. madd x0, x1, x2, x0
329 # CHECK-NEXT: [0,2] D===eeER . .. madd x0, x1, x2, x0
330 # CHECK-NEXT: [0,3] D=====eeER. .. madd x0, x0, x0, x0
331 # CHECK-NEXT: [1,0] D=======eeER .. mul x0, x0, x0
332 # CHECK-NEXT: [1,1] D=========eeER .. madd x0, x1, x2, x0
333 # CHECK-NEXT: [1,2] D==========eeER.. madd x0, x1, x2, x0
334 # CHECK-NEXT: [1,3] D============eeER madd x0, x0, x0, x0
337 # CHECK-NEXT: [0]: Executions
338 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
339 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
340 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
342 # CHECK: [0] [1] [2] [3]
343 # CHECK-NEXT: 0. 2 4.5 0.5 0.0 mul x0, x0, x0
344 # CHECK-NEXT: 1. 2 6.5 0.0 0.0 madd x0, x1, x2, x0
345 # CHECK-NEXT: 2. 2 7.5 0.0 0.0 madd x0, x1, x2, x0
346 # CHECK-NEXT: 3. 2 9.5 0.0 0.0 madd x0, x0, x0, x0
347 # CHECK-NEXT: 2 7.0 0.1 0.0 <total>
349 # CHECK: [1] Code Region - smaddl
352 # CHECK-NEXT: Instructions: 400
353 # CHECK-NEXT: Total Cycles: 703
354 # CHECK-NEXT: Total uOps: 400
357 # CHECK-NEXT: uOps Per Cycle: 0.57
358 # CHECK-NEXT: IPC: 0.57
359 # CHECK-NEXT: Block RThroughput: 3.0
362 # CHECK-NEXT: 0123456
363 # CHECK-NEXT: Index 0123456789
366 # CHECK-NEXT: [0,1] D==eeER . .. smaddl x0, w1, w2, x0
367 # CHECK-NEXT: [0,2] D===eeER . .. smaddl x0, w1, w2, x0
368 # CHECK-NEXT: [0,3] D=====eeER. .. smaddl x0, w0, w0, x0
369 # CHECK-NEXT: [1,0] D=======eeER .. mul x0, x0, x0
370 # CHECK-NEXT: [1,1] D=========eeER .. smaddl x0, w1, w2, x0
371 # CHECK-NEXT: [1,2] D==========eeER.. smaddl x0, w1, w2, x0
372 # CHECK-NEXT: [1,3] D============eeER smaddl x0, w0, w0, x0
375 # CHECK-NEXT: [0]: Executions
376 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
377 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
378 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
380 # CHECK: [0] [1] [2] [3]
381 # CHECK-NEXT: 0. 2 4.5 0.5 0.0 mul x0, x0, x0
382 # CHECK-NEXT: 1. 2 6.5 0.0 0.0 smaddl x0, w1, w2, x0
383 # CHECK-NEXT: 2. 2 7.5 0.0 0.0 smaddl x0, w1, w2, x0
384 # CHECK-NEXT: 3. 2 9.5 0.0 0.0 smaddl x0, w0, w0, x0
385 # CHECK-NEXT: 2 7.0 0.1 0.0 <total>
387 # CHECK: [2] Code Region - fmadd
390 # CHECK-NEXT: Instructions: 600
391 # CHECK-NEXT: Total Cycles: 1703
392 # CHECK-NEXT: Total uOps: 600
395 # CHECK-NEXT: uOps Per Cycle: 0.35
396 # CHECK-NEXT: IPC: 0.35
397 # CHECK-NEXT: Block RThroughput: 1.5
400 # CHECK-NEXT: 0123456789 0123456
401 # CHECK-NEXT: Index 0123456789 0123456789
404 # CHECK-NEXT: [0,1] D==eeeeER . . . . . .. fmadd d0, d1, d2, d0
405 # CHECK-NEXT: [0,2] D======eeeER . . . . .. fmul d0, d0, d0
406 # CHECK-NEXT: [0,3] D=======eeeeER . . . . .. fmadd d0, d1, d2, d0
407 # CHECK-NEXT: [0,4] D=========eeeeER . . . .. fmadd d0, d1, d2, d0
408 # CHECK-NEXT: [0,5] D=============eeeeER. . . .. fmadd d0, d0, d1, d2
409 # CHECK-NEXT: [1,0] D=================eeER . . .. fadd d0, d0, d0
410 # CHECK-NEXT: [1,1] D===================eeeeER . .. fmadd d0, d1, d2, d0
411 # CHECK-NEXT: [1,2] D=======================eeeER . .. fmul d0, d0, d0
412 # CHECK-NEXT: [1,3] D========================eeeeER .. fmadd d0, d1, d2, d0
413 # CHECK-NEXT: [1,4] D==========================eeeeER .. fmadd d0, d1, d2, d0
414 # CHECK-NEXT: [1,5] D==============================eeeeER fmadd d0, d0, d1, d2
417 # CHECK-NEXT: [0]: Executions
418 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
419 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
420 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
422 # CHECK: [0] [1] [2] [3]
423 # CHECK-NEXT: 0. 2 9.5 0.5 0.0 fadd d0, d0, d0
424 # CHECK-NEXT: 1. 2 11.5 0.0 0.0 fmadd d0, d1, d2, d0
425 # CHECK-NEXT: 2. 2 15.5 0.0 0.0 fmul d0, d0, d0
426 # CHECK-NEXT: 3. 2 16.5 0.0 0.0 fmadd d0, d1, d2, d0
427 # CHECK-NEXT: 4. 2 18.5 0.0 0.0 fmadd d0, d1, d2, d0
428 # CHECK-NEXT: 5. 2 22.5 0.0 0.0 fmadd d0, d0, d1, d2
429 # CHECK-NEXT: 2 15.7 0.1 0.0 <total>
431 # CHECK: [3] Code Region - saba
434 # CHECK-NEXT: Instructions: 400
435 # CHECK-NEXT: Total Cycles: 1303
436 # CHECK-NEXT: Total uOps: 400
439 # CHECK-NEXT: uOps Per Cycle: 0.31
440 # CHECK-NEXT: IPC: 0.31
441 # CHECK-NEXT: Block RThroughput: 1.5
444 # CHECK-NEXT: 0123456789
445 # CHECK-NEXT: Index 0123456789 012345678
448 # CHECK-NEXT: [0,1] D====eeeeER . . . . saba v0.4s, v1.4s, v2.4s
449 # CHECK-NEXT: [0,2] D=====eeeeER . . . . saba v0.4s, v1.4s, v2.4s
450 # CHECK-NEXT: [0,3] D=========eeeeER . . . saba v0.4s, v0.4s, v1.4s
451 # CHECK-NEXT: [1,0] D=============eeeeER. . . mul v0.4s, v0.4s, v0.4s
452 # CHECK-NEXT: [1,1] D=================eeeeER . . saba v0.4s, v1.4s, v2.4s
453 # CHECK-NEXT: [1,2] D==================eeeeER. . saba v0.4s, v1.4s, v2.4s
454 # CHECK-NEXT: [1,3] D======================eeeeER saba v0.4s, v0.4s, v1.4s
457 # CHECK-NEXT: [0]: Executions
458 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
459 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
460 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
462 # CHECK: [0] [1] [2] [3]
463 # CHECK-NEXT: 0. 2 7.5 0.5 0.0 mul v0.4s, v0.4s, v0.4s
464 # CHECK-NEXT: 1. 2 11.5 0.0 0.0 saba v0.4s, v1.4s, v2.4s
465 # CHECK-NEXT: 2. 2 12.5 0.0 0.0 saba v0.4s, v1.4s, v2.4s
466 # CHECK-NEXT: 3. 2 16.5 0.0 0.0 saba v0.4s, v0.4s, v1.4s
467 # CHECK-NEXT: 2 12.0 0.1 0.0 <total>
469 # CHECK: [4] Code Region - sdot
472 # CHECK-NEXT: Instructions: 400
473 # CHECK-NEXT: Total Cycles: 1103
474 # CHECK-NEXT: Total uOps: 400
477 # CHECK-NEXT: uOps Per Cycle: 0.36
478 # CHECK-NEXT: IPC: 0.36
479 # CHECK-NEXT: Block RThroughput: 0.8
482 # CHECK-NEXT: 0123456789
483 # CHECK-NEXT: Index 0123456789 01234
486 # CHECK-NEXT: [0,1] D====eeeER. . . . sdot v0.4s, v1.16b, v2.16b
487 # CHECK-NEXT: [0,2] D=====eeeER . . . sdot v0.4s, v1.16b, v2.16b
488 # CHECK-NEXT: [0,3] D========eeeER . . . sdot v0.4s, v0.16b, v1.16b
489 # CHECK-NEXT: [1,0] D===========eeeeER . . mul v0.4s, v0.4s, v0.4s
490 # CHECK-NEXT: [1,1] D===============eeeER . sdot v0.4s, v1.16b, v2.16b
491 # CHECK-NEXT: [1,2] D================eeeER . sdot v0.4s, v1.16b, v2.16b
492 # CHECK-NEXT: [1,3] D===================eeeER sdot v0.4s, v0.16b, v1.16b
495 # CHECK-NEXT: [0]: Executions
496 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
497 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
498 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
500 # CHECK: [0] [1] [2] [3]
501 # CHECK-NEXT: 0. 2 6.5 0.5 0.0 mul v0.4s, v0.4s, v0.4s
502 # CHECK-NEXT: 1. 2 10.5 0.0 0.0 sdot v0.4s, v1.16b, v2.16b
503 # CHECK-NEXT: 2. 2 11.5 0.0 0.0 sdot v0.4s, v1.16b, v2.16b
504 # CHECK-NEXT: 3. 2 14.5 0.0 0.0 sdot v0.4s, v0.16b, v1.16b
505 # CHECK-NEXT: 2 10.8 0.1 0.0 <total>
507 # CHECK: [5] Code Region - smmla
510 # CHECK-NEXT: Instructions: 400
511 # CHECK-NEXT: Total Cycles: 1103
512 # CHECK-NEXT: Total uOps: 400
515 # CHECK-NEXT: uOps Per Cycle: 0.36
516 # CHECK-NEXT: IPC: 0.36
517 # CHECK-NEXT: Block RThroughput: 0.8
520 # CHECK-NEXT: 0123456789
521 # CHECK-NEXT: Index 0123456789 01234
524 # CHECK-NEXT: [0,1] D====eeeER. . . . smmla v0.4s, v1.16b, v2.16b
525 # CHECK-NEXT: [0,2] D=====eeeER . . . smmla v0.4s, v1.16b, v2.16b
526 # CHECK-NEXT: [0,3] D========eeeER . . . smmla v0.4s, v0.16b, v1.16b
527 # CHECK-NEXT: [1,0] D===========eeeeER . . mul v0.4s, v0.4s, v0.4s
528 # CHECK-NEXT: [1,1] D===============eeeER . smmla v0.4s, v1.16b, v2.16b
529 # CHECK-NEXT: [1,2] D================eeeER . smmla v0.4s, v1.16b, v2.16b
530 # CHECK-NEXT: [1,3] D===================eeeER smmla v0.4s, v0.16b, v1.16b
533 # CHECK-NEXT: [0]: Executions
534 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
535 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
536 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
538 # CHECK: [0] [1] [2] [3]
539 # CHECK-NEXT: 0. 2 6.5 0.5 0.0 mul v0.4s, v0.4s, v0.4s
540 # CHECK-NEXT: 1. 2 10.5 0.0 0.0 smmla v0.4s, v1.16b, v2.16b
541 # CHECK-NEXT: 2. 2 11.5 0.0 0.0 smmla v0.4s, v1.16b, v2.16b
542 # CHECK-NEXT: 3. 2 14.5 0.0 0.0 smmla v0.4s, v0.16b, v1.16b
543 # CHECK-NEXT: 2 10.8 0.1 0.0 <total>
545 # CHECK: [6] Code Region - mla
548 # CHECK-NEXT: Instructions: 400
549 # CHECK-NEXT: Total Cycles: 1303
550 # CHECK-NEXT: Total uOps: 400
553 # CHECK-NEXT: uOps Per Cycle: 0.31
554 # CHECK-NEXT: IPC: 0.31
555 # CHECK-NEXT: Block RThroughput: 2.0
558 # CHECK-NEXT: 0123456789
559 # CHECK-NEXT: Index 0123456789 012345678
562 # CHECK-NEXT: [0,1] D====eeeeER . . . . mla v0.4s, v1.4s, v2.4s
563 # CHECK-NEXT: [0,2] D=====eeeeER . . . . mla v0.4s, v1.4s, v2.4s
564 # CHECK-NEXT: [0,3] D=========eeeeER . . . mla v0.4s, v0.4s, v1.4s
565 # CHECK-NEXT: [1,0] D=============eeeeER. . . mul v0.4s, v0.4s, v0.4s
566 # CHECK-NEXT: [1,1] D=================eeeeER . . mla v0.4s, v1.4s, v2.4s
567 # CHECK-NEXT: [1,2] D==================eeeeER. . mla v0.4s, v1.4s, v2.4s
568 # CHECK-NEXT: [1,3] D======================eeeeER mla v0.4s, v0.4s, v1.4s
571 # CHECK-NEXT: [0]: Executions
572 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
573 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
574 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
576 # CHECK: [0] [1] [2] [3]
577 # CHECK-NEXT: 0. 2 7.5 0.5 0.0 mul v0.4s, v0.4s, v0.4s
578 # CHECK-NEXT: 1. 2 11.5 0.0 0.0 mla v0.4s, v1.4s, v2.4s
579 # CHECK-NEXT: 2. 2 12.5 0.0 0.0 mla v0.4s, v1.4s, v2.4s
580 # CHECK-NEXT: 3. 2 16.5 0.0 0.0 mla v0.4s, v0.4s, v1.4s
581 # CHECK-NEXT: 2 12.0 0.1 0.0 <total>
583 # CHECK: [7] Code Region - sqrdmlah
586 # CHECK-NEXT: Instructions: 400
587 # CHECK-NEXT: Total Cycles: 1403
588 # CHECK-NEXT: Total uOps: 400
591 # CHECK-NEXT: uOps Per Cycle: 0.29
592 # CHECK-NEXT: IPC: 0.29
593 # CHECK-NEXT: Block RThroughput: 3.5
596 # CHECK-NEXT: 0123456789 0
597 # CHECK-NEXT: Index 0123456789 0123456789
600 # CHECK-NEXT: [0,1] D====eeeeER . . . . sqrdmlah v0.4s, v1.4s, v2.4s
601 # CHECK-NEXT: [0,2] D======eeeeER . . . . sqrdmlah v0.4s, v1.4s, v2.4s
602 # CHECK-NEXT: [0,3] D==========eeeeER . . . sqrdmlah v0.4s, v0.4s, v1.4s
603 # CHECK-NEXT: [1,0] D==============eeeeER . . mul v0.4s, v0.4s, v0.4s
604 # CHECK-NEXT: [1,1] D==================eeeeER. . sqrdmlah v0.4s, v1.4s, v2.4s
605 # CHECK-NEXT: [1,2] D====================eeeeER . sqrdmlah v0.4s, v1.4s, v2.4s
606 # CHECK-NEXT: [1,3] D========================eeeeER sqrdmlah v0.4s, v0.4s, v1.4s
609 # CHECK-NEXT: [0]: Executions
610 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
611 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
612 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
614 # CHECK: [0] [1] [2] [3]
615 # CHECK-NEXT: 0. 2 8.0 0.5 0.0 mul v0.4s, v0.4s, v0.4s
616 # CHECK-NEXT: 1. 2 12.0 0.0 0.0 sqrdmlah v0.4s, v1.4s, v2.4s
617 # CHECK-NEXT: 2. 2 14.0 0.0 0.0 sqrdmlah v0.4s, v1.4s, v2.4s
618 # CHECK-NEXT: 3. 2 18.0 0.0 0.0 sqrdmlah v0.4s, v0.4s, v1.4s
619 # CHECK-NEXT: 2 13.0 0.1 0.0 <total>
621 # CHECK: [8] Code Region - smlal2
624 # CHECK-NEXT: Instructions: 400
625 # CHECK-NEXT: Total Cycles: 1303
626 # CHECK-NEXT: Total uOps: 400
629 # CHECK-NEXT: uOps Per Cycle: 0.31
630 # CHECK-NEXT: IPC: 0.31
631 # CHECK-NEXT: Block RThroughput: 2.0
634 # CHECK-NEXT: 0123456789
635 # CHECK-NEXT: Index 0123456789 012345678
638 # CHECK-NEXT: [0,1] D====eeeeER . . . . smlal2 v0.4s, v1.8h, v2.8h
639 # CHECK-NEXT: [0,2] D=====eeeeER . . . . smlal2 v0.4s, v1.8h, v2.8h
640 # CHECK-NEXT: [0,3] D=========eeeeER . . . smlal2 v0.4s, v0.8h, v1.8h
641 # CHECK-NEXT: [1,0] D=============eeeeER. . . mul v0.4s, v0.4s, v0.4s
642 # CHECK-NEXT: [1,1] D=================eeeeER . . smlal2 v0.4s, v1.8h, v2.8h
643 # CHECK-NEXT: [1,2] D==================eeeeER. . smlal2 v0.4s, v1.8h, v2.8h
644 # CHECK-NEXT: [1,3] D======================eeeeER smlal2 v0.4s, v0.8h, v1.8h
647 # CHECK-NEXT: [0]: Executions
648 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
649 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
650 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
652 # CHECK: [0] [1] [2] [3]
653 # CHECK-NEXT: 0. 2 7.5 0.5 0.0 mul v0.4s, v0.4s, v0.4s
654 # CHECK-NEXT: 1. 2 11.5 0.0 0.0 smlal2 v0.4s, v1.8h, v2.8h
655 # CHECK-NEXT: 2. 2 12.5 0.0 0.0 smlal2 v0.4s, v1.8h, v2.8h
656 # CHECK-NEXT: 3. 2 16.5 0.0 0.0 smlal2 v0.4s, v0.8h, v1.8h
657 # CHECK-NEXT: 2 12.0 0.1 0.0 <total>
659 # CHECK: [9] Code Region - sadalp
662 # CHECK-NEXT: Instructions: 400
663 # CHECK-NEXT: Total Cycles: 1303
664 # CHECK-NEXT: Total uOps: 400
667 # CHECK-NEXT: uOps Per Cycle: 0.31
668 # CHECK-NEXT: IPC: 0.31
669 # CHECK-NEXT: Block RThroughput: 1.5
672 # CHECK-NEXT: 0123456789
673 # CHECK-NEXT: Index 0123456789 012345678
676 # CHECK-NEXT: [0,1] D====eeeeER . . . . sadalp v0.2d, v1.4s
677 # CHECK-NEXT: [0,2] D=====eeeeER . . . . sadalp v0.2d, v1.4s
678 # CHECK-NEXT: [0,3] D=========eeeeER . . . sadalp v0.2d, v0.4s
679 # CHECK-NEXT: [1,0] D=============eeeeER. . . mul v0.4s, v0.4s, v0.4s
680 # CHECK-NEXT: [1,1] D=================eeeeER . . sadalp v0.2d, v1.4s
681 # CHECK-NEXT: [1,2] D==================eeeeER. . sadalp v0.2d, v1.4s
682 # CHECK-NEXT: [1,3] D======================eeeeER sadalp v0.2d, v0.4s
685 # CHECK-NEXT: [0]: Executions
686 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
687 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
688 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
690 # CHECK: [0] [1] [2] [3]
691 # CHECK-NEXT: 0. 2 7.5 0.5 0.0 mul v0.4s, v0.4s, v0.4s
692 # CHECK-NEXT: 1. 2 11.5 0.0 0.0 sadalp v0.2d, v1.4s
693 # CHECK-NEXT: 2. 2 12.5 0.0 0.0 sadalp v0.2d, v1.4s
694 # CHECK-NEXT: 3. 2 16.5 0.0 0.0 sadalp v0.2d, v0.4s
695 # CHECK-NEXT: 2 12.0 0.1 0.0 <total>
697 # CHECK: [10] Code Region - ssra
700 # CHECK-NEXT: Instructions: 400
701 # CHECK-NEXT: Total Cycles: 1303
702 # CHECK-NEXT: Total uOps: 400
705 # CHECK-NEXT: uOps Per Cycle: 0.31
706 # CHECK-NEXT: IPC: 0.31
707 # CHECK-NEXT: Block RThroughput: 1.5
710 # CHECK-NEXT: 0123456789
711 # CHECK-NEXT: Index 0123456789 012345678
714 # CHECK-NEXT: [0,1] D====eeeeER . . . . ssra v0.2d, v1.2d, #1
715 # CHECK-NEXT: [0,2] D=====eeeeER . . . . ssra v0.2d, v1.2d, #1
716 # CHECK-NEXT: [0,3] D=========eeeeER . . . ssra v0.2d, v0.2d, #1
717 # CHECK-NEXT: [1,0] D=============eeeeER. . . mul v0.4s, v0.4s, v0.4s
718 # CHECK-NEXT: [1,1] D=================eeeeER . . ssra v0.2d, v1.2d, #1
719 # CHECK-NEXT: [1,2] D==================eeeeER. . ssra v0.2d, v1.2d, #1
720 # CHECK-NEXT: [1,3] D======================eeeeER ssra v0.2d, v0.2d, #1
723 # CHECK-NEXT: [0]: Executions
724 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
725 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
726 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
728 # CHECK: [0] [1] [2] [3]
729 # CHECK-NEXT: 0. 2 7.5 0.5 0.0 mul v0.4s, v0.4s, v0.4s
730 # CHECK-NEXT: 1. 2 11.5 0.0 0.0 ssra v0.2d, v1.2d, #1
731 # CHECK-NEXT: 2. 2 12.5 0.0 0.0 ssra v0.2d, v1.2d, #1
732 # CHECK-NEXT: 3. 2 16.5 0.0 0.0 ssra v0.2d, v0.2d, #1
733 # CHECK-NEXT: 2 12.0 0.1 0.0 <total>
735 # CHECK: [11] Code Region - fcmla
738 # CHECK-NEXT: Instructions: 400
739 # CHECK-NEXT: Total Cycles: 1303
740 # CHECK-NEXT: Total uOps: 400
743 # CHECK-NEXT: uOps Per Cycle: 0.31
744 # CHECK-NEXT: IPC: 0.31
745 # CHECK-NEXT: Block RThroughput: 1.0
748 # CHECK-NEXT: 0123456789
749 # CHECK-NEXT: Index 0123456789 012345678
752 # CHECK-NEXT: [0,1] D===eeeeER. . . . . fcmla v0.2d, v1.2d, v2.2d, #90
753 # CHECK-NEXT: [0,2] D=====eeeeER . . . . fcmla v0.2d, v1.2d, v2.2d, #90
754 # CHECK-NEXT: [0,3] D=========eeeeER . . . fcmla v0.2d, v0.2d, v1.2d, #90
755 # CHECK-NEXT: [1,0] D=============eeeER . . . fmul v0.4s, v0.4s, v0.4s
756 # CHECK-NEXT: [1,1] D================eeeeER . . fcmla v0.2d, v1.2d, v2.2d, #90
757 # CHECK-NEXT: [1,2] D==================eeeeER. . fcmla v0.2d, v1.2d, v2.2d, #90
758 # CHECK-NEXT: [1,3] D======================eeeeER fcmla v0.2d, v0.2d, v1.2d, #90
761 # CHECK-NEXT: [0]: Executions
762 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
763 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
764 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
766 # CHECK: [0] [1] [2] [3]
767 # CHECK-NEXT: 0. 2 7.5 0.5 0.0 fmul v0.4s, v0.4s, v0.4s
768 # CHECK-NEXT: 1. 2 10.5 0.0 0.0 fcmla v0.2d, v1.2d, v2.2d, #90
769 # CHECK-NEXT: 2. 2 12.5 0.0 0.0 fcmla v0.2d, v1.2d, v2.2d, #90
770 # CHECK-NEXT: 3. 2 16.5 0.0 0.0 fcmla v0.2d, v0.2d, v1.2d, #90
771 # CHECK-NEXT: 2 11.8 0.1 0.0 <total>
773 # CHECK: [12] Code Region - fmla
776 # CHECK-NEXT: Instructions: 600
777 # CHECK-NEXT: Total Cycles: 1703
778 # CHECK-NEXT: Total uOps: 600
781 # CHECK-NEXT: uOps Per Cycle: 0.35
782 # CHECK-NEXT: IPC: 0.35
783 # CHECK-NEXT: Block RThroughput: 1.5
786 # CHECK-NEXT: 0123456789 0123456
787 # CHECK-NEXT: Index 0123456789 0123456789
789 # CHECK: [0,0] DeeeER . . . . . .. fmul v0.2d, v0.2d, v0.2d
790 # CHECK-NEXT: [0,1] D=eeeeER . . . . . .. fmla v0.2d, v1.2d, v2.2d
791 # CHECK-NEXT: [0,2] D=====eeER. . . . . .. fadd v0.2d, v0.2d, v0.2d
792 # CHECK-NEXT: [0,3] D=======eeeeER . . . . .. fmla v0.2d, v1.2d, v2.2d
793 # CHECK-NEXT: [0,4] D=========eeeeER . . . .. fmla v0.2d, v1.2d, v2.2d
794 # CHECK-NEXT: [0,5] D=============eeeeER. . . .. fmla v0.2d, v0.2d, v1.2d
795 # CHECK-NEXT: [1,0] D=================eeeER . . .. fmul v0.2d, v0.2d, v0.2d
796 # CHECK-NEXT: [1,1] D==================eeeeER. . .. fmla v0.2d, v1.2d, v2.2d
797 # CHECK-NEXT: [1,2] D======================eeER . .. fadd v0.2d, v0.2d, v0.2d
798 # CHECK-NEXT: [1,3] D========================eeeeER .. fmla v0.2d, v1.2d, v2.2d
799 # CHECK-NEXT: [1,4] D==========================eeeeER .. fmla v0.2d, v1.2d, v2.2d
800 # CHECK-NEXT: [1,5] D==============================eeeeER fmla v0.2d, v0.2d, v1.2d
803 # CHECK-NEXT: [0]: Executions
804 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
805 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
806 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
808 # CHECK: [0] [1] [2] [3]
809 # CHECK-NEXT: 0. 2 9.5 0.5 0.0 fmul v0.2d, v0.2d, v0.2d
810 # CHECK-NEXT: 1. 2 10.5 0.0 0.0 fmla v0.2d, v1.2d, v2.2d
811 # CHECK-NEXT: 2. 2 14.5 0.0 0.0 fadd v0.2d, v0.2d, v0.2d
812 # CHECK-NEXT: 3. 2 16.5 0.0 0.0 fmla v0.2d, v1.2d, v2.2d
813 # CHECK-NEXT: 4. 2 18.5 0.0 0.0 fmla v0.2d, v1.2d, v2.2d
814 # CHECK-NEXT: 5. 2 22.5 0.0 0.0 fmla v0.2d, v0.2d, v1.2d
815 # CHECK-NEXT: 2 15.3 0.1 0.0 <total>
817 # CHECK: [13] Code Region - fmlal
820 # CHECK-NEXT: Instructions: 600
821 # CHECK-NEXT: Total Cycles: 1903
822 # CHECK-NEXT: Total uOps: 600
825 # CHECK-NEXT: uOps Per Cycle: 0.32
826 # CHECK-NEXT: IPC: 0.32
827 # CHECK-NEXT: Block RThroughput: 1.5
830 # CHECK-NEXT: 0123456789 0123456789
831 # CHECK-NEXT: Index 0123456789 0123456789 0
833 # CHECK: [0,0] DeeeER . . . . . . . fmul v0.2d, v0.2d, v0.2d
834 # CHECK-NEXT: [0,1] D===eeeeER. . . . . . . fmlal v0.4s, v1.4h, v2.4h
835 # CHECK-NEXT: [0,2] D=======eeER . . . . . . fadd v0.2d, v0.2d, v0.2d
836 # CHECK-NEXT: [0,3] D=========eeeeER . . . . . fmlal v0.4s, v1.4h, v2.4h
837 # CHECK-NEXT: [0,4] D===========eeeeER . . . . . fmlal v0.4s, v1.4h, v2.4h
838 # CHECK-NEXT: [0,5] D===============eeeeER . . . . fmlal v0.4s, v0.4h, v1.4h
839 # CHECK-NEXT: [1,0] D===================eeeER. . . . fmul v0.2d, v0.2d, v0.2d
840 # CHECK-NEXT: [1,1] D======================eeeeER . . . fmlal v0.4s, v1.4h, v2.4h
841 # CHECK-NEXT: [1,2] D==========================eeER . . fadd v0.2d, v0.2d, v0.2d
842 # CHECK-NEXT: [1,3] D============================eeeeER. . fmlal v0.4s, v1.4h, v2.4h
843 # CHECK-NEXT: [1,4] D==============================eeeeER . fmlal v0.4s, v1.4h, v2.4h
844 # CHECK-NEXT: [1,5] D==================================eeeeER fmlal v0.4s, v0.4h, v1.4h
847 # CHECK-NEXT: [0]: Executions
848 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
849 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
850 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
852 # CHECK: [0] [1] [2] [3]
853 # CHECK-NEXT: 0. 2 10.5 0.5 0.0 fmul v0.2d, v0.2d, v0.2d
854 # CHECK-NEXT: 1. 2 13.5 0.0 0.0 fmlal v0.4s, v1.4h, v2.4h
855 # CHECK-NEXT: 2. 2 17.5 0.0 0.0 fadd v0.2d, v0.2d, v0.2d
856 # CHECK-NEXT: 3. 2 19.5 0.0 0.0 fmlal v0.4s, v1.4h, v2.4h
857 # CHECK-NEXT: 4. 2 21.5 0.0 0.0 fmlal v0.4s, v1.4h, v2.4h
858 # CHECK-NEXT: 5. 2 25.5 0.0 0.0 fmlal v0.4s, v0.4h, v1.4h
859 # CHECK-NEXT: 2 18.0 0.1 0.0 <total>
861 # CHECK: [14] Code Region - bfdot
864 # CHECK-NEXT: Instructions: 400
865 # CHECK-NEXT: Total Cycles: 1603
866 # CHECK-NEXT: Total uOps: 400
869 # CHECK-NEXT: uOps Per Cycle: 0.25
870 # CHECK-NEXT: IPC: 0.25
871 # CHECK-NEXT: Block RThroughput: 1.0
874 # CHECK-NEXT: 0123456789 01234
875 # CHECK-NEXT: Index 0123456789 0123456789
877 # CHECK: [0,0] DeeeER . . . . . . fmul v0.2d, v0.2d, v0.2d
878 # CHECK-NEXT: [0,1] D===eeeeeER . . . . . bfdot v0.4s, v1.8h, v2.8h
879 # CHECK-NEXT: [0,2] D======eeeeeER . . . . . bfdot v0.4s, v1.8h, v2.8h
880 # CHECK-NEXT: [0,3] D===========eeeeeER . . . . bfdot v0.4s, v0.8h, v1.8h
881 # CHECK-NEXT: [1,0] D================eeeER . . . fmul v0.2d, v0.2d, v0.2d
882 # CHECK-NEXT: [1,1] D===================eeeeeER . . bfdot v0.4s, v1.8h, v2.8h
883 # CHECK-NEXT: [1,2] D======================eeeeeER. . bfdot v0.4s, v1.8h, v2.8h
884 # CHECK-NEXT: [1,3] D===========================eeeeeER bfdot v0.4s, v0.8h, v1.8h
887 # CHECK-NEXT: [0]: Executions
888 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
889 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
890 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
892 # CHECK: [0] [1] [2] [3]
893 # CHECK-NEXT: 0. 2 9.0 0.5 0.0 fmul v0.2d, v0.2d, v0.2d
894 # CHECK-NEXT: 1. 2 12.0 0.0 0.0 bfdot v0.4s, v1.8h, v2.8h
895 # CHECK-NEXT: 2. 2 15.0 0.0 0.0 bfdot v0.4s, v1.8h, v2.8h
896 # CHECK-NEXT: 3. 2 20.0 0.0 0.0 bfdot v0.4s, v0.8h, v1.8h
897 # CHECK-NEXT: 2 14.0 0.1 0.0 <total>
899 # CHECK: [15] Code Region - bfmmla
902 # CHECK-NEXT: Instructions: 400
903 # CHECK-NEXT: Total Cycles: 1903
904 # CHECK-NEXT: Total uOps: 400
907 # CHECK-NEXT: uOps Per Cycle: 0.21
908 # CHECK-NEXT: IPC: 0.21
909 # CHECK-NEXT: Block RThroughput: 1.0
912 # CHECK-NEXT: 0123456789 0123456789
913 # CHECK-NEXT: Index 0123456789 0123456789 0
915 # CHECK: [0,0] DeeeER . . . . . . . fmul v0.2d, v0.2d, v0.2d
916 # CHECK-NEXT: [0,1] D===eeeeeeER . . . . . . bfmmla v0.4s, v1.8h, v2.8h
917 # CHECK-NEXT: [0,2] D=======eeeeeeER . . . . . bfmmla v0.4s, v1.8h, v2.8h
918 # CHECK-NEXT: [0,3] D=============eeeeeeER . . . . bfmmla v0.4s, v0.8h, v1.8h
919 # CHECK-NEXT: [1,0] D===================eeeER. . . . fmul v0.2d, v0.2d, v0.2d
920 # CHECK-NEXT: [1,1] D======================eeeeeeER . . bfmmla v0.4s, v1.8h, v2.8h
921 # CHECK-NEXT: [1,2] D==========================eeeeeeER. . bfmmla v0.4s, v1.8h, v2.8h
922 # CHECK-NEXT: [1,3] D================================eeeeeeER bfmmla v0.4s, v0.8h, v1.8h
925 # CHECK-NEXT: [0]: Executions
926 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
927 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
928 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
930 # CHECK: [0] [1] [2] [3]
931 # CHECK-NEXT: 0. 2 10.5 0.5 0.0 fmul v0.2d, v0.2d, v0.2d
932 # CHECK-NEXT: 1. 2 13.5 0.0 0.0 bfmmla v0.4s, v1.8h, v2.8h
933 # CHECK-NEXT: 2. 2 17.5 0.0 0.0 bfmmla v0.4s, v1.8h, v2.8h
934 # CHECK-NEXT: 3. 2 23.5 0.0 0.0 bfmmla v0.4s, v0.8h, v1.8h
935 # CHECK-NEXT: 2 16.3 0.1 0.0 <total>
937 # CHECK: [16] Code Region - bfmlalb
940 # CHECK-NEXT: Instructions: 400
941 # CHECK-NEXT: Total Cycles: 1503
942 # CHECK-NEXT: Total uOps: 400
945 # CHECK-NEXT: uOps Per Cycle: 0.27
946 # CHECK-NEXT: IPC: 0.27
947 # CHECK-NEXT: Block RThroughput: 1.0
950 # CHECK-NEXT: 0123456789 012
951 # CHECK-NEXT: Index 0123456789 0123456789
953 # CHECK: [0,0] DeeeER . . . . . . fmul v0.2d, v0.2d, v0.2d
954 # CHECK-NEXT: [0,1] D===eeeeeER . . . . . bfmlalb v0.4s, v1.8h, v2.8h
955 # CHECK-NEXT: [0,2] D=====eeeeeER . . . . . bfmlalb v0.4s, v1.8h, v2.8h
956 # CHECK-NEXT: [0,3] D==========eeeeeER . . . . bfmlalb v0.4s, v0.8h, v1.8h
957 # CHECK-NEXT: [1,0] D===============eeeER . . . fmul v0.2d, v0.2d, v0.2d
958 # CHECK-NEXT: [1,1] D==================eeeeeER . . bfmlalb v0.4s, v1.8h, v2.8h
959 # CHECK-NEXT: [1,2] D====================eeeeeER . . bfmlalb v0.4s, v1.8h, v2.8h
960 # CHECK-NEXT: [1,3] D=========================eeeeeER bfmlalb v0.4s, v0.8h, v1.8h
963 # CHECK-NEXT: [0]: Executions
964 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
965 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
966 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
968 # CHECK: [0] [1] [2] [3]
969 # CHECK-NEXT: 0. 2 8.5 0.5 0.0 fmul v0.2d, v0.2d, v0.2d
970 # CHECK-NEXT: 1. 2 11.5 0.0 0.0 bfmlalb v0.4s, v1.8h, v2.8h
971 # CHECK-NEXT: 2. 2 13.5 0.0 0.0 bfmlalb v0.4s, v1.8h, v2.8h
972 # CHECK-NEXT: 3. 2 18.5 0.0 0.0 bfmlalb v0.4s, v0.8h, v1.8h
973 # CHECK-NEXT: 2 13.0 0.1 0.0 <total>
975 # CHECK: [17] Code Region - crc32b
978 # CHECK-NEXT: Instructions: 400
979 # CHECK-NEXT: Total Cycles: 703
980 # CHECK-NEXT: Total uOps: 400
983 # CHECK-NEXT: uOps Per Cycle: 0.57
984 # CHECK-NEXT: IPC: 0.57
985 # CHECK-NEXT: Block RThroughput: 3.0
988 # CHECK-NEXT: 0123456
989 # CHECK-NEXT: Index 0123456789
992 # CHECK-NEXT: [0,1] D==eeER . .. crc32b w0, w0, w1
993 # CHECK-NEXT: [0,2] D===eeER . .. crc32b w0, w0, w1
994 # CHECK-NEXT: [0,3] D=====eeER. .. crc32b w0, w0, w0
995 # CHECK-NEXT: [1,0] D=======eeER .. mul w0, w0, w0
996 # CHECK-NEXT: [1,1] D=========eeER .. crc32b w0, w0, w1
997 # CHECK-NEXT: [1,2] D==========eeER.. crc32b w0, w0, w1
998 # CHECK-NEXT: [1,3] D============eeER crc32b w0, w0, w0
1001 # CHECK-NEXT: [0]: Executions
1002 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1003 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1004 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1006 # CHECK: [0] [1] [2] [3]
1007 # CHECK-NEXT: 0. 2 4.5 0.5 0.0 mul w0, w0, w0
1008 # CHECK-NEXT: 1. 2 6.5 0.0 0.0 crc32b w0, w0, w1
1009 # CHECK-NEXT: 2. 2 7.5 0.0 0.0 crc32b w0, w0, w1
1010 # CHECK-NEXT: 3. 2 9.5 0.0 0.0 crc32b w0, w0, w0
1011 # CHECK-NEXT: 2 7.0 0.1 0.0 <total>
1013 # CHECK: [18] Code Region - Z saba
1016 # CHECK-NEXT: Instructions: 400
1017 # CHECK-NEXT: Total Cycles: 1403
1018 # CHECK-NEXT: Total uOps: 500
1021 # CHECK-NEXT: uOps Per Cycle: 0.36
1022 # CHECK-NEXT: IPC: 0.29
1023 # CHECK-NEXT: Block RThroughput: 1.5
1026 # CHECK-NEXT: 0123456789 0
1027 # CHECK-NEXT: Index 0123456789 0123456789
1029 # CHECK: [0,0] DeeeeeER . . . . . mul z0.d, z0.d, z0.d
1030 # CHECK-NEXT: [0,1] D=====eeeeER . . . . saba z0.d, z1.d, z2.d
1031 # CHECK-NEXT: [0,2] D======eeeeER . . . . saba z0.d, z1.d, z2.d
1032 # CHECK-NEXT: [0,3] D==========eeeeER . . . saba z0.d, z0.d, z1.d
1033 # CHECK-NEXT: [1,0] D==============eeeeeER . . mul z0.d, z0.d, z0.d
1034 # CHECK-NEXT: [1,1] D===================eeeeER . saba z0.d, z1.d, z2.d
1035 # CHECK-NEXT: [1,2] D====================eeeeER . saba z0.d, z1.d, z2.d
1036 # CHECK-NEXT: [1,3] D========================eeeeER saba z0.d, z0.d, z1.d
1039 # CHECK-NEXT: [0]: Executions
1040 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1041 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1042 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1044 # CHECK: [0] [1] [2] [3]
1045 # CHECK-NEXT: 0. 2 8.0 0.5 0.0 mul z0.d, z0.d, z0.d
1046 # CHECK-NEXT: 1. 2 13.0 0.0 0.0 saba z0.d, z1.d, z2.d
1047 # CHECK-NEXT: 2. 2 14.0 0.0 0.0 saba z0.d, z1.d, z2.d
1048 # CHECK-NEXT: 3. 2 18.0 0.0 0.0 saba z0.d, z0.d, z1.d
1049 # CHECK-NEXT: 2 13.3 0.1 0.0 <total>
1051 # CHECK: [19] Code Region - Z sadalp
1054 # CHECK-NEXT: Instructions: 400
1055 # CHECK-NEXT: Total Cycles: 1403
1056 # CHECK-NEXT: Total uOps: 500
1059 # CHECK-NEXT: uOps Per Cycle: 0.36
1060 # CHECK-NEXT: IPC: 0.29
1061 # CHECK-NEXT: Block RThroughput: 1.5
1064 # CHECK-NEXT: 0123456789 0
1065 # CHECK-NEXT: Index 0123456789 0123456789
1067 # CHECK: [0,0] DeeeeeER . . . . . mul z0.d, z0.d, z0.d
1068 # CHECK-NEXT: [0,1] D=====eeeeER . . . . sadalp z0.d, p0/m, z1.s
1069 # CHECK-NEXT: [0,2] D======eeeeER . . . . sadalp z0.d, p0/m, z1.s
1070 # CHECK-NEXT: [0,3] D==========eeeeER . . . sadalp z0.d, p0/m, z0.s
1071 # CHECK-NEXT: [1,0] D==============eeeeeER . . mul z0.d, z0.d, z0.d
1072 # CHECK-NEXT: [1,1] D===================eeeeER . sadalp z0.d, p0/m, z1.s
1073 # CHECK-NEXT: [1,2] D====================eeeeER . sadalp z0.d, p0/m, z1.s
1074 # CHECK-NEXT: [1,3] D========================eeeeER sadalp z0.d, p0/m, z0.s
1077 # CHECK-NEXT: [0]: Executions
1078 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1079 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1080 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1082 # CHECK: [0] [1] [2] [3]
1083 # CHECK-NEXT: 0. 2 8.0 0.5 0.0 mul z0.d, z0.d, z0.d
1084 # CHECK-NEXT: 1. 2 13.0 0.0 0.0 sadalp z0.d, p0/m, z1.s
1085 # CHECK-NEXT: 2. 2 14.0 0.0 0.0 sadalp z0.d, p0/m, z1.s
1086 # CHECK-NEXT: 3. 2 18.0 0.0 0.0 sadalp z0.d, p0/m, z0.s
1087 # CHECK-NEXT: 2 13.3 0.1 0.0 <total>
1089 # CHECK: [20] Code Region - Z ssra
1092 # CHECK-NEXT: Instructions: 400
1093 # CHECK-NEXT: Total Cycles: 1403
1094 # CHECK-NEXT: Total uOps: 500
1097 # CHECK-NEXT: uOps Per Cycle: 0.36
1098 # CHECK-NEXT: IPC: 0.29
1099 # CHECK-NEXT: Block RThroughput: 1.5
1102 # CHECK-NEXT: 0123456789 0
1103 # CHECK-NEXT: Index 0123456789 0123456789
1105 # CHECK: [0,0] DeeeeeER . . . . . mul z0.d, z0.d, z0.d
1106 # CHECK-NEXT: [0,1] D=====eeeeER . . . . ssra z0.d, z1.d, #1
1107 # CHECK-NEXT: [0,2] D======eeeeER . . . . ssra z0.d, z1.d, #1
1108 # CHECK-NEXT: [0,3] D==========eeeeER . . . ssra z0.d, z0.d, #1
1109 # CHECK-NEXT: [1,0] D==============eeeeeER . . mul z0.d, z0.d, z0.d
1110 # CHECK-NEXT: [1,1] D===================eeeeER . ssra z0.d, z1.d, #1
1111 # CHECK-NEXT: [1,2] D====================eeeeER . ssra z0.d, z1.d, #1
1112 # CHECK-NEXT: [1,3] D========================eeeeER ssra z0.d, z0.d, #1
1115 # CHECK-NEXT: [0]: Executions
1116 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1117 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1118 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1120 # CHECK: [0] [1] [2] [3]
1121 # CHECK-NEXT: 0. 2 8.0 0.5 0.0 mul z0.d, z0.d, z0.d
1122 # CHECK-NEXT: 1. 2 13.0 0.0 0.0 ssra z0.d, z1.d, #1
1123 # CHECK-NEXT: 2. 2 14.0 0.0 0.0 ssra z0.d, z1.d, #1
1124 # CHECK-NEXT: 3. 2 18.0 0.0 0.0 ssra z0.d, z0.d, #1
1125 # CHECK-NEXT: 2 13.3 0.1 0.0 <total>
1127 # CHECK: [21] Code Region - Z cdot.s
1130 # CHECK-NEXT: Instructions: 400
1131 # CHECK-NEXT: Total Cycles: 1203
1132 # CHECK-NEXT: Total uOps: 500
1135 # CHECK-NEXT: uOps Per Cycle: 0.42
1136 # CHECK-NEXT: IPC: 0.33
1137 # CHECK-NEXT: Block RThroughput: 1.0
1140 # CHECK-NEXT: 0123456789
1141 # CHECK-NEXT: Index 0123456789 0123456
1143 # CHECK: [0,0] DeeeeeER . . . .. mul z0.d, z0.d, z0.d
1144 # CHECK-NEXT: [0,1] D=====eeeER . . .. cdot z0.s, z1.b, z2.b, #90
1145 # CHECK-NEXT: [0,2] D======eeeER . . .. cdot z0.s, z1.b, z2.b, #90
1146 # CHECK-NEXT: [0,3] D=========eeeER. . .. cdot z0.s, z0.b, z1.b, #90
1147 # CHECK-NEXT: [1,0] D============eeeeeER. .. mul z0.d, z0.d, z0.d
1148 # CHECK-NEXT: [1,1] D=================eeeER .. cdot z0.s, z1.b, z2.b, #90
1149 # CHECK-NEXT: [1,2] D==================eeeER .. cdot z0.s, z1.b, z2.b, #90
1150 # CHECK-NEXT: [1,3] D=====================eeeER cdot z0.s, z0.b, z1.b, #90
1153 # CHECK-NEXT: [0]: Executions
1154 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1155 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1156 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1158 # CHECK: [0] [1] [2] [3]
1159 # CHECK-NEXT: 0. 2 7.0 0.5 0.0 mul z0.d, z0.d, z0.d
1160 # CHECK-NEXT: 1. 2 12.0 0.0 0.0 cdot z0.s, z1.b, z2.b, #90
1161 # CHECK-NEXT: 2. 2 13.0 0.0 0.0 cdot z0.s, z1.b, z2.b, #90
1162 # CHECK-NEXT: 3. 2 16.0 0.0 0.0 cdot z0.s, z0.b, z1.b, #90
1163 # CHECK-NEXT: 2 12.0 0.1 0.0 <total>
1165 # CHECK: [22] Code Region - Z cdot.d
1168 # CHECK-NEXT: Instructions: 400
1169 # CHECK-NEXT: Total Cycles: 1403
1170 # CHECK-NEXT: Total uOps: 500
1173 # CHECK-NEXT: uOps Per Cycle: 0.36
1174 # CHECK-NEXT: IPC: 0.29
1175 # CHECK-NEXT: Block RThroughput: 2.5
1178 # CHECK-NEXT: 0123456789 0
1179 # CHECK-NEXT: Index 0123456789 0123456789
1181 # CHECK: [0,0] DeeeeeER . . . . . mul z0.d, z0.d, z0.d
1182 # CHECK-NEXT: [0,1] D=====eeeeER . . . . cdot z0.d, z1.h, z2.h, #90
1183 # CHECK-NEXT: [0,2] D======eeeeER . . . . cdot z0.d, z1.h, z2.h, #90
1184 # CHECK-NEXT: [0,3] D==========eeeeER . . . cdot z0.d, z0.h, z1.h, #90
1185 # CHECK-NEXT: [1,0] D==============eeeeeER . . mul z0.d, z0.d, z0.d
1186 # CHECK-NEXT: [1,1] D===================eeeeER . cdot z0.d, z1.h, z2.h, #90
1187 # CHECK-NEXT: [1,2] D====================eeeeER . cdot z0.d, z1.h, z2.h, #90
1188 # CHECK-NEXT: [1,3] D========================eeeeER cdot z0.d, z0.h, z1.h, #90
1191 # CHECK-NEXT: [0]: Executions
1192 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1193 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1194 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1196 # CHECK: [0] [1] [2] [3]
1197 # CHECK-NEXT: 0. 2 8.0 0.5 0.0 mul z0.d, z0.d, z0.d
1198 # CHECK-NEXT: 1. 2 13.0 0.0 0.0 cdot z0.d, z1.h, z2.h, #90
1199 # CHECK-NEXT: 2. 2 14.0 0.0 0.0 cdot z0.d, z1.h, z2.h, #90
1200 # CHECK-NEXT: 3. 2 18.0 0.0 0.0 cdot z0.d, z0.h, z1.h, #90
1201 # CHECK-NEXT: 2 13.3 0.1 0.0 <total>
1203 # CHECK: [23] Code Region - Z cmla.b
1206 # CHECK-NEXT: Instructions: 400
1207 # CHECK-NEXT: Total Cycles: 1403
1208 # CHECK-NEXT: Total uOps: 500
1211 # CHECK-NEXT: uOps Per Cycle: 0.36
1212 # CHECK-NEXT: IPC: 0.29
1213 # CHECK-NEXT: Block RThroughput: 2.5
1216 # CHECK-NEXT: 0123456789 0
1217 # CHECK-NEXT: Index 0123456789 0123456789
1219 # CHECK: [0,0] DeeeeeER . . . . . mul z0.d, z0.d, z0.d
1220 # CHECK-NEXT: [0,1] D=====eeeeER . . . . cmla z0.b, z1.b, z2.b, #90
1221 # CHECK-NEXT: [0,2] D======eeeeER . . . . cmla z0.b, z1.b, z2.b, #90
1222 # CHECK-NEXT: [0,3] D==========eeeeER . . . cmla z0.b, z0.b, z1.b, #90
1223 # CHECK-NEXT: [1,0] D==============eeeeeER . . mul z0.d, z0.d, z0.d
1224 # CHECK-NEXT: [1,1] D===================eeeeER . cmla z0.b, z1.b, z2.b, #90
1225 # CHECK-NEXT: [1,2] D====================eeeeER . cmla z0.b, z1.b, z2.b, #90
1226 # CHECK-NEXT: [1,3] D========================eeeeER cmla z0.b, z0.b, z1.b, #90
1229 # CHECK-NEXT: [0]: Executions
1230 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1231 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1232 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1234 # CHECK: [0] [1] [2] [3]
1235 # CHECK-NEXT: 0. 2 8.0 0.5 0.0 mul z0.d, z0.d, z0.d
1236 # CHECK-NEXT: 1. 2 13.0 0.0 0.0 cmla z0.b, z1.b, z2.b, #90
1237 # CHECK-NEXT: 2. 2 14.0 0.0 0.0 cmla z0.b, z1.b, z2.b, #90
1238 # CHECK-NEXT: 3. 2 18.0 0.0 0.0 cmla z0.b, z0.b, z1.b, #90
1239 # CHECK-NEXT: 2 13.3 0.1 0.0 <total>
1241 # CHECK: [24] Code Region - Z cmla.d
1244 # CHECK-NEXT: Instructions: 400
1245 # CHECK-NEXT: Total Cycles: 1803
1246 # CHECK-NEXT: Total uOps: 500
1249 # CHECK-NEXT: uOps Per Cycle: 0.28
1250 # CHECK-NEXT: IPC: 0.22
1251 # CHECK-NEXT: Block RThroughput: 4.0
1254 # CHECK-NEXT: 0123456789 012345678
1255 # CHECK-NEXT: Index 0123456789 0123456789
1257 # CHECK: [0,0] DeeeeeER . . . . . . . mul z0.d, z0.d, z0.d
1258 # CHECK-NEXT: [0,1] D=====eeeeeER . . . . . . cmla z0.d, z1.d, z2.d, #90
1259 # CHECK-NEXT: [0,2] D========eeeeeER . . . . . cmla z0.d, z1.d, z2.d, #90
1260 # CHECK-NEXT: [0,3] D=============eeeeeER . . . . cmla z0.d, z0.d, z1.d, #90
1261 # CHECK-NEXT: [1,0] D==================eeeeeER . . . mul z0.d, z0.d, z0.d
1262 # CHECK-NEXT: [1,1] D=======================eeeeeER . . cmla z0.d, z1.d, z2.d, #90
1263 # CHECK-NEXT: [1,2] D==========================eeeeeER . . cmla z0.d, z1.d, z2.d, #90
1264 # CHECK-NEXT: [1,3] D===============================eeeeeER cmla z0.d, z0.d, z1.d, #90
1267 # CHECK-NEXT: [0]: Executions
1268 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1269 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1270 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1272 # CHECK: [0] [1] [2] [3]
1273 # CHECK-NEXT: 0. 2 10.0 0.5 0.0 mul z0.d, z0.d, z0.d
1274 # CHECK-NEXT: 1. 2 15.0 0.0 0.0 cmla z0.d, z1.d, z2.d, #90
1275 # CHECK-NEXT: 2. 2 18.0 0.0 0.0 cmla z0.d, z1.d, z2.d, #90
1276 # CHECK-NEXT: 3. 2 23.0 0.0 0.0 cmla z0.d, z0.d, z1.d, #90
1277 # CHECK-NEXT: 2 16.5 0.1 0.0 <total>
1279 # CHECK: [25] Code Region - Z sdot.s
1282 # CHECK-NEXT: Instructions: 400
1283 # CHECK-NEXT: Total Cycles: 1203
1284 # CHECK-NEXT: Total uOps: 500
1287 # CHECK-NEXT: uOps Per Cycle: 0.42
1288 # CHECK-NEXT: IPC: 0.33
1289 # CHECK-NEXT: Block RThroughput: 1.0
1292 # CHECK-NEXT: 0123456789
1293 # CHECK-NEXT: Index 0123456789 0123456
1295 # CHECK: [0,0] DeeeeeER . . . .. mul z0.d, z0.d, z0.d
1296 # CHECK-NEXT: [0,1] D=====eeeER . . .. sdot z0.s, z1.b, z2.b
1297 # CHECK-NEXT: [0,2] D======eeeER . . .. sdot z0.s, z1.b, z2.b
1298 # CHECK-NEXT: [0,3] D=========eeeER. . .. sdot z0.s, z0.b, z1.b
1299 # CHECK-NEXT: [1,0] D============eeeeeER. .. mul z0.d, z0.d, z0.d
1300 # CHECK-NEXT: [1,1] D=================eeeER .. sdot z0.s, z1.b, z2.b
1301 # CHECK-NEXT: [1,2] D==================eeeER .. sdot z0.s, z1.b, z2.b
1302 # CHECK-NEXT: [1,3] D=====================eeeER sdot z0.s, z0.b, z1.b
1305 # CHECK-NEXT: [0]: Executions
1306 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1307 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1308 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1310 # CHECK: [0] [1] [2] [3]
1311 # CHECK-NEXT: 0. 2 7.0 0.5 0.0 mul z0.d, z0.d, z0.d
1312 # CHECK-NEXT: 1. 2 12.0 0.0 0.0 sdot z0.s, z1.b, z2.b
1313 # CHECK-NEXT: 2. 2 13.0 0.0 0.0 sdot z0.s, z1.b, z2.b
1314 # CHECK-NEXT: 3. 2 16.0 0.0 0.0 sdot z0.s, z0.b, z1.b
1315 # CHECK-NEXT: 2 12.0 0.1 0.0 <total>
1317 # CHECK: [26] Code Region - Z sudot
1320 # CHECK-NEXT: Instructions: 400
1321 # CHECK-NEXT: Total Cycles: 1203
1322 # CHECK-NEXT: Total uOps: 500
1325 # CHECK-NEXT: uOps Per Cycle: 0.42
1326 # CHECK-NEXT: IPC: 0.33
1327 # CHECK-NEXT: Block RThroughput: 1.0
1330 # CHECK-NEXT: 0123456789
1331 # CHECK-NEXT: Index 0123456789 0123456
1333 # CHECK: [0,0] DeeeeeER . . . .. mul z0.d, z0.d, z0.d
1334 # CHECK-NEXT: [0,1] D=====eeeER . . .. sdot z0.s, z1.b, z2.b[1]
1335 # CHECK-NEXT: [0,2] D======eeeER . . .. sdot z0.s, z1.b, z2.b[1]
1336 # CHECK-NEXT: [0,3] D=========eeeER. . .. sdot z0.s, z0.b, z1.b[1]
1337 # CHECK-NEXT: [1,0] D============eeeeeER. .. mul z0.d, z0.d, z0.d
1338 # CHECK-NEXT: [1,1] D=================eeeER .. sdot z0.s, z1.b, z2.b[1]
1339 # CHECK-NEXT: [1,2] D==================eeeER .. sdot z0.s, z1.b, z2.b[1]
1340 # CHECK-NEXT: [1,3] D=====================eeeER sdot z0.s, z0.b, z1.b[1]
1343 # CHECK-NEXT: [0]: Executions
1344 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1345 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1346 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1348 # CHECK: [0] [1] [2] [3]
1349 # CHECK-NEXT: 0. 2 7.0 0.5 0.0 mul z0.d, z0.d, z0.d
1350 # CHECK-NEXT: 1. 2 12.0 0.0 0.0 sdot z0.s, z1.b, z2.b[1]
1351 # CHECK-NEXT: 2. 2 13.0 0.0 0.0 sdot z0.s, z1.b, z2.b[1]
1352 # CHECK-NEXT: 3. 2 16.0 0.0 0.0 sdot z0.s, z0.b, z1.b[1]
1353 # CHECK-NEXT: 2 12.0 0.1 0.0 <total>
1355 # CHECK: [27] Code Region - Z sdot.d
1358 # CHECK-NEXT: Instructions: 400
1359 # CHECK-NEXT: Total Cycles: 1403
1360 # CHECK-NEXT: Total uOps: 500
1363 # CHECK-NEXT: uOps Per Cycle: 0.36
1364 # CHECK-NEXT: IPC: 0.29
1365 # CHECK-NEXT: Block RThroughput: 2.5
1368 # CHECK-NEXT: 0123456789 0
1369 # CHECK-NEXT: Index 0123456789 0123456789
1371 # CHECK: [0,0] DeeeeeER . . . . . mul z0.d, z0.d, z0.d
1372 # CHECK-NEXT: [0,1] D=====eeeeER . . . . sdot z0.d, z1.h, z2.h
1373 # CHECK-NEXT: [0,2] D======eeeeER . . . . sdot z0.d, z1.h, z2.h
1374 # CHECK-NEXT: [0,3] D==========eeeeER . . . sdot z0.d, z0.h, z1.h
1375 # CHECK-NEXT: [1,0] D==============eeeeeER . . mul z0.d, z0.d, z0.d
1376 # CHECK-NEXT: [1,1] D===================eeeeER . sdot z0.d, z1.h, z2.h
1377 # CHECK-NEXT: [1,2] D====================eeeeER . sdot z0.d, z1.h, z2.h
1378 # CHECK-NEXT: [1,3] D========================eeeeER sdot z0.d, z0.h, z1.h
1381 # CHECK-NEXT: [0]: Executions
1382 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1383 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1384 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1386 # CHECK: [0] [1] [2] [3]
1387 # CHECK-NEXT: 0. 2 8.0 0.5 0.0 mul z0.d, z0.d, z0.d
1388 # CHECK-NEXT: 1. 2 13.0 0.0 0.0 sdot z0.d, z1.h, z2.h
1389 # CHECK-NEXT: 2. 2 14.0 0.0 0.0 sdot z0.d, z1.h, z2.h
1390 # CHECK-NEXT: 3. 2 18.0 0.0 0.0 sdot z0.d, z0.h, z1.h
1391 # CHECK-NEXT: 2 13.3 0.1 0.0 <total>
1393 # CHECK: [28] Code Region - Z smmla
1396 # CHECK-NEXT: Instructions: 400
1397 # CHECK-NEXT: Total Cycles: 1103
1398 # CHECK-NEXT: Total uOps: 400
1401 # CHECK-NEXT: uOps Per Cycle: 0.36
1402 # CHECK-NEXT: IPC: 0.36
1403 # CHECK-NEXT: Block RThroughput: 0.8
1406 # CHECK-NEXT: 0123456789
1407 # CHECK-NEXT: Index 0123456789 01234
1410 # CHECK-NEXT: [0,1] D====eeeER. . . . smmla z0.s, z1.b, z2.b
1411 # CHECK-NEXT: [0,2] D=====eeeER . . . smmla z0.s, z1.b, z2.b
1412 # CHECK-NEXT: [0,3] D========eeeER . . . smmla z0.s, z0.b, z1.b
1413 # CHECK-NEXT: [1,0] D===========eeeeER . . mul z0.s, z0.s, z0.s
1414 # CHECK-NEXT: [1,1] D===============eeeER . smmla z0.s, z1.b, z2.b
1415 # CHECK-NEXT: [1,2] D================eeeER . smmla z0.s, z1.b, z2.b
1416 # CHECK-NEXT: [1,3] D===================eeeER smmla z0.s, z0.b, z1.b
1419 # CHECK-NEXT: [0]: Executions
1420 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1421 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1422 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1424 # CHECK: [0] [1] [2] [3]
1425 # CHECK-NEXT: 0. 2 6.5 0.5 0.0 mul z0.s, z0.s, z0.s
1426 # CHECK-NEXT: 1. 2 10.5 0.0 0.0 smmla z0.s, z1.b, z2.b
1427 # CHECK-NEXT: 2. 2 11.5 0.0 0.0 smmla z0.s, z1.b, z2.b
1428 # CHECK-NEXT: 3. 2 14.5 0.0 0.0 smmla z0.s, z0.b, z1.b
1429 # CHECK-NEXT: 2 10.8 0.1 0.0 <total>
1431 # CHECK: [29] Code Region - Z mla.b
1434 # CHECK-NEXT: Instructions: 400
1435 # CHECK-NEXT: Total Cycles: 1403
1436 # CHECK-NEXT: Total uOps: 500
1439 # CHECK-NEXT: uOps Per Cycle: 0.36
1440 # CHECK-NEXT: IPC: 0.29
1441 # CHECK-NEXT: Block RThroughput: 4.0
1444 # CHECK-NEXT: 0123456789 0
1445 # CHECK-NEXT: Index 0123456789 0123456789
1447 # CHECK: [0,0] DeeeeeER . . . . . mul z0.d, z0.d, z0.d
1448 # CHECK-NEXT: [0,1] D=====eeeeER . . . . mla z0.b, p0/m, z1.b, z2.b
1449 # CHECK-NEXT: [0,2] D======eeeeER . . . . mla z0.b, p0/m, z1.b, z2.b
1450 # CHECK-NEXT: [0,3] D==========eeeeER . . . mla z0.b, p0/m, z0.b, z1.b
1451 # CHECK-NEXT: [1,0] D==============eeeeeER . . mul z0.d, z0.d, z0.d
1452 # CHECK-NEXT: [1,1] D===================eeeeER . mla z0.b, p0/m, z1.b, z2.b
1453 # CHECK-NEXT: [1,2] D====================eeeeER . mla z0.b, p0/m, z1.b, z2.b
1454 # CHECK-NEXT: [1,3] D========================eeeeER mla z0.b, p0/m, z0.b, z1.b
1457 # CHECK-NEXT: [0]: Executions
1458 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1459 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1460 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1462 # CHECK: [0] [1] [2] [3]
1463 # CHECK-NEXT: 0. 2 8.0 0.5 0.0 mul z0.d, z0.d, z0.d
1464 # CHECK-NEXT: 1. 2 13.0 0.0 0.0 mla z0.b, p0/m, z1.b, z2.b
1465 # CHECK-NEXT: 2. 2 14.0 0.0 0.0 mla z0.b, p0/m, z1.b, z2.b
1466 # CHECK-NEXT: 3. 2 18.0 0.0 0.0 mla z0.b, p0/m, z0.b, z1.b
1467 # CHECK-NEXT: 2 13.3 0.1 0.0 <total>
1469 # CHECK: [30] Code Region - Z mla.d
1472 # CHECK-NEXT: Instructions: 400
1473 # CHECK-NEXT: Total Cycles: 1803
1474 # CHECK-NEXT: Total uOps: 500
1477 # CHECK-NEXT: uOps Per Cycle: 0.28
1478 # CHECK-NEXT: IPC: 0.22
1479 # CHECK-NEXT: Block RThroughput: 4.0
1482 # CHECK-NEXT: 0123456789 012345678
1483 # CHECK-NEXT: Index 0123456789 0123456789
1485 # CHECK: [0,0] DeeeeeER . . . . . . . mul z0.d, z0.d, z0.d
1486 # CHECK-NEXT: [0,1] D=====eeeeeER . . . . . . mla z0.d, p0/m, z1.d, z2.d
1487 # CHECK-NEXT: [0,2] D========eeeeeER . . . . . mla z0.d, p0/m, z1.d, z2.d
1488 # CHECK-NEXT: [0,3] D=============eeeeeER . . . . mla z0.d, p0/m, z0.d, z1.d
1489 # CHECK-NEXT: [1,0] D==================eeeeeER . . . mul z0.d, z0.d, z0.d
1490 # CHECK-NEXT: [1,1] D=======================eeeeeER . . mla z0.d, p0/m, z1.d, z2.d
1491 # CHECK-NEXT: [1,2] D==========================eeeeeER . . mla z0.d, p0/m, z1.d, z2.d
1492 # CHECK-NEXT: [1,3] D===============================eeeeeER mla z0.d, p0/m, z0.d, z1.d
1495 # CHECK-NEXT: [0]: Executions
1496 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1497 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1498 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1500 # CHECK: [0] [1] [2] [3]
1501 # CHECK-NEXT: 0. 2 10.0 0.5 0.0 mul z0.d, z0.d, z0.d
1502 # CHECK-NEXT: 1. 2 15.0 0.0 0.0 mla z0.d, p0/m, z1.d, z2.d
1503 # CHECK-NEXT: 2. 2 18.0 0.0 0.0 mla z0.d, p0/m, z1.d, z2.d
1504 # CHECK-NEXT: 3. 2 23.0 0.0 0.0 mla z0.d, p0/m, z0.d, z1.d
1505 # CHECK-NEXT: 2 16.5 0.1 0.0 <total>
1507 # CHECK: [31] Code Region - Z smlalb
1510 # CHECK-NEXT: Instructions: 400
1511 # CHECK-NEXT: Total Cycles: 1403
1512 # CHECK-NEXT: Total uOps: 500
1515 # CHECK-NEXT: uOps Per Cycle: 0.36
1516 # CHECK-NEXT: IPC: 0.29
1517 # CHECK-NEXT: Block RThroughput: 2.5
1520 # CHECK-NEXT: 0123456789 0
1521 # CHECK-NEXT: Index 0123456789 0123456789
1523 # CHECK: [0,0] DeeeeeER . . . . . mul z0.d, z0.d, z0.d
1524 # CHECK-NEXT: [0,1] D=====eeeeER . . . . smlalb z0.d, z1.s, z2.s
1525 # CHECK-NEXT: [0,2] D======eeeeER . . . . smlalb z0.d, z1.s, z2.s
1526 # CHECK-NEXT: [0,3] D==========eeeeER . . . smlalb z0.d, z0.s, z1.s
1527 # CHECK-NEXT: [1,0] D==============eeeeeER . . mul z0.d, z0.d, z0.d
1528 # CHECK-NEXT: [1,1] D===================eeeeER . smlalb z0.d, z1.s, z2.s
1529 # CHECK-NEXT: [1,2] D====================eeeeER . smlalb z0.d, z1.s, z2.s
1530 # CHECK-NEXT: [1,3] D========================eeeeER smlalb z0.d, z0.s, z1.s
1533 # CHECK-NEXT: [0]: Executions
1534 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1535 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1536 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1538 # CHECK: [0] [1] [2] [3]
1539 # CHECK-NEXT: 0. 2 8.0 0.5 0.0 mul z0.d, z0.d, z0.d
1540 # CHECK-NEXT: 1. 2 13.0 0.0 0.0 smlalb z0.d, z1.s, z2.s
1541 # CHECK-NEXT: 2. 2 14.0 0.0 0.0 smlalb z0.d, z1.s, z2.s
1542 # CHECK-NEXT: 3. 2 18.0 0.0 0.0 smlalb z0.d, z0.s, z1.s
1543 # CHECK-NEXT: 2 13.3 0.1 0.0 <total>
1545 # CHECK: [32] Code Region - Z sqdmlalb
1548 # CHECK-NEXT: Instructions: 400
1549 # CHECK-NEXT: Total Cycles: 1503
1550 # CHECK-NEXT: Total uOps: 500
1553 # CHECK-NEXT: uOps Per Cycle: 0.33
1554 # CHECK-NEXT: IPC: 0.27
1555 # CHECK-NEXT: Block RThroughput: 2.5
1558 # CHECK-NEXT: 0123456789 012
1559 # CHECK-NEXT: Index 0123456789 0123456789
1561 # CHECK: [0,0] DeeeeeER . . . . . . mul z0.d, z0.d, z0.d
1562 # CHECK-NEXT: [0,1] D=====eeeeER . . . . . sqdmlalb z0.d, z1.s, z2.s
1563 # CHECK-NEXT: [0,2] D=======eeeeER . . . . . sqdmlalb z0.d, z1.s, z2.s
1564 # CHECK-NEXT: [0,3] D===========eeeeER . . . . sqdmlalb z0.d, z0.s, z1.s
1565 # CHECK-NEXT: [1,0] D===============eeeeeER . . . mul z0.d, z0.d, z0.d
1566 # CHECK-NEXT: [1,1] D====================eeeeER . . sqdmlalb z0.d, z1.s, z2.s
1567 # CHECK-NEXT: [1,2] D======================eeeeER . . sqdmlalb z0.d, z1.s, z2.s
1568 # CHECK-NEXT: [1,3] D==========================eeeeER sqdmlalb z0.d, z0.s, z1.s
1571 # CHECK-NEXT: [0]: Executions
1572 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1573 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1574 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1576 # CHECK: [0] [1] [2] [3]
1577 # CHECK-NEXT: 0. 2 8.5 0.5 0.0 mul z0.d, z0.d, z0.d
1578 # CHECK-NEXT: 1. 2 13.5 0.0 0.0 sqdmlalb z0.d, z1.s, z2.s
1579 # CHECK-NEXT: 2. 2 15.5 0.0 0.0 sqdmlalb z0.d, z1.s, z2.s
1580 # CHECK-NEXT: 3. 2 19.5 0.0 0.0 sqdmlalb z0.d, z0.s, z1.s
1581 # CHECK-NEXT: 2 14.3 0.1 0.0 <total>
1583 # CHECK: [33] Code Region - Z sqrdmlah.b
1586 # CHECK-NEXT: Instructions: 400
1587 # CHECK-NEXT: Total Cycles: 1503
1588 # CHECK-NEXT: Total uOps: 500
1591 # CHECK-NEXT: uOps Per Cycle: 0.33
1592 # CHECK-NEXT: IPC: 0.27
1593 # CHECK-NEXT: Block RThroughput: 2.5
1596 # CHECK-NEXT: 0123456789 012
1597 # CHECK-NEXT: Index 0123456789 0123456789
1599 # CHECK: [0,0] DeeeeeER . . . . . . mul z0.d, z0.d, z0.d
1600 # CHECK-NEXT: [0,1] D=====eeeeER . . . . . sqrdmlah z0.b, z1.b, z2.b
1601 # CHECK-NEXT: [0,2] D=======eeeeER . . . . . sqrdmlah z0.b, z1.b, z2.b
1602 # CHECK-NEXT: [0,3] D===========eeeeER . . . . sqrdmlah z0.b, z0.b, z1.b
1603 # CHECK-NEXT: [1,0] D===============eeeeeER . . . mul z0.d, z0.d, z0.d
1604 # CHECK-NEXT: [1,1] D====================eeeeER . . sqrdmlah z0.b, z1.b, z2.b
1605 # CHECK-NEXT: [1,2] D======================eeeeER . . sqrdmlah z0.b, z1.b, z2.b
1606 # CHECK-NEXT: [1,3] D==========================eeeeER sqrdmlah z0.b, z0.b, z1.b
1609 # CHECK-NEXT: [0]: Executions
1610 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1611 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1612 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1614 # CHECK: [0] [1] [2] [3]
1615 # CHECK-NEXT: 0. 2 8.5 0.5 0.0 mul z0.d, z0.d, z0.d
1616 # CHECK-NEXT: 1. 2 13.5 0.0 0.0 sqrdmlah z0.b, z1.b, z2.b
1617 # CHECK-NEXT: 2. 2 15.5 0.0 0.0 sqrdmlah z0.b, z1.b, z2.b
1618 # CHECK-NEXT: 3. 2 19.5 0.0 0.0 sqrdmlah z0.b, z0.b, z1.b
1619 # CHECK-NEXT: 2 14.3 0.1 0.0 <total>
1621 # CHECK: [34] Code Region - Z sqrdmlah.d
1624 # CHECK-NEXT: Instructions: 400
1625 # CHECK-NEXT: Total Cycles: 1803
1626 # CHECK-NEXT: Total uOps: 500
1629 # CHECK-NEXT: uOps Per Cycle: 0.28
1630 # CHECK-NEXT: IPC: 0.22
1631 # CHECK-NEXT: Block RThroughput: 4.0
1634 # CHECK-NEXT: 0123456789 012345678
1635 # CHECK-NEXT: Index 0123456789 0123456789
1637 # CHECK: [0,0] DeeeeeER . . . . . . . mul z0.d, z0.d, z0.d
1638 # CHECK-NEXT: [0,1] D=====eeeeeER . . . . . . sqrdmlah z0.d, z1.d, z2.d
1639 # CHECK-NEXT: [0,2] D========eeeeeER . . . . . sqrdmlah z0.d, z1.d, z2.d
1640 # CHECK-NEXT: [0,3] D=============eeeeeER . . . . sqrdmlah z0.d, z0.d, z1.d
1641 # CHECK-NEXT: [1,0] D==================eeeeeER . . . mul z0.d, z0.d, z0.d
1642 # CHECK-NEXT: [1,1] D=======================eeeeeER . . sqrdmlah z0.d, z1.d, z2.d
1643 # CHECK-NEXT: [1,2] D==========================eeeeeER . . sqrdmlah z0.d, z1.d, z2.d
1644 # CHECK-NEXT: [1,3] D===============================eeeeeER sqrdmlah z0.d, z0.d, z1.d
1647 # CHECK-NEXT: [0]: Executions
1648 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1649 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1650 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1652 # CHECK: [0] [1] [2] [3]
1653 # CHECK-NEXT: 0. 2 10.0 0.5 0.0 mul z0.d, z0.d, z0.d
1654 # CHECK-NEXT: 1. 2 15.0 0.0 0.0 sqrdmlah z0.d, z1.d, z2.d
1655 # CHECK-NEXT: 2. 2 18.0 0.0 0.0 sqrdmlah z0.d, z1.d, z2.d
1656 # CHECK-NEXT: 3. 2 23.0 0.0 0.0 sqrdmlah z0.d, z0.d, z1.d
1657 # CHECK-NEXT: 2 16.5 0.1 0.0 <total>
1659 # CHECK: [35] Code Region - Z fcmla ZPmZZ
1662 # CHECK-NEXT: Instructions: 400
1663 # CHECK-NEXT: Total Cycles: 1503
1664 # CHECK-NEXT: Total uOps: 400
1667 # CHECK-NEXT: uOps Per Cycle: 0.27
1668 # CHECK-NEXT: IPC: 0.27
1669 # CHECK-NEXT: Block RThroughput: 1.0
1672 # CHECK-NEXT: 0123456789 012
1673 # CHECK-NEXT: Index 0123456789 0123456789
1675 # CHECK: [0,0] DeeeER . . . . . . fmul z0.d, z0.d, z0.d
1676 # CHECK-NEXT: [0,1] D===eeeeeER . . . . . fcmla z0.d, p0/m, z1.d, z2.d, #90
1677 # CHECK-NEXT: [0,2] D=====eeeeeER . . . . . fcmla z0.d, p0/m, z1.d, z2.d, #90
1678 # CHECK-NEXT: [0,3] D==========eeeeeER . . . . fcmla z0.d, p0/m, z0.d, z1.d, #90
1679 # CHECK-NEXT: [1,0] D===============eeeER . . . fmul z0.d, z0.d, z0.d
1680 # CHECK-NEXT: [1,1] D==================eeeeeER . . fcmla z0.d, p0/m, z1.d, z2.d, #90
1681 # CHECK-NEXT: [1,2] D====================eeeeeER . . fcmla z0.d, p0/m, z1.d, z2.d, #90
1682 # CHECK-NEXT: [1,3] D=========================eeeeeER fcmla z0.d, p0/m, z0.d, z1.d, #90
1685 # CHECK-NEXT: [0]: Executions
1686 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1687 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1688 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1690 # CHECK: [0] [1] [2] [3]
1691 # CHECK-NEXT: 0. 2 8.5 0.5 0.0 fmul z0.d, z0.d, z0.d
1692 # CHECK-NEXT: 1. 2 11.5 0.0 0.0 fcmla z0.d, p0/m, z1.d, z2.d, #90
1693 # CHECK-NEXT: 2. 2 13.5 0.0 0.0 fcmla z0.d, p0/m, z1.d, z2.d, #90
1694 # CHECK-NEXT: 3. 2 18.5 0.0 0.0 fcmla z0.d, p0/m, z0.d, z1.d, #90
1695 # CHECK-NEXT: 2 13.0 0.1 0.0 <total>
1697 # CHECK: [36] Code Region - Z fcmla ZZZI
1700 # CHECK-NEXT: Instructions: 400
1701 # CHECK-NEXT: Total Cycles: 1503
1702 # CHECK-NEXT: Total uOps: 400
1705 # CHECK-NEXT: uOps Per Cycle: 0.27
1706 # CHECK-NEXT: IPC: 0.27
1707 # CHECK-NEXT: Block RThroughput: 1.0
1710 # CHECK-NEXT: 0123456789 012
1711 # CHECK-NEXT: Index 0123456789 0123456789
1713 # CHECK: [0,0] DeeeER . . . . . . fmul z0.d, z0.d, z0.d
1714 # CHECK-NEXT: [0,1] D===eeeeeER . . . . . fcmla z0.s, z1.s, z2.s[1], #90
1715 # CHECK-NEXT: [0,2] D=====eeeeeER . . . . . fcmla z0.s, z1.s, z2.s[1], #90
1716 # CHECK-NEXT: [0,3] D==========eeeeeER . . . . fcmla z0.s, z0.s, z1.s[1], #90
1717 # CHECK-NEXT: [1,0] D===============eeeER . . . fmul z0.d, z0.d, z0.d
1718 # CHECK-NEXT: [1,1] D==================eeeeeER . . fcmla z0.s, z1.s, z2.s[1], #90
1719 # CHECK-NEXT: [1,2] D====================eeeeeER . . fcmla z0.s, z1.s, z2.s[1], #90
1720 # CHECK-NEXT: [1,3] D=========================eeeeeER fcmla z0.s, z0.s, z1.s[1], #90
1723 # CHECK-NEXT: [0]: Executions
1724 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1725 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1726 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1728 # CHECK: [0] [1] [2] [3]
1729 # CHECK-NEXT: 0. 2 8.5 0.5 0.0 fmul z0.d, z0.d, z0.d
1730 # CHECK-NEXT: 1. 2 11.5 0.0 0.0 fcmla z0.s, z1.s, z2.s[1], #90
1731 # CHECK-NEXT: 2. 2 13.5 0.0 0.0 fcmla z0.s, z1.s, z2.s[1], #90
1732 # CHECK-NEXT: 3. 2 18.5 0.0 0.0 fcmla z0.s, z0.s, z1.s[1], #90
1733 # CHECK-NEXT: 2 13.0 0.1 0.0 <total>
1735 # CHECK: [37] Code Region - Z fmla ZPmZZ
1738 # CHECK-NEXT: Instructions: 400
1739 # CHECK-NEXT: Total Cycles: 1303
1740 # CHECK-NEXT: Total uOps: 400
1743 # CHECK-NEXT: uOps Per Cycle: 0.31
1744 # CHECK-NEXT: IPC: 0.31
1745 # CHECK-NEXT: Block RThroughput: 1.0
1748 # CHECK-NEXT: 0123456789
1749 # CHECK-NEXT: Index 0123456789 012345678
1751 # CHECK: [0,0] DeeeER . . . . . fmul z0.d, z0.d, z0.d
1752 # CHECK-NEXT: [0,1] D===eeeeER. . . . . fmla z0.d, p0/m, z1.d, z2.d
1753 # CHECK-NEXT: [0,2] D=====eeeeER . . . . fmla z0.d, p0/m, z1.d, z2.d
1754 # CHECK-NEXT: [0,3] D=========eeeeER . . . fmla z0.d, p0/m, z0.d, z1.d
1755 # CHECK-NEXT: [1,0] D=============eeeER . . . fmul z0.d, z0.d, z0.d
1756 # CHECK-NEXT: [1,1] D================eeeeER . . fmla z0.d, p0/m, z1.d, z2.d
1757 # CHECK-NEXT: [1,2] D==================eeeeER. . fmla z0.d, p0/m, z1.d, z2.d
1758 # CHECK-NEXT: [1,3] D======================eeeeER fmla z0.d, p0/m, z0.d, z1.d
1761 # CHECK-NEXT: [0]: Executions
1762 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1763 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1764 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1766 # CHECK: [0] [1] [2] [3]
1767 # CHECK-NEXT: 0. 2 7.5 0.5 0.0 fmul z0.d, z0.d, z0.d
1768 # CHECK-NEXT: 1. 2 10.5 0.0 0.0 fmla z0.d, p0/m, z1.d, z2.d
1769 # CHECK-NEXT: 2. 2 12.5 0.0 0.0 fmla z0.d, p0/m, z1.d, z2.d
1770 # CHECK-NEXT: 3. 2 16.5 0.0 0.0 fmla z0.d, p0/m, z0.d, z1.d
1771 # CHECK-NEXT: 2 11.8 0.1 0.0 <total>
1773 # CHECK: [38] Code Region - Z fmla ZZZI
1776 # CHECK-NEXT: Instructions: 400
1777 # CHECK-NEXT: Total Cycles: 1303
1778 # CHECK-NEXT: Total uOps: 400
1781 # CHECK-NEXT: uOps Per Cycle: 0.31
1782 # CHECK-NEXT: IPC: 0.31
1783 # CHECK-NEXT: Block RThroughput: 1.0
1786 # CHECK-NEXT: 0123456789
1787 # CHECK-NEXT: Index 0123456789 012345678
1789 # CHECK: [0,0] DeeeER . . . . . fmul z0.d, z0.d, z0.d
1790 # CHECK-NEXT: [0,1] D===eeeeER. . . . . fmla z0.d, z1.d, z2.d[1]
1791 # CHECK-NEXT: [0,2] D=====eeeeER . . . . fmla z0.d, z1.d, z2.d[1]
1792 # CHECK-NEXT: [0,3] D=========eeeeER . . . fmla z0.d, z0.d, z1.d[1]
1793 # CHECK-NEXT: [1,0] D=============eeeER . . . fmul z0.d, z0.d, z0.d
1794 # CHECK-NEXT: [1,1] D================eeeeER . . fmla z0.d, z1.d, z2.d[1]
1795 # CHECK-NEXT: [1,2] D==================eeeeER. . fmla z0.d, z1.d, z2.d[1]
1796 # CHECK-NEXT: [1,3] D======================eeeeER fmla z0.d, z0.d, z1.d[1]
1799 # CHECK-NEXT: [0]: Executions
1800 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1801 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1802 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1804 # CHECK: [0] [1] [2] [3]
1805 # CHECK-NEXT: 0. 2 7.5 0.5 0.0 fmul z0.d, z0.d, z0.d
1806 # CHECK-NEXT: 1. 2 10.5 0.0 0.0 fmla z0.d, z1.d, z2.d[1]
1807 # CHECK-NEXT: 2. 2 12.5 0.0 0.0 fmla z0.d, z1.d, z2.d[1]
1808 # CHECK-NEXT: 3. 2 16.5 0.0 0.0 fmla z0.d, z0.d, z1.d[1]
1809 # CHECK-NEXT: 2 11.8 0.1 0.0 <total>
1811 # CHECK: [39] Code Region - Z fmlalb ZZZ
1814 # CHECK-NEXT: Instructions: 400
1815 # CHECK-NEXT: Total Cycles: 1303
1816 # CHECK-NEXT: Total uOps: 400
1819 # CHECK-NEXT: uOps Per Cycle: 0.31
1820 # CHECK-NEXT: IPC: 0.31
1821 # CHECK-NEXT: Block RThroughput: 1.0
1824 # CHECK-NEXT: 0123456789
1825 # CHECK-NEXT: Index 0123456789 012345678
1827 # CHECK: [0,0] DeeeER . . . . . fmul z0.d, z0.d, z0.d
1828 # CHECK-NEXT: [0,1] D===eeeeER. . . . . fmlalb z0.s, z1.h, z2.h
1829 # CHECK-NEXT: [0,2] D=====eeeeER . . . . fmlalb z0.s, z1.h, z2.h
1830 # CHECK-NEXT: [0,3] D=========eeeeER . . . fmlalb z0.s, z0.h, z1.h
1831 # CHECK-NEXT: [1,0] D=============eeeER . . . fmul z0.d, z0.d, z0.d
1832 # CHECK-NEXT: [1,1] D================eeeeER . . fmlalb z0.s, z1.h, z2.h
1833 # CHECK-NEXT: [1,2] D==================eeeeER. . fmlalb z0.s, z1.h, z2.h
1834 # CHECK-NEXT: [1,3] D======================eeeeER fmlalb z0.s, z0.h, z1.h
1837 # CHECK-NEXT: [0]: Executions
1838 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1839 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1840 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1842 # CHECK: [0] [1] [2] [3]
1843 # CHECK-NEXT: 0. 2 7.5 0.5 0.0 fmul z0.d, z0.d, z0.d
1844 # CHECK-NEXT: 1. 2 10.5 0.0 0.0 fmlalb z0.s, z1.h, z2.h
1845 # CHECK-NEXT: 2. 2 12.5 0.0 0.0 fmlalb z0.s, z1.h, z2.h
1846 # CHECK-NEXT: 3. 2 16.5 0.0 0.0 fmlalb z0.s, z0.h, z1.h
1847 # CHECK-NEXT: 2 11.8 0.1 0.0 <total>
1849 # CHECK: [40] Code Region - Z bfdot
1852 # CHECK-NEXT: Instructions: 400
1853 # CHECK-NEXT: Total Cycles: 1603
1854 # CHECK-NEXT: Total uOps: 400
1857 # CHECK-NEXT: uOps Per Cycle: 0.25
1858 # CHECK-NEXT: IPC: 0.25
1859 # CHECK-NEXT: Block RThroughput: 1.0
1862 # CHECK-NEXT: 0123456789 01234
1863 # CHECK-NEXT: Index 0123456789 0123456789
1865 # CHECK: [0,0] DeeeER . . . . . . fmul z0.d, z0.d, z0.d
1866 # CHECK-NEXT: [0,1] D===eeeeeER . . . . . bfdot z0.s, z1.h, z2.h
1867 # CHECK-NEXT: [0,2] D======eeeeeER . . . . . bfdot z0.s, z1.h, z2.h
1868 # CHECK-NEXT: [0,3] D===========eeeeeER . . . . bfdot z0.s, z0.h, z1.h
1869 # CHECK-NEXT: [1,0] D================eeeER . . . fmul z0.d, z0.d, z0.d
1870 # CHECK-NEXT: [1,1] D===================eeeeeER . . bfdot z0.s, z1.h, z2.h
1871 # CHECK-NEXT: [1,2] D======================eeeeeER. . bfdot z0.s, z1.h, z2.h
1872 # CHECK-NEXT: [1,3] D===========================eeeeeER bfdot z0.s, z0.h, z1.h
1875 # CHECK-NEXT: [0]: Executions
1876 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1877 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1878 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1880 # CHECK: [0] [1] [2] [3]
1881 # CHECK-NEXT: 0. 2 9.0 0.5 0.0 fmul z0.d, z0.d, z0.d
1882 # CHECK-NEXT: 1. 2 12.0 0.0 0.0 bfdot z0.s, z1.h, z2.h
1883 # CHECK-NEXT: 2. 2 15.0 0.0 0.0 bfdot z0.s, z1.h, z2.h
1884 # CHECK-NEXT: 3. 2 20.0 0.0 0.0 bfdot z0.s, z0.h, z1.h
1885 # CHECK-NEXT: 2 14.0 0.1 0.0 <total>
1887 # CHECK: [41] Code Region - Z bfmmla
1890 # CHECK-NEXT: Instructions: 400
1891 # CHECK-NEXT: Total Cycles: 1903
1892 # CHECK-NEXT: Total uOps: 400
1895 # CHECK-NEXT: uOps Per Cycle: 0.21
1896 # CHECK-NEXT: IPC: 0.21
1897 # CHECK-NEXT: Block RThroughput: 1.0
1900 # CHECK-NEXT: 0123456789 0123456789
1901 # CHECK-NEXT: Index 0123456789 0123456789 0
1903 # CHECK: [0,0] DeeeER . . . . . . . fmul z0.d, z0.d, z0.d
1904 # CHECK-NEXT: [0,1] D===eeeeeeER . . . . . . bfmmla z0.s, z1.h, z2.h
1905 # CHECK-NEXT: [0,2] D=======eeeeeeER . . . . . bfmmla z0.s, z1.h, z2.h
1906 # CHECK-NEXT: [0,3] D=============eeeeeeER . . . . bfmmla z0.s, z0.h, z1.h
1907 # CHECK-NEXT: [1,0] D===================eeeER. . . . fmul z0.d, z0.d, z0.d
1908 # CHECK-NEXT: [1,1] D======================eeeeeeER . . bfmmla z0.s, z1.h, z2.h
1909 # CHECK-NEXT: [1,2] D==========================eeeeeeER. . bfmmla z0.s, z1.h, z2.h
1910 # CHECK-NEXT: [1,3] D================================eeeeeeER bfmmla z0.s, z0.h, z1.h
1913 # CHECK-NEXT: [0]: Executions
1914 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1915 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1916 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1918 # CHECK: [0] [1] [2] [3]
1919 # CHECK-NEXT: 0. 2 10.5 0.5 0.0 fmul z0.d, z0.d, z0.d
1920 # CHECK-NEXT: 1. 2 13.5 0.0 0.0 bfmmla z0.s, z1.h, z2.h
1921 # CHECK-NEXT: 2. 2 17.5 0.0 0.0 bfmmla z0.s, z1.h, z2.h
1922 # CHECK-NEXT: 3. 2 23.5 0.0 0.0 bfmmla z0.s, z0.h, z1.h
1923 # CHECK-NEXT: 2 16.3 0.1 0.0 <total>
1925 # CHECK: [42] Code Region - bfmlalb
1928 # CHECK-NEXT: Instructions: 400
1929 # CHECK-NEXT: Total Cycles: 1503
1930 # CHECK-NEXT: Total uOps: 400
1933 # CHECK-NEXT: uOps Per Cycle: 0.27
1934 # CHECK-NEXT: IPC: 0.27
1935 # CHECK-NEXT: Block RThroughput: 1.0
1938 # CHECK-NEXT: 0123456789 012
1939 # CHECK-NEXT: Index 0123456789 0123456789
1941 # CHECK: [0,0] DeeeER . . . . . . fmul z0.d, z0.d, z0.d
1942 # CHECK-NEXT: [0,1] D===eeeeeER . . . . . bfmlalb z0.s, z1.h, z2.h
1943 # CHECK-NEXT: [0,2] D=====eeeeeER . . . . . bfmlalb z0.s, z1.h, z2.h
1944 # CHECK-NEXT: [0,3] D==========eeeeeER . . . . bfmlalb z0.s, z0.h, z1.h
1945 # CHECK-NEXT: [1,0] D===============eeeER . . . fmul z0.d, z0.d, z0.d
1946 # CHECK-NEXT: [1,1] D==================eeeeeER . . bfmlalb z0.s, z1.h, z2.h
1947 # CHECK-NEXT: [1,2] D====================eeeeeER . . bfmlalb z0.s, z1.h, z2.h
1948 # CHECK-NEXT: [1,3] D=========================eeeeeER bfmlalb z0.s, z0.h, z1.h
1951 # CHECK-NEXT: [0]: Executions
1952 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
1953 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
1954 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
1956 # CHECK: [0] [1] [2] [3]
1957 # CHECK-NEXT: 0. 2 8.5 0.5 0.0 fmul z0.d, z0.d, z0.d
1958 # CHECK-NEXT: 1. 2 11.5 0.0 0.0 bfmlalb z0.s, z1.h, z2.h
1959 # CHECK-NEXT: 2. 2 13.5 0.0 0.0 bfmlalb z0.s, z1.h, z2.h
1960 # CHECK-NEXT: 3. 2 18.5 0.0 0.0 bfmlalb z0.s, z0.h, z1.h
1961 # CHECK-NEXT: 2 13.0 0.1 0.0 <total>