Implicitly padded FFT convolution / results.json
Failed on benchmark
1{
2 "dft_inverse": [
3 {
4 "kind": "dft",
5 "L": 7,
6 "M": 16,
7 "m": 1,
8 "relerr": 1.1817672573251125e-15
9 },
10 {
11 "kind": "inverse",
12 "L": 7,
13 "M": 16,
14 "m": 1,
15 "relerr": 5.800052325495267e-16
16 },
17 {
18 "kind": "dft",
19 "L": 7,
20 "M": 16,
21 "m": 2,
22 "relerr": 2.8967725563412747e-16
23 },
24 {
25 "kind": "inverse",
26 "L": 7,
27 "M": 16,
28 "m": 2,
29 "relerr": 2.1143684992226253e-16
30 },
31 {
32 "kind": "dft",
33 "L": 7,
34 "M": 16,
35 "m": 4,
36 "relerr": 2.3127439775969316e-16
37 },
38 {
39 "kind": "inverse",
40 "L": 7,
41 "M": 16,
42 "m": 4,
43 "relerr": 1.256470296091257e-16
44 },
45 {
46 "kind": "dft",
47 "L": 7,
48 "M": 16,
49 "m": 8,
50 "relerr": 7.689008398908375e-16
51 },
52 {
53 "kind": "inverse",
54 "L": 7,
55 "M": 16,
56 "m": 8,
57 "relerr": 5.428450561933255e-16
58 },
59 {
60 "kind": "dft",
61 "L": 7,
62 "M": 16,
63 "m": 16,
64 "relerr": 1.1817672573251125e-15
65 },
66 {
67 "kind": "inverse",
68 "L": 7,
69 "M": 16,
70 "m": 16,
71 "relerr": 7.04938364200749e-16
72 },
73 {
74 "kind": "dft",
75 "L": 31,
76 "M": 64,
77 "m": 1,
78 "relerr": 5.863129525770377e-15
79 },
80 {
81 "kind": "inverse",
82 "L": 31,
83 "M": 64,
84 "m": 1,
85 "relerr": 3.136409233535329e-15
86 },
87 {
88 "kind": "dft",
89 "L": 31,
90 "M": 64,
91 "m": 2,
92 "relerr": 2.3355442651580886e-15
93 },
94 {
95 "kind": "inverse",
96 "L": 31,
97 "M": 64,
98 "m": 2,
99 "relerr": 1.7863978104310233e-15
100 },
101 {
102 "kind": "dft",
103 "L": 31,
104 "M": 64,
105 "m": 4,
106 "relerr": 1.390667846418911e-15
107 },
108 {
109 "kind": "inverse",
110 "L": 31,
111 "M": 64,
112 "m": 4,
113 "relerr": 8.963175860900024e-16
114 },
115 {
116 "kind": "dft",
117 "L": 31,
118 "M": 64,
119 "m": 8,
120 "relerr": 1.0800611686796005e-15
121 },
122 {
123 "kind": "inverse",
124 "L": 31,
125 "M": 64,
126 "m": 8,
127 "relerr": 7.678300105713112e-16
128 },
129 {
130 "kind": "dft",
131 "L": 31,
132 "M": 64,
133 "m": 16,
134 "relerr": 2.5581280969454134e-15
135 },
136 {
137 "kind": "inverse",
138 "L": 31,
139 "M": 64,
140 "m": 16,
141 "relerr": 2.9306566961545307e-15
142 },
143 {
144 "kind": "dft",
145 "L": 31,
146 "M": 64,
147 "m": 32,
148 "relerr": 5.724953123758176e-15
149 },
150 {
151 "kind": "inverse",
152 "L": 31,
153 "M": 64,
154 "m": 32,
155 "relerr": 6.6278732898028246e-15
156 },
157 {
158 "kind": "dft",
159 "L": 100,
160 "M": 256,
161 "m": 1,
162 "relerr": 1.4839991028347374e-14
163 },
164 {
165 "kind": "inverse",
166 "L": 100,
167 "M": 256,
168 "m": 1,
169 "relerr": 9.319497032582605e-15
170 },
171 {
172 "kind": "dft",
173 "L": 100,
174 "M": 256,
175 "m": 2,
176 "relerr": 8.585410927645497e-15
177 },
178 {
179 "kind": "inverse",
180 "L": 100,
181 "M": 256,
182 "m": 2,
183 "relerr": 4.572584040807797e-15
184 },
185 {
186 "kind": "dft",
187 "L": 100,
188 "M": 256,
189 "m": 4,
190 "relerr": 4.1601637950233284e-15
191 },
192 {
193 "kind": "inverse",
194 "L": 100,
195 "M": 256,
196 "m": 4,
197 "relerr": 2.121597055397902e-15
198 },
199 {
200 "kind": "dft",
201 "L": 100,
202 "M": 256,
203 "m": 8,
204 "relerr": 2.35726461684896e-15
205 },
206 {
207 "kind": "inverse",
208 "L": 100,
209 "M": 256,
210 "m": 8,
211 "relerr": 1.676387670099207e-15
212 },
213 {
214 "kind": "dft",
215 "L": 100,
216 "M": 256,
217 "m": 16,
218 "relerr": 3.0790631866473204e-15
219 },
220 {
221 "kind": "inverse",
222 "L": 100,
223 "M": 256,
224 "m": 16,
225 "relerr": 3.137296117417639e-15
226 },
227 {
228 "kind": "dft",
229 "L": 100,
230 "M": 256,
231 "m": 32,
232 "relerr": 5.7758021310076334e-15
233 },
234 {
235 "kind": "inverse",
236 "L": 100,
237 "M": 256,
238 "m": 32,
239 "relerr": 5.5400269847739274e-15
240 },
241 {
242 "kind": "dft",
243 "L": 257,
244 "M": 1024,
245 "m": 1,
246 "relerr": 4.0453723234064364e-14
247 },
248 {
249 "kind": "inverse",
250 "L": 257,
251 "M": 1024,
252 "m": 1,
253 "relerr": 1.8784134976927756e-14
254 },
255 {
256 "kind": "dft",
257 "L": 257,
258 "M": 1024,
259 "m": 2,
260 "relerr": 2.041789667859922e-14
261 },
262 {
263 "kind": "inverse",
264 "L": 257,
265 "M": 1024,
266 "m": 2,
267 "relerr": 9.957202743839094e-15
268 },
269 {
270 "kind": "dft",
271 "L": 257,
272 "M": 1024,
273 "m": 4,
274 "relerr": 9.836690298015777e-15
275 },
276 {
277 "kind": "inverse",
278 "L": 257,
279 "M": 1024,
280 "m": 4,
281 "relerr": 5.498107195361835e-15
282 },
283 {
284 "kind": "dft",
285 "L": 257,
286 "M": 1024,
287 "m": 8,
288 "relerr": 5.098244287507985e-15
289 },
290 {
291 "kind": "inverse",
292 "L": 257,
293 "M": 1024,
294 "m": 8,
295 "relerr": 2.6384801330566118e-15
296 },
297 {
298 "kind": "dft",
299 "L": 257,
300 "M": 1024,
301 "m": 16,
302 "relerr": 3.9447977241766755e-15
303 },
304 {
305 "kind": "inverse",
306 "L": 257,
307 "M": 1024,
308 "m": 16,
309 "relerr": 3.572719277747502e-15
310 },
311 {
312 "kind": "dft",
313 "L": 257,
314 "M": 1024,
315 "m": 32,
316 "relerr": 5.722703154512586e-15
317 },
318 {
319 "kind": "inverse",
320 "L": 257,
321 "M": 1024,
322 "m": 32,
323 "relerr": 5.803750325148828e-15
324 }
325 ],
326 "convolution": [
327 {
328 "L": 13,
329 "K": 5,
330 "M": 32,
331 "m": 1,
332 "relerr": 1.7379818107305134e-15
333 },
334 {
335 "L": 13,
336 "K": 5,
337 "M": 32,
338 "m": 2,
339 "relerr": 6.094347722436765e-16
340 },
341 {
342 "L": 13,
343 "K": 5,
344 "M": 32,
345 "m": 4,
346 "relerr": 2.26747433366447e-16
347 },
348 {
349 "L": 13,
350 "K": 5,
351 "M": 32,
352 "m": 8,
353 "relerr": 5.584499330869923e-16
354 },
355 {
356 "L": 13,
357 "K": 5,
358 "M": 32,
359 "m": 16,
360 "relerr": 1.6043046109323924e-15
361 },
362 {
363 "L": 13,
364 "K": 5,
365 "M": 32,
366 "m": 32,
367 "relerr": 1.3706249054340375e-15
368 },
369 {
370 "L": 31,
371 "K": 17,
372 "M": 64,
373 "m": 1,
374 "relerr": 5.49895747362759e-15
375 },
376 {
377 "L": 31,
378 "K": 17,
379 "M": 64,
380 "m": 2,
381 "relerr": 3.136517145278133e-15
382 },
383 {
384 "L": 31,
385 "K": 17,
386 "M": 64,
387 "m": 4,
388 "relerr": 1.3928054129534594e-15
389 },
390 {
391 "L": 31,
392 "K": 17,
393 "M": 64,
394 "m": 8,
395 "relerr": 1.0835117743829266e-15
396 },
397 {
398 "L": 31,
399 "K": 17,
400 "M": 64,
401 "m": 16,
402 "relerr": 2.890384933102035e-15
403 },
404 {
405 "L": 31,
406 "K": 17,
407 "M": 64,
408 "m": 32,
409 "relerr": 5.1430270130421285e-15
410 },
411 {
412 "L": 31,
413 "K": 17,
414 "M": 64,
415 "m": 64,
416 "relerr": 4.3491418988176765e-15
417 },
418 {
419 "L": 64,
420 "K": 33,
421 "M": 128,
422 "m": 1,
423 "relerr": 1.1516294793788175e-14
424 },
425 {
426 "L": 64,
427 "K": 33,
428 "M": 128,
429 "m": 2,
430 "relerr": 5.003966440305403e-15
431 },
432 {
433 "L": 64,
434 "K": 33,
435 "M": 128,
436 "m": 4,
437 "relerr": 2.83516825091437e-15
438 },
439 {
440 "L": 64,
441 "K": 33,
442 "M": 128,
443 "m": 8,
444 "relerr": 1.7702307234164651e-15
445 },
446 {
447 "L": 64,
448 "K": 33,
449 "M": 128,
450 "m": 16,
451 "relerr": 3.5245421067708554e-15
452 },
453 {
454 "L": 64,
455 "K": 33,
456 "M": 128,
457 "m": 32,
458 "relerr": 6.722182969215382e-15
459 },
460 {
461 "L": 64,
462 "K": 33,
463 "M": 128,
464 "m": 64,
465 "relerr": 8.99704601401469e-15
466 },
467 {
468 "L": 127,
469 "K": 65,
470 "M": 256,
471 "m": 1,
472 "relerr": 2.5559655649202563e-14
473 },
474 {
475 "L": 127,
476 "K": 65,
477 "M": 256,
478 "m": 2,
479 "relerr": 1.2898686056282705e-14
480 },
481 {
482 "L": 127,
483 "K": 65,
484 "M": 256,
485 "m": 4,
486 "relerr": 6.255702928901436e-15
487 },
488 {
489 "L": 127,
490 "K": 65,
491 "M": 256,
492 "m": 8,
493 "relerr": 3.3429444361411688e-15
494 },
495 {
496 "L": 127,
497 "K": 65,
498 "M": 256,
499 "m": 16,
500 "relerr": 2.9495181261656574e-15
501 },
502 {
503 "L": 127,
504 "K": 65,
505 "M": 256,
506 "m": 32,
507 "relerr": 6.826003273982211e-15
508 },
509 {
510 "L": 127,
511 "K": 65,
512 "M": 256,
513 "m": 64,
514 "relerr": 1.4651014345358924e-14
515 }
516 ],
517 "storage": [
518 {
519 "L": 4096,
520 "M": 8192,
521 "m": 16,
522 "explicit_elems": 8192,
523 "implicit_tile_elems": 4096,
524 "ratio": 2.0
525 },
526 {
527 "L": 4096,
528 "M": 8192,
529 "m": 32,
530 "explicit_elems": 8192,
531 "implicit_tile_elems": 4096,
532 "ratio": 2.0
533 },
534 {
535 "L": 4096,
536 "M": 8192,
537 "m": 64,
538 "explicit_elems": 8192,
539 "implicit_tile_elems": 4096,
540 "ratio": 2.0
541 },
542 {
543 "L": 4096,
544 "M": 8192,
545 "m": 128,
546 "explicit_elems": 8192,
547 "implicit_tile_elems": 4096,
548 "ratio": 2.0
549 },
550 {
551 "L": 4096,
552 "M": 8192,
553 "m": 256,
554 "explicit_elems": 8192,
555 "implicit_tile_elems": 4096,
556 "ratio": 2.0
557 },
558 {
559 "L": 4096,
560 "M": 8192,
561 "m": 512,
562 "explicit_elems": 8192,
563 "implicit_tile_elems": 4096,
564 "ratio": 2.0
565 },
566 {
567 "L": 4096,
568 "M": 16384,
569 "m": 16,
570 "explicit_elems": 16384,
571 "implicit_tile_elems": 4096,
572 "ratio": 4.0
573 },
574 {
575 "L": 4096,
576 "M": 16384,
577 "m": 32,
578 "explicit_elems": 16384,
579 "implicit_tile_elems": 4096,
580 "ratio": 4.0
581 },
582 {
583 "L": 4096,
584 "M": 16384,
585 "m": 64,
586 "explicit_elems": 16384,
587 "implicit_tile_elems": 4096,
588 "ratio": 4.0
589 },
590 {
591 "L": 4096,
592 "M": 16384,
593 "m": 128,
594 "explicit_elems": 16384,
595 "implicit_tile_elems": 4096,
596 "ratio": 4.0
597 },
598 {
599 "L": 4096,
600 "M": 16384,
601 "m": 256,
602 "explicit_elems": 16384,
603 "implicit_tile_elems": 4096,
604 "ratio": 4.0
605 },
606 {
607 "L": 4096,
608 "M": 16384,
609 "m": 512,
610 "explicit_elems": 16384,
611 "implicit_tile_elems": 4096,
612 "ratio": 4.0
613 },
614 {
615 "L": 16384,
616 "M": 32768,
617 "m": 16,
618 "explicit_elems": 32768,
619 "implicit_tile_elems": 16384,
620 "ratio": 2.0
621 },
622 {
623 "L": 16384,
624 "M": 32768,
625 "m": 32,
626 "explicit_elems": 32768,
627 "implicit_tile_elems": 16384,
628 "ratio": 2.0
629 },
630 {
631 "L": 16384,
632 "M": 32768,
633 "m": 64,
634 "explicit_elems": 32768,
635 "implicit_tile_elems": 16384,
636 "ratio": 2.0
637 },
638 {
639 "L": 16384,
640 "M": 32768,
641 "m": 128,
642 "explicit_elems": 32768,
643 "implicit_tile_elems": 16384,
644 "ratio": 2.0
645 },
646 {
647 "L": 16384,
648 "M": 32768,
649 "m": 256,
650 "explicit_elems": 32768,
651 "implicit_tile_elems": 16384,
652 "ratio": 2.0
653 },
654 {
655 "L": 16384,
656 "M": 32768,
657 "m": 512,
658 "explicit_elems": 32768,
659 "implicit_tile_elems": 16384,
660 "ratio": 2.0
661 },
662 {
663 "L": 16384,
664 "M": 65536,
665 "m": 16,
666 "explicit_elems": 65536,
667 "implicit_tile_elems": 16384,
668 "ratio": 4.0
669 },
670 {
671 "L": 16384,
672 "M": 65536,
673 "m": 32,
674 "explicit_elems": 65536,
675 "implicit_tile_elems": 16384,
676 "ratio": 4.0
677 },
678 {
679 "L": 16384,
680 "M": 65536,
681 "m": 64,
682 "explicit_elems": 65536,
683 "implicit_tile_elems": 16384,
684 "ratio": 4.0
685 },
686 {
687 "L": 16384,
688 "M": 65536,
689 "m": 128,
690 "explicit_elems": 65536,
691 "implicit_tile_elems": 16384,
692 "ratio": 4.0
693 },
694 {
695 "L": 16384,
696 "M": 65536,
697 "m": 256,
698 "explicit_elems": 65536,
699 "implicit_tile_elems": 16384,
700 "ratio": 4.0
701 },
702 {
703 "L": 16384,
704 "M": 65536,
705 "m": 512,
706 "explicit_elems": 65536,
707 "implicit_tile_elems": 16384,
708 "ratio": 4.0
709 }
710 ],
711 "timing": [
712 {
713 "L": 257,
714 "K": 65,
715 "M": 512,
716 "m": 16,
717 "explicit_sec": 0.00029012600134592503,
718 "implicit_sec": 0.0007790230010868981,
719 "speedup": 0.37242289501226444
720 },
721 {
722 "L": 1025,
723 "K": 257,
724 "M": 2048,
725 "m": 32,
726 "explicit_sec": 0.0005228410009294748,
727 "implicit_sec": 0.002539613997214474,
728 "speedup": 0.20587420037176626
729 },
730 {
731 "L": 2049,
732 "K": 513,
733 "M": 4096,
734 "m": 64,
735 "explicit_sec": 0.0007443119975505397,
736 "implicit_sec": 0.005844072991749272,
737 "speedup": 0.1273618585191129
738 }
739 ]
740}