|
1 |
+{ |
|
2 |
+ "source": "experiments/results/raw/bench_primitives.jsonl", |
|
3 |
+ "rows": [ |
|
4 |
+ { |
|
5 |
+ "kernel": "garch_nll_P1", |
|
6 |
+ "S": 1, |
|
7 |
+ "n": 390, |
|
8 |
+ "elements": 390, |
|
9 |
+ "backend": "cpu", |
|
10 |
+ "threads": 1, |
|
11 |
+ "median_s": 1.7909333109855652e-06, |
|
12 |
+ "ci_lo": 1.7499551177024841e-06, |
|
13 |
+ "ci_hi": 1.8328428268432617e-06, |
|
14 |
+ "device_s": 0.0, |
|
15 |
+ "elements_per_s": 217763552.44929796, |
|
16 |
+ "reps": 5, |
|
17 |
+ "precision": "fp64", |
|
18 |
+ "peak_rss_mb": 3255.451648 |
|
19 |
+ }, |
|
20 |
+ { |
|
21 |
+ "kernel": "garch_nll_P1", |
|
22 |
+ "S": 1, |
|
23 |
+ "n": 390, |
|
24 |
+ "elements": 390, |
|
25 |
+ "backend": "cpu", |
|
26 |
+ "threads": 18, |
|
27 |
+ "median_s": 1.7499551177024841e-06, |
|
28 |
+ "ci_lo": 1.6670674085617065e-06, |
|
29 |
+ "ci_hi": 1.8333084881305695e-06, |
|
30 |
+ "device_s": 0.0, |
|
31 |
+ "elements_per_s": 222862858.62692922, |
|
32 |
+ "reps": 5, |
|
33 |
+ "precision": "fp64", |
|
34 |
+ "peak_rss_mb": 3368.943616 |
|
35 |
+ }, |
|
36 |
+ { |
|
37 |
+ "kernel": "garch_nll_P1", |
|
38 |
+ "S": 1, |
|
39 |
+ "n": 390, |
|
40 |
+ "elements": 390, |
|
41 |
+ "backend": "metal", |
|
42 |
+ "threads": 0, |
|
43 |
+ "median_s": 0.0009180000051856041, |
|
44 |
+ "ci_lo": 0.00044724997133016586, |
|
45 |
+ "ci_hi": 0.0009358339011669159, |
|
46 |
+ "device_s": 0.00032679166179150343, |
|
47 |
+ "elements_per_s": 424836.59890736995, |
|
48 |
+ "reps": 5, |
|
49 |
+ "precision": "fp32", |
|
50 |
+ "peak_rss_mb": 2962.440192 |
|
51 |
+ }, |
|
52 |
+ { |
|
53 |
+ "kernel": "garch_nll_P1", |
|
54 |
+ "S": 1, |
|
55 |
+ "n": 3900, |
|
56 |
+ "elements": 3900, |
|
57 |
+ "backend": "cpu", |
|
58 |
+ "threads": 1, |
|
59 |
+ "median_s": 1.6250181943178177e-05, |
|
60 |
+ "ci_lo": 1.6207806766033173e-05, |
|
61 |
+ "ci_hi": 1.637497916817665e-05, |
|
62 |
+ "device_s": 0.0, |
|
63 |
+ "elements_per_s": 239997312.86930108, |
|
64 |
+ "reps": 5, |
|
65 |
+ "precision": "fp64", |
|
66 |
+ "peak_rss_mb": 2962.440192 |
|
67 |
+ }, |
|
68 |
+ { |
|
69 |
+ "kernel": "garch_nll_P1", |
|
70 |
+ "S": 1, |
|
71 |
+ "n": 3900, |
|
72 |
+ "elements": 3900, |
|
73 |
+ "backend": "cpu", |
|
74 |
+ "threads": 18, |
|
75 |
+ "median_s": 1.695798709988594e-05, |
|
76 |
+ "ci_lo": 1.691700890660286e-05, |
|
77 |
+ "ci_hi": 1.9416213035583496e-05, |
|
78 |
+ "device_s": 0.0, |
|
79 |
+ "elements_per_s": 229980125.41395503, |
|
80 |
+ "reps": 5, |
|
81 |
+ "precision": "fp64", |
|
82 |
+ "peak_rss_mb": 3431.858176 |
|
83 |
+ }, |
|
84 |
+ { |
|
85 |
+ "kernel": "garch_nll_P1", |
|
86 |
+ "S": 1, |
|
87 |
+ "n": 3900, |
|
88 |
+ "elements": 3900, |
|
89 |
+ "backend": "metal", |
|
90 |
+ "threads": 0, |
|
91 |
+ "median_s": 0.001348957885056734, |
|
92 |
+ "ci_lo": 0.0010095001198351383, |
|
93 |
+ "ci_hi": 0.0015331669710576534, |
|
94 |
+ "device_s": 0.0011987084290012717, |
|
95 |
+ "elements_per_s": 2891120.6518771155, |
|
96 |
+ "reps": 5, |
|
97 |
+ "precision": "fp32", |
|
98 |
+ "peak_rss_mb": 2962.440192 |
|
99 |
+ }, |
|
100 |
+ { |
|
101 |
+ "kernel": "garch_nll_P1", |
|
102 |
+ "S": 10, |
|
103 |
+ "n": 390, |
|
104 |
+ "elements": 3900, |
|
105 |
+ "backend": "cpu", |
|
106 |
+ "threads": 1, |
|
107 |
+ "median_s": 2.1916814148426056e-05, |
|
108 |
+ "ci_lo": 2.1541956812143326e-05, |
|
109 |
+ "ci_hi": 7.208297029137611e-05, |
|
110 |
+ "device_s": 0.0, |
|
111 |
+ "elements_per_s": 177945570.62847915, |
|
112 |
+ "reps": 5, |
|
113 |
+ "precision": "fp64", |
|
114 |
+ "peak_rss_mb": 2962.440192 |
|
115 |
+ }, |
|
116 |
+ { |
|
117 |
+ "kernel": "garch_nll_P1", |
|
118 |
+ "S": 10, |
|
119 |
+ "n": 390, |
|
120 |
+ "elements": 3900, |
|
121 |
+ "backend": "cpu", |
|
122 |
+ "threads": 18, |
|
123 |
+ "median_s": 2.929195761680603e-05, |
|
124 |
+ "ci_lo": 1.7000362277030945e-05, |
|
125 |
+ "ci_hi": 4.200031980872154e-05, |
|
126 |
+ "device_s": 0.0, |
|
127 |
+ "elements_per_s": 133142347.50095384, |
|
128 |
+ "reps": 5, |
|
129 |
+ "precision": "fp64", |
|
130 |
+ "peak_rss_mb": 2962.440192 |
|
131 |
+ }, |
|
132 |
+ { |
|
133 |
+ "kernel": "garch_nll_P1", |
|
134 |
+ "S": 10, |
|
135 |
+ "n": 390, |
|
136 |
+ "elements": 3900, |
|
137 |
+ "backend": "metal", |
|
138 |
+ "threads": 0, |
|
139 |
+ "median_s": 0.0003432091325521469, |
|
140 |
+ "ci_lo": 0.0003193751908838749, |
|
141 |
+ "ci_hi": 0.0009956671856343746, |
|
142 |
+ "device_s": 0.00019762502051889896, |
|
143 |
+ "elements_per_s": 11363333.98531415, |
|
144 |
+ "reps": 5, |
|
145 |
+ "precision": "fp32", |
|
146 |
+ "peak_rss_mb": 2920.169472 |
|
147 |
+ }, |
|
148 |
+ { |
|
149 |
+ "kernel": "garch_nll_P1", |
|
150 |
+ "S": 10, |
|
151 |
+ "n": 3900, |
|
152 |
+ "elements": 39000, |
|
153 |
+ "backend": "cpu", |
|
154 |
+ "threads": 1, |
|
155 |
+ "median_s": 0.0002155420370399952, |
|
156 |
+ "ci_lo": 0.00016279099509119987, |
|
157 |
+ "ci_hi": 0.00037720799446105957, |
|
158 |
+ "device_s": 0.0, |
|
159 |
+ "elements_per_s": 180939182.60948467, |
|
160 |
+ "reps": 5, |
|
161 |
+ "precision": "fp64", |
|
162 |
+ "peak_rss_mb": 576.782336 |
|
163 |
+ }, |
|
164 |
+ { |
|
165 |
+ "kernel": "garch_nll_P1", |
|
166 |
+ "S": 10, |
|
167 |
+ "n": 3900, |
|
168 |
+ "elements": 39000, |
|
169 |
+ "backend": "cpu", |
|
170 |
+ "threads": 18, |
|
171 |
+ "median_s": 6.916606798768044e-05, |
|
172 |
+ "ci_lo": 6.245775148272514e-05, |
|
173 |
+ "ci_hi": 7.533328607678413e-05, |
|
174 |
+ "device_s": 0.0, |
|
175 |
+ "elements_per_s": 563860302.2358668, |
|
176 |
+ "reps": 5, |
|
177 |
+ "precision": "fp64", |
|
178 |
+ "peak_rss_mb": 781.43488 |
|
179 |
+ }, |
|
180 |
+ { |
|
181 |
+ "kernel": "garch_nll_P1", |
|
182 |
+ "S": 10, |
|
183 |
+ "n": 3900, |
|
184 |
+ "elements": 39000, |
|
185 |
+ "backend": "metal", |
|
186 |
+ "threads": 0, |
|
187 |
+ "median_s": 0.0014300826005637646, |
|
188 |
+ "ci_lo": 0.0012115412391722202, |
|
189 |
+ "ci_hi": 0.0016847080551087856, |
|
190 |
+ "device_s": 0.0010766249615699053, |
|
191 |
+ "elements_per_s": 27271152.019208886, |
|
192 |
+ "reps": 5, |
|
193 |
+ "precision": "fp32", |
|
194 |
+ "peak_rss_mb": 3360.11264 |
|
195 |
+ }, |
|
196 |
+ { |
|
197 |
+ "kernel": "garch_nll_P1", |
|
198 |
+ "S": 100, |
|
199 |
+ "n": 390, |
|
200 |
+ "elements": 39000, |
|
201 |
+ "backend": "cpu", |
|
202 |
+ "threads": 1, |
|
203 |
+ "median_s": 0.0001916671171784401, |
|
204 |
+ "ci_lo": 0.0001916252076625824, |
|
205 |
+ "ci_hi": 0.0002199173904955387, |
|
206 |
+ "device_s": 0.0, |
|
207 |
+ "elements_per_s": 203477782.59580857, |
|
208 |
+ "reps": 5, |
|
209 |
+ "precision": "fp64", |
|
210 |
+ "peak_rss_mb": 3431.87456 |
|
211 |
+ }, |
|
212 |
+ { |
|
213 |
+ "kernel": "garch_nll_P1", |
|
214 |
+ "S": 100, |
|
215 |
+ "n": 390, |
|
216 |
+ "elements": 39000, |
|
217 |
+ "backend": "cpu", |
|
218 |
+ "threads": 18, |
|
219 |
+ "median_s": 0.00016116676852107048, |
|
220 |
+ "ci_lo": 0.00015066703781485558, |
|
221 |
+ "ci_hi": 0.00017320923507213593, |
|
222 |
+ "device_s": 0.0, |
|
223 |
+ "elements_per_s": 241985369.30335766, |
|
224 |
+ "reps": 5, |
|
225 |
+ "precision": "fp64", |
|
226 |
+ "peak_rss_mb": 3359.932416 |
|
227 |
+ }, |
|
228 |
+ { |
|
229 |
+ "kernel": "garch_nll_P1", |
|
230 |
+ "S": 100, |
|
231 |
+ "n": 390, |
|
232 |
+ "elements": 39000, |
|
233 |
+ "backend": "metal", |
|
234 |
+ "threads": 0, |
|
235 |
+ "median_s": 0.0006238752976059914, |
|
236 |
+ "ci_lo": 0.0006115422584116459, |
|
237 |
+ "ci_hi": 0.0006384579464793205, |
|
238 |
+ "device_s": 0.0004310833755880594, |
|
239 |
+ "elements_per_s": 62512492.720348835, |
|
240 |
+ "reps": 5, |
|
241 |
+ "precision": "fp32", |
|
242 |
+ "peak_rss_mb": 3355.901952 |
|
243 |
+ }, |
|
244 |
+ { |
|
245 |
+ "kernel": "garch_nll_P1", |
|
246 |
+ "S": 100, |
|
247 |
+ "n": 3900, |
|
248 |
+ "elements": 390000, |
|
249 |
+ "backend": "cpu", |
|
250 |
+ "threads": 1, |
|
251 |
+ "median_s": 0.0016154590994119644, |
|
252 |
+ "ci_lo": 0.0016071251593530178, |
|
253 |
+ "ci_hi": 0.0016200002282857895, |
|
254 |
+ "device_s": 0.0, |
|
255 |
+ "elements_per_s": 241417439.87326083, |
|
256 |
+ "reps": 5, |
|
257 |
+ "precision": "fp64", |
|
258 |
+ "peak_rss_mb": 3222.339584 |
|
259 |
+ }, |
|
260 |
+ { |
|
261 |
+ "kernel": "garch_nll_P1", |
|
262 |
+ "S": 100, |
|
263 |
+ "n": 3900, |
|
264 |
+ "elements": 390000, |
|
265 |
+ "backend": "cpu", |
|
266 |
+ "threads": 18, |
|
267 |
+ "median_s": 0.00020695803686976433, |
|
268 |
+ "ci_lo": 0.00020262505859136581, |
|
269 |
+ "ci_hi": 0.0002222089096903801, |
|
270 |
+ "device_s": 0.0, |
|
271 |
+ "elements_per_s": 1884439985.5098226, |
|
272 |
+ "reps": 5, |
|
273 |
+ "precision": "fp64", |
|
274 |
+ "peak_rss_mb": 2962.440192 |
|
275 |
+ }, |
|
276 |
+ { |
|
277 |
+ "kernel": "garch_nll_P1", |
|
278 |
+ "S": 100, |
|
279 |
+ "n": 3900, |
|
280 |
+ "elements": 390000, |
|
281 |
+ "backend": "metal", |
|
282 |
+ "threads": 0, |
|
283 |
+ "median_s": 0.0016493331640958786, |
|
284 |
+ "ci_lo": 0.0015722080133855343, |
|
285 |
+ "ci_hi": 0.004429208114743233, |
|
286 |
+ "device_s": 0.0009533748961985111, |
|
287 |
+ "elements_per_s": 236459199.68740082, |
|
288 |
+ "reps": 5, |
|
289 |
+ "precision": "fp32", |
|
290 |
+ "peak_rss_mb": 2962.440192 |
|
291 |
+ }, |
|
292 |
+ { |
|
293 |
+ "kernel": "garch_nll_P1", |
|
294 |
+ "S": 1000, |
|
295 |
+ "n": 390, |
|
296 |
+ "elements": 390000, |
|
297 |
+ "backend": "cpu", |
|
298 |
+ "threads": 1, |
|
299 |
+ "median_s": 0.0016390001401305199, |
|
300 |
+ "ci_lo": 0.001627500168979168, |
|
301 |
+ "ci_hi": 0.0016581248492002487, |
|
302 |
+ "device_s": 0.0, |
|
303 |
+ "elements_per_s": 237949949.14945084, |
|
304 |
+ "reps": 5, |
|
305 |
+ "precision": "fp64", |
|
306 |
+ "peak_rss_mb": 3359.932416 |
|
307 |
+ }, |
|
308 |
+ { |
|
309 |
+ "kernel": "garch_nll_P1", |
|
310 |
+ "S": 1000, |
|
311 |
+ "n": 390, |
|
312 |
+ "elements": 390000, |
|
313 |
+ "backend": "cpu", |
|
314 |
+ "threads": 18, |
|
315 |
+ "median_s": 0.0002765827812254429, |
|
316 |
+ "ci_lo": 0.00027295900508761406, |
|
317 |
+ "ci_hi": 0.00033191684633493423, |
|
318 |
+ "device_s": 0.0, |
|
319 |
+ "elements_per_s": 1410066086.8042636, |
|
320 |
+ "reps": 5, |
|
321 |
+ "precision": "fp64", |
|
322 |
+ "peak_rss_mb": 2962.440192 |
|
323 |
+ }, |
|
324 |
+ { |
|
325 |
+ "kernel": "garch_nll_P1", |
|
326 |
+ "S": 1000, |
|
327 |
+ "n": 390, |
|
328 |
+ "elements": 390000, |
|
329 |
+ "backend": "metal", |
|
330 |
+ "threads": 0, |
|
331 |
+ "median_s": 0.0011531668715178967, |
|
332 |
+ "ci_lo": 0.0010962923988699913, |
|
333 |
+ "ci_hi": 0.0011774590238928795, |
|
334 |
+ "device_s": 0.00017799995839595795, |
|
335 |
+ "elements_per_s": 338199101.65009224, |
|
336 |
+ "reps": 5, |
|
337 |
+ "precision": "fp32", |
|
338 |
+ "peak_rss_mb": 3222.339584 |
|
339 |
+ }, |
|
340 |
+ { |
|
341 |
+ "kernel": "garch_nll_P1", |
|
342 |
+ "S": 1000, |
|
343 |
+ "n": 3900, |
|
344 |
+ "elements": 3900000, |
|
345 |
+ "backend": "cpu", |
|
346 |
+ "threads": 1, |
|
347 |
+ "median_s": 0.018310166895389557, |
|
348 |
+ "ci_lo": 0.01771716633811593, |
|
349 |
+ "ci_hi": 0.019527375232428312, |
|
350 |
+ "device_s": 0.0, |
|
351 |
+ "elements_per_s": 212996420.09172553, |
|
352 |
+ "reps": 5, |
|
353 |
+ "precision": "fp64", |
|
354 |
+ "peak_rss_mb": 572.112896 |
|
355 |
+ }, |
|
356 |
+ { |
|
357 |
+ "kernel": "garch_nll_P1", |
|
358 |
+ "S": 1000, |
|
359 |
+ "n": 3900, |
|
360 |
+ "elements": 3900000, |
|
361 |
+ "backend": "cpu", |
|
362 |
+ "threads": 18, |
|
363 |
+ "median_s": 0.0014978330582380295, |
|
364 |
+ "ci_lo": 0.001383374910801649, |
|
365 |
+ "ci_hi": 0.0015932917594909668, |
|
366 |
+ "device_s": 0.0, |
|
367 |
+ "elements_per_s": 2603761466.306366, |
|
368 |
+ "reps": 5, |
|
369 |
+ "precision": "fp64", |
|
370 |
+ "peak_rss_mb": 3432.742912 |
|
371 |
+ }, |
|
372 |
+ { |
|
373 |
+ "kernel": "garch_nll_P1", |
|
374 |
+ "S": 1000, |
|
375 |
+ "n": 3900, |
|
376 |
+ "elements": 3900000, |
|
377 |
+ "backend": "metal", |
|
378 |
+ "threads": 0, |
|
379 |
+ "median_s": 0.0072068748995661736, |
|
380 |
+ "ci_lo": 0.007158916909247637, |
|
381 |
+ "ci_hi": 0.009398084133863449, |
|
382 |
+ "device_s": 0.0010924999369308352, |
|
383 |
+ "elements_per_s": 541149951.171591, |
|
384 |
+ "reps": 5, |
|
385 |
+ "precision": "fp32", |
|
386 |
+ "peak_rss_mb": 3360.11264 |
|
387 |
+ }, |
|
388 |
+ { |
|
389 |
+ "kernel": "garch_nll_P1", |
|
390 |
+ "S": 10000, |
|
391 |
+ "n": 390, |
|
392 |
+ "elements": 3900000, |
|
393 |
+ "backend": "cpu", |
|
394 |
+ "threads": 1, |
|
395 |
+ "median_s": 0.017741417046636343, |
|
396 |
+ "ci_lo": 0.01734916679561138, |
|
397 |
+ "ci_hi": 0.017816499806940556, |
|
398 |
+ "device_s": 0.0, |
|
399 |
+ "elements_per_s": 219824605.3146817, |
|
400 |
+ "reps": 5, |
|
401 |
+ "precision": "fp64", |
|
402 |
+ "peak_rss_mb": 3355.901952 |
|
403 |
+ }, |
|
404 |
+ { |
|
405 |
+ "kernel": "garch_nll_P1", |
|
406 |
+ "S": 10000, |
|
407 |
+ "n": 390, |
|
408 |
+ "elements": 3900000, |
|
409 |
+ "backend": "cpu", |
|
410 |
+ "threads": 18, |
|
411 |
+ "median_s": 0.0022433330304920673, |
|
412 |
+ "ci_lo": 0.002103041857481003, |
|
413 |
+ "ci_hi": 0.002292540855705738, |
|
414 |
+ "device_s": 0.0, |
|
415 |
+ "elements_per_s": 1738484632.905596, |
|
416 |
+ "reps": 5, |
|
417 |
+ "precision": "fp64", |
|
418 |
+ "peak_rss_mb": 2962.440192 |
|
419 |
+ }, |
|
420 |
+ { |
|
421 |
+ "kernel": "garch_nll_P1", |
|
422 |
+ "S": 10000, |
|
423 |
+ "n": 390, |
|
424 |
+ "elements": 3900000, |
|
425 |
+ "backend": "metal", |
|
426 |
+ "threads": 0, |
|
427 |
+ "median_s": 0.00675466563552618, |
|
428 |
+ "ci_lo": 0.006540417205542326, |
|
429 |
+ "ci_hi": 0.007071124855428934, |
|
430 |
+ "device_s": 0.00046787504106760025, |
|
431 |
+ "elements_per_s": 577378690.5880197, |
|
432 |
+ "reps": 5, |
|
433 |
+ "precision": "fp32", |
|
434 |
+ "peak_rss_mb": 2962.440192 |
|
435 |
+ }, |
|
436 |
+ { |
|
437 |
+ "kernel": "garch_nll_P1", |
|
438 |
+ "S": 10000, |
|
439 |
+ "n": 3900, |
|
440 |
+ "elements": 39000000, |
|
441 |
+ "backend": "cpu", |
|
442 |
+ "threads": 1, |
|
443 |
+ "median_s": 0.16226391727104783, |
|
444 |
+ "ci_lo": 0.16133012529462576, |
|
445 |
+ "ci_hi": 0.16484179068356752, |
|
446 |
+ "device_s": 0.0, |
|
447 |
+ "elements_per_s": 240349183.3298581, |
|
448 |
+ "reps": 5, |
|
449 |
+ "precision": "fp64", |
|
450 |
+ "peak_rss_mb": 3255.451648 |
|
451 |
+ }, |
|
452 |
+ { |
|
453 |
+ "kernel": "garch_nll_P1", |
|
454 |
+ "S": 10000, |
|
455 |
+ "n": 3900, |
|
456 |
+ "elements": 39000000, |
|
457 |
+ "backend": "cpu", |
|
458 |
+ "threads": 18, |
|
459 |
+ "median_s": 0.01383341709151864, |
|
460 |
+ "ci_lo": 0.012941500172019005, |
|
461 |
+ "ci_hi": 0.014138792175799608, |
|
462 |
+ "device_s": 0.0, |
|
463 |
+ "elements_per_s": 2819260038.3538756, |
|
464 |
+ "reps": 5, |
|
465 |
+ "precision": "fp64", |
|
466 |
+ "peak_rss_mb": 3254.272 |
|
467 |
+ }, |
|
468 |
+ { |
|
469 |
+ "kernel": "garch_nll_P1", |
|
470 |
+ "S": 10000, |
|
471 |
+ "n": 3900, |
|
472 |
+ "elements": 39000000, |
|
473 |
+ "backend": "metal", |
|
474 |
+ "threads": 0, |
|
475 |
+ "median_s": 0.06106641702353954, |
|
476 |
+ "ci_lo": 0.05950908316299319, |
|
477 |
+ "ci_hi": 0.0616582497023046, |
|
478 |
+ "device_s": 0.004054000019095838, |
|
479 |
+ "elements_per_s": 638648899.0334327, |
|
480 |
+ "reps": 5, |
|
481 |
+ "precision": "fp32", |
|
482 |
+ "peak_rss_mb": 3355.901952 |
|
483 |
+ }, |
|
484 |
+ { |
|
485 |
+ "kernel": "garch_nll_P64", |
|
486 |
+ "S": 1, |
|
487 |
+ "n": 390, |
|
488 |
+ "elements": 390, |
|
489 |
+ "backend": "cpu", |
|
490 |
+ "threads": 1, |
|
491 |
+ "median_s": 8.287513628602028e-05, |
|
492 |
+ "ci_lo": 8.27503390610218e-05, |
|
493 |
+ "ci_hi": 8.458364754915237e-05, |
|
494 |
+ "device_s": 0.0, |
|
495 |
+ "elements_per_s": 4705874.614239238, |
|
496 |
+ "reps": 5, |
|
497 |
+ "precision": "fp64", |
|
498 |
+ "peak_rss_mb": 577.159168 |
|
499 |
+ }, |
|
500 |
+ { |
|
501 |
+ "kernel": "garch_nll_P64", |
|
502 |
+ "S": 1, |
|
503 |
+ "n": 390, |
|
504 |
+ "elements": 390, |
|
505 |
+ "backend": "cpu", |
|
506 |
+ "threads": 18, |
|
507 |
+ "median_s": 0.00017224997282028198, |
|
508 |
+ "ci_lo": 0.00012754183262586594, |
|
509 |
+ "ci_hi": 0.0002139592543244362, |
|
510 |
+ "device_s": 0.0, |
|
511 |
+ "elements_per_s": 2264151.3006617934, |
|
512 |
+ "reps": 5, |
|
513 |
+ "precision": "fp64", |
|
514 |
+ "peak_rss_mb": 3431.514112 |
|
515 |
+ }, |
|
516 |
+ { |
|
517 |
+ "kernel": "garch_nll_P64", |
|
518 |
+ "S": 1, |
|
519 |
+ "n": 390, |
|
520 |
+ "elements": 390, |
|
521 |
+ "backend": "metal", |
|
522 |
+ "threads": 0, |
|
523 |
+ "median_s": 0.0005012080073356628, |
|
524 |
+ "ci_lo": 0.00047737499698996544, |
|
525 |
+ "ci_hi": 0.0006123748607933521, |
|
526 |
+ "device_s": 0.0003255000337958336, |
|
527 |
+ "elements_per_s": 778120.0505418383, |
|
528 |
+ "reps": 5, |
|
529 |
+ "precision": "fp32", |
|
530 |
+ "peak_rss_mb": 3431.46496 |
|
531 |
+ }, |
|
532 |
+ { |
|
533 |
+ "kernel": "garch_nll_P64", |
|
534 |
+ "S": 1, |
|
535 |
+ "n": 3900, |
|
536 |
+ "elements": 3900, |
|
537 |
+ "backend": "cpu", |
|
538 |
+ "threads": 1, |
|
539 |
+ "median_s": 0.0008078329265117645, |
|
540 |
+ "ci_lo": 0.0008031250908970833, |
|
541 |
+ "ci_hi": 0.0008203750476241112, |
|
542 |
+ "device_s": 0.0, |
|
543 |
+ "elements_per_s": 4827730.923076213, |
|
544 |
+ "reps": 5, |
|
545 |
+ "precision": "fp64", |
|
546 |
+ "peak_rss_mb": 3431.87456 |
|
547 |
+ }, |
|
548 |
+ { |
|
549 |
+ "kernel": "garch_nll_P64", |
|
550 |
+ "S": 1, |
|
551 |
+ "n": 3900, |
|
552 |
+ "elements": 3900, |
|
553 |
+ "backend": "cpu", |
|
554 |
+ "threads": 18, |
|
555 |
+ "median_s": 0.00014187488704919815, |
|
556 |
+ "ci_lo": 0.000135000329464674, |
|
557 |
+ "ci_hi": 0.00021779071539640427, |
|
558 |
+ "device_s": 0.0, |
|
559 |
+ "elements_per_s": 27489008.668937948, |
|
560 |
+ "reps": 5, |
|
561 |
+ "precision": "fp64", |
|
562 |
+ "peak_rss_mb": 3222.339584 |
|
563 |
+ }, |
|
564 |
+ { |
|
565 |
+ "kernel": "garch_nll_P64", |
|
566 |
+ "S": 1, |
|
567 |
+ "n": 3900, |
|
568 |
+ "elements": 3900, |
|
569 |
+ "backend": "metal", |
|
570 |
+ "threads": 0, |
|
571 |
+ "median_s": 0.0014235423877835274, |
|
572 |
+ "ci_lo": 0.00134983379393816, |
|
573 |
+ "ci_hi": 0.0033927499316632748, |
|
574 |
+ "device_s": 0.00122337497305125, |
|
575 |
+ "elements_per_s": 2739644.4485733556, |
|
576 |
+ "reps": 5, |
|
577 |
+ "precision": "fp32", |
|
578 |
+ "peak_rss_mb": 3431.87456 |
|
579 |
+ }, |
|
580 |
+ { |
|
581 |
+ "kernel": "garch_nll_P64", |
|
582 |
+ "S": 10, |
|
583 |
+ "n": 390, |
|
584 |
+ "elements": 3900, |
|
585 |
+ "backend": "cpu", |
|
586 |
+ "threads": 1, |
|
587 |
+ "median_s": 0.0008257082663476467, |
|
588 |
+ "ci_lo": 0.000809917226433754, |
|
589 |
+ "ci_hi": 0.0008320827037096024, |
|
590 |
+ "device_s": 0.0, |
|
591 |
+ "elements_per_s": 4723217.8227436915, |
|
592 |
+ "reps": 5, |
|
593 |
+ "precision": "fp64", |
|
594 |
+ "peak_rss_mb": 3432.742912 |
|
595 |
+ }, |
|
596 |
+ { |
|
597 |
+ "kernel": "garch_nll_P64", |
|
598 |
+ "S": 10, |
|
599 |
+ "n": 390, |
|
600 |
+ "elements": 3900, |
|
601 |
+ "backend": "cpu", |
|
602 |
+ "threads": 18, |
|
603 |
+ "median_s": 0.0002438751980662346, |
|
604 |
+ "ci_lo": 0.00013074977323412895, |
|
605 |
+ "ci_hi": 0.0002598753198981285, |
|
606 |
+ "device_s": 0.0, |
|
607 |
+ "elements_per_s": 15991786.089460358, |
|
608 |
+ "reps": 5, |
|
609 |
+ "precision": "fp64", |
|
610 |
+ "peak_rss_mb": 3368.943616 |
|
611 |
+ }, |
|
612 |
+ { |
|
613 |
+ "kernel": "garch_nll_P64", |
|
614 |
+ "S": 10, |
|
615 |
+ "n": 390, |
|
616 |
+ "elements": 3900, |
|
617 |
+ "backend": "metal", |
|
618 |
+ "threads": 0, |
|
619 |
+ "median_s": 0.0010179998353123665, |
|
620 |
+ "ci_lo": 0.0004632081836462021, |
|
621 |
+ "ci_hi": 0.0010751672089099884, |
|
622 |
+ "device_s": 0.00032300001475960016, |
|
623 |
+ "elements_per_s": 3831041.877136759, |
|
624 |
+ "reps": 5, |
|
625 |
+ "precision": "fp32", |
|
626 |
+ "peak_rss_mb": 3431.530496 |
|
627 |
+ }, |
|
628 |
+ { |
|
629 |
+ "kernel": "garch_nll_P64", |
|
630 |
+ "S": 10, |
|
631 |
+ "n": 3900, |
|
632 |
+ "elements": 39000, |
|
633 |
+ "backend": "cpu", |
|
634 |
+ "threads": 1, |
|
635 |
+ "median_s": 0.008083874825388193, |
|
636 |
+ "ci_lo": 0.008056249935179949, |
|
637 |
+ "ci_hi": 0.00812424998730421, |
|
638 |
+ "device_s": 0.0, |
|
639 |
+ "elements_per_s": 4824419.086440666, |
|
640 |
+ "reps": 5, |
|
641 |
+ "precision": "fp64", |
|
642 |
+ "peak_rss_mb": 3355.901952 |
|
643 |
+ }, |
|
644 |
+ { |
|
645 |
+ "kernel": "garch_nll_P64", |
|
646 |
+ "S": 10, |
|
647 |
+ "n": 3900, |
|
648 |
+ "elements": 39000, |
|
649 |
+ "backend": "cpu", |
|
650 |
+ "threads": 18, |
|
651 |
+ "median_s": 0.000775500200688839, |
|
652 |
+ "ci_lo": 0.0006874999962747097, |
|
653 |
+ "ci_hi": 0.0008766250684857368, |
|
654 |
+ "device_s": 0.0, |
|
655 |
+ "elements_per_s": 50290122.38211957, |
|
656 |
+ "reps": 5, |
|
657 |
+ "precision": "fp64", |
|
658 |
+ "peak_rss_mb": 3432.742912 |
|
659 |
+ }, |
|
660 |
+ { |
|
661 |
+ "kernel": "garch_nll_P64", |
|
662 |
+ "S": 10, |
|
663 |
+ "n": 3900, |
|
664 |
+ "elements": 39000, |
|
665 |
+ "backend": "metal", |
|
666 |
+ "threads": 0, |
|
667 |
+ "median_s": 0.0013822498731315136, |
|
668 |
+ "ci_lo": 0.0008970410563051701, |
|
669 |
+ "ci_hi": 0.0033571659587323666, |
|
670 |
+ "device_s": 0.0006641249638050795, |
|
671 |
+ "elements_per_s": 28214869.654243305, |
|
672 |
+ "reps": 5, |
|
673 |
+ "precision": "fp32", |
|
674 |
+ "peak_rss_mb": 3431.530496 |
|
675 |
+ }, |
|
676 |
+ { |
|
677 |
+ "kernel": "garch_nll_P64", |
|
678 |
+ "S": 100, |
|
679 |
+ "n": 390, |
|
680 |
+ "elements": 39000, |
|
681 |
+ "backend": "cpu", |
|
682 |
+ "threads": 1, |
|
683 |
+ "median_s": 0.008346542250365019, |
|
684 |
+ "ci_lo": 0.008285791147500277, |
|
685 |
+ "ci_hi": 0.008543540723621845, |
|
686 |
+ "device_s": 0.0, |
|
687 |
+ "elements_per_s": 4672593.611839012, |
|
688 |
+ "reps": 5, |
|
689 |
+ "precision": "fp64", |
|
690 |
+ "peak_rss_mb": 3431.514112 |
|
691 |
+ }, |
|
692 |
+ { |
|
693 |
+ "kernel": "garch_nll_P64", |
|
694 |
+ "S": 100, |
|
695 |
+ "n": 390, |
|
696 |
+ "elements": 39000, |
|
697 |
+ "backend": "cpu", |
|
698 |
+ "threads": 18, |
|
699 |
+ "median_s": 0.001005750149488449, |
|
700 |
+ "ci_lo": 0.0009415419772267342, |
|
701 |
+ "ci_hi": 0.0010966667905449867, |
|
702 |
+ "device_s": 0.0, |
|
703 |
+ "elements_per_s": 38777026.30204572, |
|
704 |
+ "reps": 5, |
|
705 |
+ "precision": "fp64", |
|
706 |
+ "peak_rss_mb": 781.484032 |
|
707 |
+ }, |
|
708 |
+ { |
|
709 |
+ "kernel": "garch_nll_P64", |
|
710 |
+ "S": 100, |
|
711 |
+ "n": 390, |
|
712 |
+ "elements": 39000, |
|
713 |
+ "backend": "metal", |
|
714 |
+ "threads": 0, |
|
715 |
+ "median_s": 0.0005332920700311661, |
|
716 |
+ "ci_lo": 0.0005230000242590904, |
|
717 |
+ "ci_hi": 0.0005429168231785297, |
|
718 |
+ "device_s": 0.00033650000113993883, |
|
719 |
+ "elements_per_s": 73130658.02332444, |
|
720 |
+ "reps": 5, |
|
721 |
+ "precision": "fp32", |
|
722 |
+ "peak_rss_mb": 2962.440192 |
|
723 |
+ }, |
|
724 |
+ { |
|
725 |
+ "kernel": "garch_nll_P64", |
|
726 |
+ "S": 100, |
|
727 |
+ "n": 3900, |
|
728 |
+ "elements": 390000, |
|
729 |
+ "backend": "cpu", |
|
730 |
+ "threads": 1, |
|
731 |
+ "median_s": 0.0801338329911232, |
|
732 |
+ "ci_lo": 0.07999316696077585, |
|
733 |
+ "ci_hi": 0.08033083425834775, |
|
734 |
+ "device_s": 0.0, |
|
735 |
+ "elements_per_s": 4866858.172667244, |
|
736 |
+ "reps": 5, |
|
737 |
+ "precision": "fp64", |
|
738 |
+ "peak_rss_mb": 3359.932416 |
|
739 |
+ }, |
|
740 |
+ { |
|
741 |
+ "kernel": "garch_nll_P64", |
|
742 |
+ "S": 100, |
|
743 |
+ "n": 3900, |
|
744 |
+ "elements": 390000, |
|
745 |
+ "backend": "cpu", |
|
746 |
+ "threads": 18, |
|
747 |
+ "median_s": 0.006173874717205763, |
|
748 |
+ "ci_lo": 0.005890249740332365, |
|
749 |
+ "ci_hi": 0.006268457975238562, |
|
750 |
+ "device_s": 0.0, |
|
751 |
+ "elements_per_s": 63169406.22606451, |
|
752 |
+ "reps": 5, |
|
753 |
+ "precision": "fp64", |
|
754 |
+ "peak_rss_mb": 3432.742912 |
|
755 |
+ }, |
|
756 |
+ { |
|
757 |
+ "kernel": "garch_nll_P64", |
|
758 |
+ "S": 100, |
|
759 |
+ "n": 3900, |
|
760 |
+ "elements": 390000, |
|
761 |
+ "backend": "metal", |
|
762 |
+ "threads": 0, |
|
763 |
+ "median_s": 0.0021704169921576977, |
|
764 |
+ "ci_lo": 0.0018634586594998837, |
|
765 |
+ "ci_hi": 0.0022297906689345837, |
|
766 |
+ "device_s": 0.0010580417001619935, |
|
767 |
+ "elements_per_s": 179688972.86059555, |
|
768 |
+ "reps": 5, |
|
769 |
+ "precision": "fp32", |
|
770 |
+ "peak_rss_mb": 3431.858176 |
|
771 |
+ }, |
|
772 |
+ { |
|
773 |
+ "kernel": "garch_nll_P64", |
|
774 |
+ "S": 1000, |
|
775 |
+ "n": 390, |
|
776 |
+ "elements": 390000, |
|
777 |
+ "backend": "cpu", |
|
778 |
+ "threads": 1, |
|
779 |
+ "median_s": 0.09679854195564985, |
|
780 |
+ "ci_lo": 0.08949454175308347, |
|
781 |
+ "ci_hi": 0.10223195794969797, |
|
782 |
+ "device_s": 0.0, |
|
783 |
+ "elements_per_s": 4028986.306205791, |
|
784 |
+ "reps": 5, |
|
785 |
+ "precision": "fp64", |
|
786 |
+ "peak_rss_mb": 2962.440192 |
|
787 |
+ }, |
|
788 |
+ { |
|
789 |
+ "kernel": "garch_nll_P64", |
|
790 |
+ "S": 1000, |
|
791 |
+ "n": 390, |
|
792 |
+ "elements": 390000, |
|
793 |
+ "backend": "cpu", |
|
794 |
+ "threads": 18, |
|
795 |
+ "median_s": 0.00848708301782608, |
|
796 |
+ "ci_lo": 0.008417499717324972, |
|
797 |
+ "ci_hi": 0.008939292281866074, |
|
798 |
+ "device_s": 0.0, |
|
799 |
+ "elements_per_s": 45952183.94598623, |
|
800 |
+ "reps": 5, |
|
801 |
+ "precision": "fp64", |
|
802 |
+ "peak_rss_mb": 2962.440192 |
|
803 |
+ }, |
|
804 |
+ { |
|
805 |
+ "kernel": "garch_nll_P64", |
|
806 |
+ "S": 1000, |
|
807 |
+ "n": 390, |
|
808 |
+ "elements": 390000, |
|
809 |
+ "backend": "metal", |
|
810 |
+ "threads": 0, |
|
811 |
+ "median_s": 0.002336665987968445, |
|
812 |
+ "ci_lo": 0.002312499564141035, |
|
813 |
+ "ci_hi": 0.0027117920108139515, |
|
814 |
+ "device_s": 0.001452916651032865, |
|
815 |
+ "elements_per_s": 166904470.73228282, |
|
816 |
+ "reps": 5, |
|
817 |
+ "precision": "fp32", |
|
818 |
+ "peak_rss_mb": 3359.932416 |
|
819 |
+ }, |
|
820 |
+ { |
|
821 |
+ "kernel": "garch_nll_P64", |
|
822 |
+ "S": 1000, |
|
823 |
+ "n": 3900, |
|
824 |
+ "elements": 3900000, |
|
825 |
+ "backend": "cpu", |
|
826 |
+ "threads": 1, |
|
827 |
+ "median_s": 0.8561791670508683, |
|
828 |
+ "ci_lo": 0.8505779169499874, |
|
829 |
+ "ci_hi": 0.9446879159659147, |
|
830 |
+ "device_s": 0.0, |
|
831 |
+ "elements_per_s": 4555121.34619399, |
|
832 |
+ "reps": 5, |
|
833 |
+ "precision": "fp64", |
|
834 |
+ "peak_rss_mb": 2962.440192 |
|
835 |
+ }, |
|
836 |
+ { |
|
837 |
+ "kernel": "garch_nll_P64", |
|
838 |
+ "S": 1000, |
|
839 |
+ "n": 3900, |
|
840 |
+ "elements": 3900000, |
|
841 |
+ "backend": "cpu", |
|
842 |
+ "threads": 18, |
|
843 |
+ "median_s": 0.08150566695258021, |
|
844 |
+ "ci_lo": 0.0744811249896884, |
|
845 |
+ "ci_hi": 0.10778554202988744, |
|
846 |
+ "device_s": 0.0, |
|
847 |
+ "elements_per_s": 47849433.61384933, |
|
848 |
+ "reps": 5, |
|
849 |
+ "precision": "fp64", |
|
850 |
+ "peak_rss_mb": 3255.451648 |
|
851 |
+ }, |
|
852 |
+ { |
|
853 |
+ "kernel": "garch_nll_P64", |
|
854 |
+ "S": 1000, |
|
855 |
+ "n": 3900, |
|
856 |
+ "elements": 3900000, |
|
857 |
+ "backend": "metal", |
|
858 |
+ "threads": 0, |
|
859 |
+ "median_s": 0.010272707790136337, |
|
860 |
+ "ci_lo": 0.009604125283658504, |
|
861 |
+ "ci_hi": 0.010956583078950644, |
|
862 |
+ "device_s": 0.0029698750004172325, |
|
863 |
+ "elements_per_s": 379646737.7125929, |
|
864 |
+ "reps": 5, |
|
865 |
+ "precision": "fp32", |
|
866 |
+ "peak_rss_mb": 2962.440192 |
|
867 |
+ }, |
|
868 |
+ { |
|
869 |
+ "kernel": "realized_fused", |
|
870 |
+ "S": 1, |
|
871 |
+ "n": 390, |
|
872 |
+ "elements": 390, |
|
873 |
+ "backend": "cpu", |
|
874 |
+ "threads": 1, |
|
875 |
+ "median_s": 1.4998950064182281e-06, |
|
876 |
+ "ci_lo": 1.416075974702835e-06, |
|
877 |
+ "ci_hi": 4.041939973831177e-06, |
|
878 |
+ "device_s": 0.0, |
|
879 |
+ "elements_per_s": 260018200.16144055, |
|
880 |
+ "reps": 5, |
|
881 |
+ "precision": "fp64", |
|
882 |
+ "peak_rss_mb": 2962.440192 |
|
883 |
+ }, |
|
884 |
+ { |
|
885 |
+ "kernel": "realized_fused", |
|
886 |
+ "S": 1, |
|
887 |
+ "n": 390, |
|
888 |
+ "elements": 390, |
|
889 |
+ "backend": "cpu", |
|
890 |
+ "threads": 18, |
|
891 |
+ "median_s": 1.4998950064182281e-06, |
|
892 |
+ "ci_lo": 1.4579854905605316e-06, |
|
893 |
+ "ci_hi": 1.6670674085617065e-06, |
|
894 |
+ "device_s": 0.0, |
|
895 |
+ "elements_per_s": 260018200.16144055, |
|
896 |
+ "reps": 5, |
|
897 |
+ "precision": "fp64", |
|
898 |
+ "peak_rss_mb": 2962.440192 |
|
899 |
+ }, |
|
900 |
+ { |
|
901 |
+ "kernel": "realized_fused", |
|
902 |
+ "S": 1, |
|
903 |
+ "n": 390, |
|
904 |
+ "elements": 390, |
|
905 |
+ "backend": "metal", |
|
906 |
+ "threads": 0, |
|
907 |
+ "median_s": 0.0002344171516597271, |
|
908 |
+ "ci_lo": 0.00019499985501170158, |
|
909 |
+ "ci_hi": 0.00025337468832731247, |
|
910 |
+ "device_s": 3.199989441782236e-05, |
|
911 |
+ "elements_per_s": 1663700.7882687368, |
|
912 |
+ "reps": 5, |
|
913 |
+ "precision": "fp32", |
|
914 |
+ "peak_rss_mb": 3432.742912 |
|
915 |
+ }, |
|
916 |
+ { |
|
917 |
+ "kernel": "realized_fused", |
|
918 |
+ "S": 1, |
|
919 |
+ "n": 3900, |
|
920 |
+ "elements": 3900, |
|
921 |
+ "backend": "cpu", |
|
922 |
+ "threads": 1, |
|
923 |
+ "median_s": 1.1624768376350403e-05, |
|
924 |
+ "ci_lo": 1.1375173926353455e-05, |
|
925 |
+ "ci_hi": 1.2792181223630905e-05, |
|
926 |
+ "device_s": 0.0, |
|
927 |
+ "elements_per_s": 335490555.4879026, |
|
928 |
+ "reps": 5, |
|
929 |
+ "precision": "fp64", |
|
930 |
+ "peak_rss_mb": 2962.440192 |
|
931 |
+ }, |
|
932 |
+ { |
|
933 |
+ "kernel": "realized_fused", |
|
934 |
+ "S": 1, |
|
935 |
+ "n": 3900, |
|
936 |
+ "elements": 3900, |
|
937 |
+ "backend": "cpu", |
|
938 |
+ "threads": 18, |
|
939 |
+ "median_s": 1.116609200835228e-05, |
|
940 |
+ "ci_lo": 1.1124648153781891e-05, |
|
941 |
+ "ci_hi": 1.2124888598918915e-05, |
|
942 |
+ "device_s": 0.0, |
|
943 |
+ "elements_per_s": 349271705.5423496, |
|
944 |
+ "reps": 5, |
|
945 |
+ "precision": "fp64", |
|
946 |
+ "peak_rss_mb": 3432.742912 |
|
947 |
+ }, |
|
948 |
+ { |
|
949 |
+ "kernel": "realized_fused", |
|
950 |
+ "S": 1, |
|
951 |
+ "n": 3900, |
|
952 |
+ "elements": 3900, |
|
953 |
+ "backend": "metal", |
|
954 |
+ "threads": 0, |
|
955 |
+ "median_s": 0.0006333747878670692, |
|
956 |
+ "ci_lo": 0.0001420830376446247, |
|
957 |
+ "ci_hi": 0.000777125358581543, |
|
958 |
+ "device_s": 2.037500962615013e-05, |
|
959 |
+ "elements_per_s": 6157491.7011356, |
|
960 |
+ "reps": 5, |
|
961 |
+ "precision": "fp32", |
|
962 |
+ "peak_rss_mb": 2913.878016 |
|
963 |
+ }, |
|
964 |
+ { |
|
965 |
+ "kernel": "realized_fused", |
|
966 |
+ "S": 1, |
|
967 |
+ "n": 39000, |
|
968 |
+ "elements": 39000, |
|
969 |
+ "backend": "cpu", |
|
970 |
+ "threads": 1, |
|
971 |
+ "median_s": 0.00018258299678564072, |
|
972 |
+ "ci_lo": 0.0001637078821659088, |
|
973 |
+ "ci_hi": 0.00037499982863664627, |
|
974 |
+ "device_s": 0.0, |
|
975 |
+ "elements_per_s": 213601489.11230472, |
|
976 |
+ "reps": 5, |
|
977 |
+ "precision": "fp64", |
|
978 |
+ "peak_rss_mb": 2962.440192 |
|
979 |
+ }, |
|
980 |
+ { |
|
981 |
+ "kernel": "realized_fused", |
|
982 |
+ "S": 1, |
|
983 |
+ "n": 39000, |
|
984 |
+ "elements": 39000, |
|
985 |
+ "backend": "cpu", |
|
986 |
+ "threads": 18, |
|
987 |
+ "median_s": 0.0001671668142080307, |
|
988 |
+ "ci_lo": 0.00015920819714665413, |
|
989 |
+ "ci_hi": 0.00017870916053652763, |
|
990 |
+ "device_s": 0.0, |
|
991 |
+ "elements_per_s": 233299893.79032168, |
|
992 |
+ "reps": 5, |
|
993 |
+ "precision": "fp64", |
|
994 |
+ "peak_rss_mb": 2962.440192 |
|
995 |
+ }, |
|
996 |
+ { |
|
997 |
+ "kernel": "realized_fused", |
|
998 |
+ "S": 1, |
|
999 |
+ "n": 39000, |
|
1000 |
+ "elements": 39000, |
|
1001 |
+ "backend": "metal", |
|
1002 |
+ "threads": 0, |
|
1003 |
+ "median_s": 0.000206624623388052, |
|
1004 |
+ "ci_lo": 0.0001971670426428318, |
|
1005 |
+ "ci_hi": 0.00024229194968938828, |
|
1006 |
+ "device_s": 4.3874955736100674e-05, |
|
1007 |
+ "elements_per_s": 188748075.42543435, |
|
1008 |
+ "reps": 5, |
|
1009 |
+ "precision": "fp32", |
|
1010 |
+ "peak_rss_mb": 3355.901952 |
|
1011 |
+ }, |
|
1012 |
+ { |
|
1013 |
+ "kernel": "realized_fused", |
|
1014 |
+ "S": 1, |
|
1015 |
+ "n": 390000, |
|
1016 |
+ "elements": 390000, |
|
1017 |
+ "backend": "cpu", |
|
1018 |
+ "threads": 1, |
|
1019 |
+ "median_s": 0.002032375428825617, |
|
1020 |
+ "ci_lo": 0.002019832842051983, |
|
1021 |
+ "ci_hi": 0.002052249852567911, |
|
1022 |
+ "device_s": 0.0, |
|
1023 |
+ "elements_per_s": 191893679.91196227, |
|
1024 |
+ "reps": 5, |
|
1025 |
+ "precision": "fp64", |
|
1026 |
+ "peak_rss_mb": 3222.339584 |
|
1027 |
+ }, |
|
1028 |
+ { |
|
1029 |
+ "kernel": "realized_fused", |
|
1030 |
+ "S": 1, |
|
1031 |
+ "n": 390000, |
|
1032 |
+ "elements": 390000, |
|
1033 |
+ "backend": "cpu", |
|
1034 |
+ "threads": 18, |
|
1035 |
+ "median_s": 0.0020858747884631157, |
|
1036 |
+ "ci_lo": 0.002067000139504671, |
|
1037 |
+ "ci_hi": 0.0027133747935295105, |
|
1038 |
+ "device_s": 0.0, |
|
1039 |
+ "elements_per_s": 186971913.25053322, |
|
1040 |
+ "reps": 5, |
|
1041 |
+ "precision": "fp64", |
|
1042 |
+ "peak_rss_mb": 2962.440192 |
|
1043 |
+ }, |
|
1044 |
+ { |
|
1045 |
+ "kernel": "realized_fused", |
|
1046 |
+ "S": 1, |
|
1047 |
+ "n": 390000, |
|
1048 |
+ "elements": 390000, |
|
1049 |
+ "backend": "metal", |
|
1050 |
+ "threads": 0, |
|
1051 |
+ "median_s": 0.0009353337809443474, |
|
1052 |
+ "ci_lo": 0.00017445813864469528, |
|
1053 |
+ "ci_hi": 0.0009425836615264416, |
|
1054 |
+ "device_s": 1.2583332136273384e-05, |
|
1055 |
+ "elements_per_s": 416963449.78178984, |
|
1056 |
+ "reps": 5, |
|
1057 |
+ "precision": "fp32", |
|
1058 |
+ "peak_rss_mb": 781.1072 |
|
1059 |
+ }, |
|
1060 |
+ { |
|
1061 |
+ "kernel": "realized_fused", |
|
1062 |
+ "S": 10, |
|
1063 |
+ "n": 390, |
|
1064 |
+ "elements": 3900, |
|
1065 |
+ "backend": "cpu", |
|
1066 |
+ "threads": 1, |
|
1067 |
+ "median_s": 1.1292286217212677e-05, |
|
1068 |
+ "ci_lo": 1.1167023330926895e-05, |
|
1069 |
+ "ci_hi": 1.2415926903486252e-05, |
|
1070 |
+ "device_s": 0.0, |
|
1071 |
+ "elements_per_s": 345368504.214433, |
|
1072 |
+ "reps": 5, |
|
1073 |
+ "precision": "fp64", |
|
1074 |
+ "peak_rss_mb": 3432.742912 |
|
1075 |
+ }, |
|
1076 |
+ { |
|
1077 |
+ "kernel": "realized_fused", |
|
1078 |
+ "S": 10, |
|
1079 |
+ "n": 390, |
|
1080 |
+ "elements": 3900, |
|
1081 |
+ "backend": "cpu", |
|
1082 |
+ "threads": 18, |
|
1083 |
+ "median_s": 0.00014200014993548393, |
|
1084 |
+ "ci_lo": 0.0001277080737054348, |
|
1085 |
+ "ci_hi": 0.0001649591140449047, |
|
1086 |
+ "device_s": 0.0, |
|
1087 |
+ "elements_per_s": 27464759.732802525, |
|
1088 |
+ "reps": 5, |
|
1089 |
+ "precision": "fp64", |
|
1090 |
+ "peak_rss_mb": 577.175552 |
|
1091 |
+ }, |
|
1092 |
+ { |
|
1093 |
+ "kernel": "realized_fused", |
|
1094 |
+ "S": 10, |
|
1095 |
+ "n": 390, |
|
1096 |
+ "elements": 3900, |
|
1097 |
+ "backend": "metal", |
|
1098 |
+ "threads": 0, |
|
1099 |
+ "median_s": 0.0002327919937670231, |
|
1100 |
+ "ci_lo": 0.00019591627642512321, |
|
1101 |
+ "ci_hi": 0.0002467092126607895, |
|
1102 |
+ "device_s": 3.124994691461325e-05, |
|
1103 |
+ "elements_per_s": 16753153.477877328, |
|
1104 |
+ "reps": 5, |
|
1105 |
+ "precision": "fp32", |
|
1106 |
+ "peak_rss_mb": 3255.451648 |
|
1107 |
+ }, |
|
1108 |
+ { |
|
1109 |
+ "kernel": "realized_fused", |
|
1110 |
+ "S": 10, |
|
1111 |
+ "n": 3900, |
|
1112 |
+ "elements": 39000, |
|
1113 |
+ "backend": "cpu", |
|
1114 |
+ "threads": 1, |
|
1115 |
+ "median_s": 0.00018791621550917625, |
|
1116 |
+ "ci_lo": 0.00017224997282028198, |
|
1117 |
+ "ci_hi": 0.00020966678857803345, |
|
1118 |
+ "device_s": 0.0, |
|
1119 |
+ "elements_per_s": 207539300.929012, |
|
1120 |
+ "reps": 5, |
|
1121 |
+ "precision": "fp64", |
|
1122 |
+ "peak_rss_mb": 3431.858176 |
|
1123 |
+ }, |
|
1124 |
+ { |
|
1125 |
+ "kernel": "realized_fused", |
|
1126 |
+ "S": 10, |
|
1127 |
+ "n": 3900, |
|
1128 |
+ "elements": 39000, |
|
1129 |
+ "backend": "cpu", |
|
1130 |
+ "threads": 18, |
|
1131 |
+ "median_s": 0.000135000329464674, |
|
1132 |
+ "ci_lo": 0.00012287497520446777, |
|
1133 |
+ "ci_hi": 0.0001421659253537655, |
|
1134 |
+ "device_s": 0.0, |
|
1135 |
+ "elements_per_s": 288888183.86332357, |
|
1136 |
+ "reps": 5, |
|
1137 |
+ "precision": "fp64", |
|
1138 |
+ "peak_rss_mb": 3360.096256 |
|
1139 |
+ }, |
|
1140 |
+ { |
|
1141 |
+ "kernel": "realized_fused", |
|
1142 |
+ "S": 10, |
|
1143 |
+ "n": 3900, |
|
1144 |
+ "elements": 39000, |
|
1145 |
+ "backend": "metal", |
|
1146 |
+ "threads": 0, |
|
1147 |
+ "median_s": 0.00016404176130890846, |
|
1148 |
+ "ci_lo": 0.00015954114496707916, |
|
1149 |
+ "ci_hi": 0.0009339582175016403, |
|
1150 |
+ "device_s": 1.6249949112534523e-05, |
|
1151 |
+ "elements_per_s": 237744338.32467064, |
|
1152 |
+ "reps": 5, |
|
1153 |
+ "precision": "fp32", |
|
1154 |
+ "peak_rss_mb": 3222.339584 |
|
1155 |
+ }, |
|
1156 |
+ { |
|
1157 |
+ "kernel": "realized_fused", |
|
1158 |
+ "S": 10, |
|
1159 |
+ "n": 39000, |
|
1160 |
+ "elements": 390000, |
|
1161 |
+ "backend": "cpu", |
|
1162 |
+ "threads": 1, |
|
1163 |
+ "median_s": 0.002572625409811735, |
|
1164 |
+ "ci_lo": 0.0020360001362860203, |
|
1165 |
+ "ci_hi": 0.0035845423117280006, |
|
1166 |
+ "device_s": 0.0, |
|
1167 |
+ "elements_per_s": 151596108.2062624, |
|
1168 |
+ "reps": 5, |
|
1169 |
+ "precision": "fp64", |
|
1170 |
+ "peak_rss_mb": 2962.440192 |
|
1171 |
+ }, |
|
1172 |
+ { |
|
1173 |
+ "kernel": "realized_fused", |
|
1174 |
+ "S": 10, |
|
1175 |
+ "n": 39000, |
|
1176 |
+ "elements": 390000, |
|
1177 |
+ "backend": "cpu", |
|
1178 |
+ "threads": 18, |
|
1179 |
+ "median_s": 0.00036349985748529434, |
|
1180 |
+ "ci_lo": 0.00035787513479590416, |
|
1181 |
+ "ci_hi": 0.00039070891216397285, |
|
1182 |
+ "device_s": 0.0, |
|
1183 |
+ "elements_per_s": 1072902759.0217906, |
|
1184 |
+ "reps": 5, |
|
1185 |
+ "precision": "fp64", |
|
1186 |
+ "peak_rss_mb": 3369.04192 |
|
1187 |
+ }, |
|
1188 |
+ { |
|
1189 |
+ "kernel": "realized_fused", |
|
1190 |
+ "S": 10, |
|
1191 |
+ "n": 39000, |
|
1192 |
+ "elements": 390000, |
|
1193 |
+ "backend": "metal", |
|
1194 |
+ "threads": 0, |
|
1195 |
+ "median_s": 0.0007184999994933605, |
|
1196 |
+ "ci_lo": 0.000268666073679924, |
|
1197 |
+ "ci_hi": 0.0007987502031028271, |
|
1198 |
+ "device_s": 5.52500132471323e-05, |
|
1199 |
+ "elements_per_s": 542797495.1635388, |
|
1200 |
+ "reps": 5, |
|
1201 |
+ "precision": "fp32", |
|
1202 |
+ "peak_rss_mb": 3355.901952 |
|
1203 |
+ }, |
|
1204 |
+ { |
|
1205 |
+ "kernel": "realized_fused", |
|
1206 |
+ "S": 10, |
|
1207 |
+ "n": 390000, |
|
1208 |
+ "elements": 3900000, |
|
1209 |
+ "backend": "cpu", |
|
1210 |
+ "threads": 1, |
|
1211 |
+ "median_s": 0.02089220890775323, |
|
1212 |
+ "ci_lo": 0.020823125261813402, |
|
1213 |
+ "ci_hi": 0.021495667286217213, |
|
1214 |
+ "device_s": 0.0, |
|
1215 |
+ "elements_per_s": 186672458.48535842, |
|
1216 |
+ "reps": 5, |
|
1217 |
+ "precision": "fp64", |
|
1218 |
+ "peak_rss_mb": 3431.497728 |
|
1219 |
+ }, |
|
1220 |
+ { |
|
1221 |
+ "kernel": "realized_fused", |
|
1222 |
+ "S": 10, |
|
1223 |
+ "n": 390000, |
|
1224 |
+ "elements": 3900000, |
|
1225 |
+ "backend": "cpu", |
|
1226 |
+ "threads": 18, |
|
1227 |
+ "median_s": 0.0025267917662858963, |
|
1228 |
+ "ci_lo": 0.0025061247870326042, |
|
1229 |
+ "ci_hi": 0.0027628750540316105, |
|
1230 |
+ "device_s": 0.0, |
|
1231 |
+ "elements_per_s": 1543459200.7289019, |
|
1232 |
+ "reps": 5, |
|
1233 |
+ "precision": "fp64", |
|
1234 |
+ "peak_rss_mb": 3431.858176 |
|
1235 |
+ }, |
|
1236 |
+ { |
|
1237 |
+ "kernel": "realized_fused", |
|
1238 |
+ "S": 10, |
|
1239 |
+ "n": 390000, |
|
1240 |
+ "elements": 3900000, |
|
1241 |
+ "backend": "metal", |
|
1242 |
+ "threads": 0, |
|
1243 |
+ "median_s": 0.0010219174437224865, |
|
1244 |
+ "ci_lo": 0.001003749668598175, |
|
1245 |
+ "ci_hi": 0.0010474580340087414, |
|
1246 |
+ "device_s": 8.649996016174555e-05, |
|
1247 |
+ "elements_per_s": 3816355248.6134977, |
|
1248 |
+ "reps": 5, |
|
1249 |
+ "precision": "fp32", |
|
1250 |
+ "peak_rss_mb": 3222.339584 |
|
1251 |
+ }, |
|
1252 |
+ { |
|
1253 |
+ "kernel": "realized_fused", |
|
1254 |
+ "S": 100, |
|
1255 |
+ "n": 390, |
|
1256 |
+ "elements": 39000, |
|
1257 |
+ "backend": "cpu", |
|
1258 |
+ "threads": 1, |
|
1259 |
+ "median_s": 0.0001871250569820404, |
|
1260 |
+ "ci_lo": 0.00016624992713332176, |
|
1261 |
+ "ci_hi": 0.00021525006741285324, |
|
1262 |
+ "device_s": 0.0, |
|
1263 |
+ "elements_per_s": 208416770.2016683, |
|
1264 |
+ "reps": 5, |
|
1265 |
+ "precision": "fp64", |
|
1266 |
+ "peak_rss_mb": 2962.440192 |
|
1267 |
+ }, |
|
1268 |
+ { |
|
1269 |
+ "kernel": "realized_fused", |
|
1270 |
+ "S": 100, |
|
1271 |
+ "n": 390, |
|
1272 |
+ "elements": 39000, |
|
1273 |
+ "backend": "cpu", |
|
1274 |
+ "threads": 18, |
|
1275 |
+ "median_s": 0.0005520828999578953, |
|
1276 |
+ "ci_lo": 0.0004998329095542431, |
|
1277 |
+ "ci_hi": 0.0005905842408537865, |
|
1278 |
+ "device_s": 0.0, |
|
1279 |
+ "elements_per_s": 70641564.88631389, |
|
1280 |
+ "reps": 5, |
|
1281 |
+ "precision": "fp64", |
|
1282 |
+ "peak_rss_mb": 3431.530496 |
|
1283 |
+ }, |
|
1284 |
+ { |
|
1285 |
+ "kernel": "realized_fused", |
|
1286 |
+ "S": 100, |
|
1287 |
+ "n": 390, |
|
1288 |
+ "elements": 39000, |
|
1289 |
+ "backend": "metal", |
|
1290 |
+ "threads": 0, |
|
1291 |
+ "median_s": 0.00022633420303463936, |
|
1292 |
+ "ci_lo": 0.00017816666513681412, |
|
1293 |
+ "ci_hi": 0.00027566729113459587, |
|
1294 |
+ "device_s": 3.15000070258975e-05, |
|
1295 |
+ "elements_per_s": 172311561.73966, |
|
1296 |
+ "reps": 5, |
|
1297 |
+ "precision": "fp32", |
|
1298 |
+ "peak_rss_mb": 3368.943616 |
|
1299 |
+ }, |
|
1300 |
+ { |
|
1301 |
+ "kernel": "realized_fused", |
|
1302 |
+ "S": 100, |
|
1303 |
+ "n": 3900, |
|
1304 |
+ "elements": 390000, |
|
1305 |
+ "backend": "cpu", |
|
1306 |
+ "threads": 1, |
|
1307 |
+ "median_s": 0.002043417189270258, |
|
1308 |
+ "ci_lo": 0.0020072502084076405, |
|
1309 |
+ "ci_hi": 0.0020909998565912247, |
|
1310 |
+ "device_s": 0.0, |
|
1311 |
+ "elements_per_s": 190856767.7945766, |
|
1312 |
+ "reps": 5, |
|
1313 |
+ "precision": "fp64", |
|
1314 |
+ "peak_rss_mb": 3432.742912 |
|
1315 |
+ }, |
|
1316 |
+ { |
|
1317 |
+ "kernel": "realized_fused", |
|
1318 |
+ "S": 100, |
|
1319 |
+ "n": 3900, |
|
1320 |
+ "elements": 390000, |
|
1321 |
+ "backend": "cpu", |
|
1322 |
+ "threads": 18, |
|
1323 |
+ "median_s": 0.0006015831604599953, |
|
1324 |
+ "ci_lo": 0.0005330839194357395, |
|
1325 |
+ "ci_hi": 0.0006621670909225941, |
|
1326 |
+ "device_s": 0.0, |
|
1327 |
+ "elements_per_s": 648289423.0313727, |
|
1328 |
+ "reps": 5, |
|
1329 |
+ "precision": "fp64", |
|
1330 |
+ "peak_rss_mb": 3355.8528 |
|
1331 |
+ }, |
|
1332 |
+ { |
|
1333 |
+ "kernel": "realized_fused", |
|
1334 |
+ "S": 100, |
|
1335 |
+ "n": 3900, |
|
1336 |
+ "elements": 390000, |
|
1337 |
+ "backend": "metal", |
|
1338 |
+ "threads": 0, |
|
1339 |
+ "median_s": 0.0006413329392671585, |
|
1340 |
+ "ci_lo": 0.000292791984975338, |
|
1341 |
+ "ci_hi": 0.0008833748288452625, |
|
1342 |
+ "device_s": 5.287490785121918e-05, |
|
1343 |
+ "elements_per_s": 608108481.7593294, |
|
1344 |
+ "reps": 5, |
|
1345 |
+ "precision": "fp32", |
|
1346 |
+ "peak_rss_mb": 490.962944 |
|
1347 |
+ }, |
|
1348 |
+ { |
|
1349 |
+ "kernel": "realized_fused", |
|
1350 |
+ "S": 100, |
|
1351 |
+ "n": 39000, |
|
1352 |
+ "elements": 3900000, |
|
1353 |
+ "backend": "cpu", |
|
1354 |
+ "threads": 1, |
|
1355 |
+ "median_s": 0.020590624772012234, |
|
1356 |
+ "ci_lo": 0.020551583264023066, |
|
1357 |
+ "ci_hi": 0.020679709035903215, |
|
1358 |
+ "device_s": 0.0, |
|
1359 |
+ "elements_per_s": 189406588.83265492, |
|
1360 |
+ "reps": 5, |
|
1361 |
+ "precision": "fp64", |
|
1362 |
+ "peak_rss_mb": 3222.339584 |
|
1363 |
+ }, |
|
1364 |
+ { |
|
1365 |
+ "kernel": "realized_fused", |
|
1366 |
+ "S": 100, |
|
1367 |
+ "n": 39000, |
|
1368 |
+ "elements": 3900000, |
|
1369 |
+ "backend": "cpu", |
|
1370 |
+ "threads": 18, |
|
1371 |
+ "median_s": 0.0021904585883021355, |
|
1372 |
+ "ci_lo": 0.001996333710849285, |
|
1373 |
+ "ci_hi": 0.002361500170081854, |
|
1374 |
+ "device_s": 0.0, |
|
1375 |
+ "elements_per_s": 1780449089.8971806, |
|
1376 |
+ "reps": 5, |
|
1377 |
+ "precision": "fp64", |
|
1378 |
+ "peak_rss_mb": 2962.440192 |
|
1379 |
+ }, |
|
1380 |
+ { |
|
1381 |
+ "kernel": "realized_fused", |
|
1382 |
+ "S": 100, |
|
1383 |
+ "n": 39000, |
|
1384 |
+ "elements": 3900000, |
|
1385 |
+ "backend": "metal", |
|
1386 |
+ "threads": 0, |
|
1387 |
+ "median_s": 0.0011692089028656483, |
|
1388 |
+ "ci_lo": 0.0008370000869035721, |
|
1389 |
+ "ci_hi": 0.0011960407719016075, |
|
1390 |
+ "device_s": 0.000259208376519382, |
|
1391 |
+ "elements_per_s": 3335588696.289753, |
|
1392 |
+ "reps": 5, |
|
1393 |
+ "precision": "fp32", |
|
1394 |
+ "peak_rss_mb": 3360.096256 |
|
1395 |
+ }, |
|
1396 |
+ { |
|
1397 |
+ "kernel": "realized_fused", |
|
1398 |
+ "S": 100, |
|
1399 |
+ "n": 390000, |
|
1400 |
+ "elements": 39000000, |
|
1401 |
+ "backend": "cpu", |
|
1402 |
+ "threads": 1, |
|
1403 |
+ "median_s": 0.2325868341140449, |
|
1404 |
+ "ci_lo": 0.2128961249254644, |
|
1405 |
+ "ci_hi": 0.24819900002330542, |
|
1406 |
+ "device_s": 0.0, |
|
1407 |
+ "elements_per_s": 167679310.60481706, |
|
1408 |
+ "reps": 5, |
|
1409 |
+ "precision": "fp64", |
|
1410 |
+ "peak_rss_mb": 2962.440192 |
|
1411 |
+ }, |
|
1412 |
+ { |
|
1413 |
+ "kernel": "realized_fused", |
|
1414 |
+ "S": 100, |
|
1415 |
+ "n": 390000, |
|
1416 |
+ "elements": 39000000, |
|
1417 |
+ "backend": "cpu", |
|
1418 |
+ "threads": 18, |
|
1419 |
+ "median_s": 0.01879258267581463, |
|
1420 |
+ "ci_lo": 0.016645667143166065, |
|
1421 |
+ "ci_hi": 0.02031658310443163, |
|
1422 |
+ "device_s": 0.0, |
|
1423 |
+ "elements_per_s": 2075286865.7159925, |
|
1424 |
+ "reps": 5, |
|
1425 |
+ "precision": "fp64", |
|
1426 |
+ "peak_rss_mb": 2962.440192 |
|
1427 |
+ }, |
|
1428 |
+ { |
|
1429 |
+ "kernel": "realized_fused", |
|
1430 |
+ "S": 100, |
|
1431 |
+ "n": 390000, |
|
1432 |
+ "elements": 39000000, |
|
1433 |
+ "backend": "metal", |
|
1434 |
+ "threads": 0, |
|
1435 |
+ "median_s": 0.008720249868929386, |
|
1436 |
+ "ci_lo": 0.007397250272333622, |
|
1437 |
+ "ci_hi": 0.008947291877120733, |
|
1438 |
+ "device_s": 0.0021910000359639525, |
|
1439 |
+ "elements_per_s": 4472348910.43187, |
|
1440 |
+ "reps": 5, |
|
1441 |
+ "precision": "fp32", |
|
1442 |
+ "peak_rss_mb": 486.178816 |
|
1443 |
+ }, |
|
1444 |
+ { |
|
1445 |
+ "kernel": "realized_fused", |
|
1446 |
+ "S": 1000, |
|
1447 |
+ "n": 390, |
|
1448 |
+ "elements": 390000, |
|
1449 |
+ "backend": "cpu", |
|
1450 |
+ "threads": 1, |
|
1451 |
+ "median_s": 0.002235791180282831, |
|
1452 |
+ "ci_lo": 0.0021259579807519913, |
|
1453 |
+ "ci_hi": 0.003065959084779024, |
|
1454 |
+ "device_s": 0.0, |
|
1455 |
+ "elements_per_s": 174434895.10083154, |
|
1456 |
+ "reps": 5, |
|
1457 |
+ "precision": "fp64", |
|
1458 |
+ "peak_rss_mb": 2962.440192 |
|
1459 |
+ }, |
|
1460 |
+ { |
|
1461 |
+ "kernel": "realized_fused", |
|
1462 |
+ "S": 1000, |
|
1463 |
+ "n": 390, |
|
1464 |
+ "elements": 390000, |
|
1465 |
+ "backend": "cpu", |
|
1466 |
+ "threads": 18, |
|
1467 |
+ "median_s": 0.0008399169892072678, |
|
1468 |
+ "ci_lo": 0.0007132496684789658, |
|
1469 |
+ "ci_hi": 0.0009002499282360077, |
|
1470 |
+ "device_s": 0.0, |
|
1471 |
+ "elements_per_s": 464331600.6360231, |
|
1472 |
+ "reps": 5, |
|
1473 |
+ "precision": "fp64", |
|
1474 |
+ "peak_rss_mb": 3355.8528 |
|
1475 |
+ }, |
|
1476 |
+ { |
|
1477 |
+ "kernel": "realized_fused", |
|
1478 |
+ "S": 1000, |
|
1479 |
+ "n": 390, |
|
1480 |
+ "elements": 390000, |
|
1481 |
+ "backend": "metal", |
|
1482 |
+ "threads": 0, |
|
1483 |
+ "median_s": 0.00033845799043774605, |
|
1484 |
+ "ci_lo": 0.00033012498170137405, |
|
1485 |
+ "ci_hi": 0.00035137496888637543, |
|
1486 |
+ "device_s": 0.00013987498823553324, |
|
1487 |
+ "elements_per_s": 1152284806.4410944, |
|
1488 |
+ "reps": 5, |
|
1489 |
+ "precision": "fp32", |
|
1490 |
+ "peak_rss_mb": 3431.87456 |
|
1491 |
+ }, |
|
1492 |
+ { |
|
1493 |
+ "kernel": "realized_fused", |
|
1494 |
+ "S": 1000, |
|
1495 |
+ "n": 3900, |
|
1496 |
+ "elements": 3900000, |
|
1497 |
+ "backend": "cpu", |
|
1498 |
+ "threads": 1, |
|
1499 |
+ "median_s": 0.021244540810585022, |
|
1500 |
+ "ci_lo": 0.021230708342045546, |
|
1501 |
+ "ci_hi": 0.021389917004853487, |
|
1502 |
+ "device_s": 0.0, |
|
1503 |
+ "elements_per_s": 183576573.14282066, |
|
1504 |
+ "reps": 5, |
|
1505 |
+ "precision": "fp64", |
|
1506 |
+ "peak_rss_mb": 3431.530496 |
|
1507 |
+ }, |
|
1508 |
+ { |
|
1509 |
+ "kernel": "realized_fused", |
|
1510 |
+ "S": 1000, |
|
1511 |
+ "n": 3900, |
|
1512 |
+ "elements": 3900000, |
|
1513 |
+ "backend": "cpu", |
|
1514 |
+ "threads": 18, |
|
1515 |
+ "median_s": 0.0017422502860426903, |
|
1516 |
+ "ci_lo": 0.0017107920721173286, |
|
1517 |
+ "ci_hi": 0.0017863749526441097, |
|
1518 |
+ "device_s": 0.0, |
|
1519 |
+ "elements_per_s": 2238484350.522551, |
|
1520 |
+ "reps": 5, |
|
1521 |
+ "precision": "fp64", |
|
1522 |
+ "peak_rss_mb": 3431.46496 |
|
1523 |
+ }, |
|
1524 |
+ { |
|
1525 |
+ "kernel": "realized_fused", |
|
1526 |
+ "S": 1000, |
|
1527 |
+ "n": 3900, |
|
1528 |
+ "elements": 3900000, |
|
1529 |
+ "backend": "metal", |
|
1530 |
+ "threads": 0, |
|
1531 |
+ "median_s": 0.0008750832639634609, |
|
1532 |
+ "ci_lo": 0.0008294158615171909, |
|
1533 |
+ "ci_hi": 0.0015468327328562737, |
|
1534 |
+ "device_s": 0.0002547500189393759, |
|
1535 |
+ "elements_per_s": 4456718761.065055, |
|
1536 |
+ "reps": 5, |
|
1537 |
+ "precision": "fp32", |
|
1538 |
+ "peak_rss_mb": 3432.742912 |
|
1539 |
+ }, |
|
1540 |
+ { |
|
1541 |
+ "kernel": "realized_fused", |
|
1542 |
+ "S": 1000, |
|
1543 |
+ "n": 39000, |
|
1544 |
+ "elements": 39000000, |
|
1545 |
+ "backend": "cpu", |
|
1546 |
+ "threads": 1, |
|
1547 |
+ "median_s": 0.23877166723832488, |
|
1548 |
+ "ci_lo": 0.21975037455558777, |
|
1549 |
+ "ci_hi": 0.2514020833186805, |
|
1550 |
+ "device_s": 0.0, |
|
1551 |
+ "elements_per_s": 163335962.13939813, |
|
1552 |
+ "reps": 5, |
|
1553 |
+ "precision": "fp64", |
|
1554 |
+ "peak_rss_mb": 2962.440192 |
|
1555 |
+ }, |
|
1556 |
+ { |
|
1557 |
+ "kernel": "realized_fused", |
|
1558 |
+ "S": 1000, |
|
1559 |
+ "n": 39000, |
|
1560 |
+ "elements": 39000000, |
|
1561 |
+ "backend": "cpu", |
|
1562 |
+ "threads": 18, |
|
1563 |
+ "median_s": 0.02024729223921895, |
|
1564 |
+ "ci_lo": 0.019154875073581934, |
|
1565 |
+ "ci_hi": 0.029473000206053257, |
|
1566 |
+ "device_s": 0.0, |
|
1567 |
+ "elements_per_s": 1926183488.5979028, |
|
1568 |
+ "reps": 5, |
|
1569 |
+ "precision": "fp64", |
|
1570 |
+ "peak_rss_mb": 2962.440192 |
|
1571 |
+ }, |
|
1572 |
+ { |
|
1573 |
+ "kernel": "realized_fused", |
|
1574 |
+ "S": 1000, |
|
1575 |
+ "n": 39000, |
|
1576 |
+ "elements": 39000000, |
|
1577 |
+ "backend": "metal", |
|
1578 |
+ "threads": 0, |
|
1579 |
+ "median_s": 0.005891874898225069, |
|
1580 |
+ "ci_lo": 0.005617166869342327, |
|
1581 |
+ "ci_hi": 0.00844891695305705, |
|
1582 |
+ "device_s": 0.0009469999931752682, |
|
1583 |
+ "elements_per_s": 6619285146.693929, |
|
1584 |
+ "reps": 5, |
|
1585 |
+ "precision": "fp32", |
|
1586 |
+ "peak_rss_mb": 3369.04192 |
|
1587 |
+ }, |
|
1588 |
+ { |
|
1589 |
+ "kernel": "realized_fused", |
|
1590 |
+ "S": 10000, |
|
1591 |
+ "n": 390, |
|
1592 |
+ "elements": 3900000, |
|
1593 |
+ "backend": "cpu", |
|
1594 |
+ "threads": 1, |
|
1595 |
+ "median_s": 0.021238334011286497, |
|
1596 |
+ "ci_lo": 0.020878124982118607, |
|
1597 |
+ "ci_hi": 0.021370540838688612, |
|
1598 |
+ "device_s": 0.0, |
|
1599 |
+ "elements_per_s": 183630222.49897087, |
|
1600 |
+ "reps": 5, |
|
1601 |
+ "precision": "fp64", |
|
1602 |
+ "peak_rss_mb": 3431.858176 |
|
1603 |
+ }, |
|
1604 |
+ { |
|
1605 |
+ "kernel": "realized_fused", |
|
1606 |
+ "S": 10000, |
|
1607 |
+ "n": 390, |
|
1608 |
+ "elements": 3900000, |
|
1609 |
+ "backend": "cpu", |
|
1610 |
+ "threads": 18, |
|
1611 |
+ "median_s": 0.002125917002558708, |
|
1612 |
+ "ci_lo": 0.0019880831241607666, |
|
1613 |
+ "ci_hi": 0.002400666009634733, |
|
1614 |
+ "device_s": 0.0, |
|
1615 |
+ "elements_per_s": 1834502473.6647966, |
|
1616 |
+ "reps": 5, |
|
1617 |
+ "precision": "fp64", |
|
1618 |
+ "peak_rss_mb": 2962.440192 |
|
1619 |
+ }, |
|
1620 |
+ { |
|
1621 |
+ "kernel": "realized_fused", |
|
1622 |
+ "S": 10000, |
|
1623 |
+ "n": 390, |
|
1624 |
+ "elements": 3900000, |
|
1625 |
+ "backend": "metal", |
|
1626 |
+ "threads": 0, |
|
1627 |
+ "median_s": 0.0022132499143481255, |
|
1628 |
+ "ci_lo": 0.0018930002115666866, |
|
1629 |
+ "ci_hi": 0.0032122922129929066, |
|
1630 |
+ "device_s": 0.001203041640110314, |
|
1631 |
+ "elements_per_s": 1762114605.6380522, |
|
1632 |
+ "reps": 5, |
|
1633 |
+ "precision": "fp32", |
|
1634 |
+ "peak_rss_mb": 3431.87456 |
|
1635 |
+ }, |
|
1636 |
+ { |
|
1637 |
+ "kernel": "realized_fused", |
|
1638 |
+ "S": 10000, |
|
1639 |
+ "n": 3900, |
|
1640 |
+ "elements": 39000000, |
|
1641 |
+ "backend": "cpu", |
|
1642 |
+ "threads": 1, |
|
1643 |
+ "median_s": 0.2336724577471614, |
|
1644 |
+ "ci_lo": 0.22654250031337142, |
|
1645 |
+ "ci_hi": 0.24493679078295827, |
|
1646 |
+ "device_s": 0.0, |
|
1647 |
+ "elements_per_s": 166900285.87878695, |
|
1648 |
+ "reps": 5, |
|
1649 |
+ "precision": "fp64", |
|
1650 |
+ "peak_rss_mb": 2962.440192 |
|
1651 |
+ }, |
|
1652 |
+ { |
|
1653 |
+ "kernel": "realized_fused", |
|
1654 |
+ "S": 10000, |
|
1655 |
+ "n": 3900, |
|
1656 |
+ "elements": 39000000, |
|
1657 |
+ "backend": "cpu", |
|
1658 |
+ "threads": 18, |
|
1659 |
+ "median_s": 0.01569391693919897, |
|
1660 |
+ "ci_lo": 0.015392750035971403, |
|
1661 |
+ "ci_hi": 0.01590104214847088, |
|
1662 |
+ "device_s": 0.0, |
|
1663 |
+ "elements_per_s": 2485039276.7524476, |
|
1664 |
+ "reps": 5, |
|
1665 |
+ "precision": "fp64", |
|
1666 |
+ "peak_rss_mb": 3432.742912 |
|
1667 |
+ }, |
|
1668 |
+ { |
|
1669 |
+ "kernel": "realized_fused", |
|
1670 |
+ "S": 10000, |
|
1671 |
+ "n": 3900, |
|
1672 |
+ "elements": 39000000, |
|
1673 |
+ "backend": "metal", |
|
1674 |
+ "threads": 0, |
|
1675 |
+ "median_s": 0.0078027499839663506, |
|
1676 |
+ "ci_lo": 0.006132957991212606, |
|
1677 |
+ "ci_hi": 0.008690916933119297, |
|
1678 |
+ "device_s": 0.0019207500154152513, |
|
1679 |
+ "elements_per_s": 4998237811.046104, |
|
1680 |
+ "reps": 5, |
|
1681 |
+ "precision": "fp32", |
|
1682 |
+ "peak_rss_mb": 577.1264 |
|
1683 |
+ }, |
|
1684 |
+ { |
|
1685 |
+ "kernel": "regression_stats", |
|
1686 |
+ "S": 1, |
|
1687 |
+ "n": 390, |
|
1688 |
+ "elements": 390, |
|
1689 |
+ "backend": "cpu", |
|
1690 |
+ "threads": 1, |
|
1691 |
+ "median_s": 3.1669624149799347e-06, |
|
1692 |
+ "ci_lo": 3.125052899122238e-06, |
|
1693 |
+ "ci_hi": 3.2088719308376312e-06, |
|
1694 |
+ "device_s": 0.0, |
|
1695 |
+ "elements_per_s": 123146393.57741508, |
|
1696 |
+ "reps": 5, |
|
1697 |
+ "precision": "fp64", |
|
1698 |
+ "peak_rss_mb": 2962.440192 |
|
1699 |
+ }, |
|
1700 |
+ { |
|
1701 |
+ "kernel": "regression_stats", |
|
1702 |
+ "S": 1, |
|
1703 |
+ "n": 390, |
|
1704 |
+ "elements": 390, |
|
1705 |
+ "backend": "cpu", |
|
1706 |
+ "threads": 18, |
|
1707 |
+ "median_s": 3.2088719308376312e-06, |
|
1708 |
+ "ci_lo": 3.2079406082630157e-06, |
|
1709 |
+ "ci_hi": 3.3332034945487976e-06, |
|
1710 |
+ "device_s": 0.0, |
|
1711 |
+ "elements_per_s": 121538038.41532433, |
|
1712 |
+ "reps": 5, |
|
1713 |
+ "precision": "fp64", |
|
1714 |
+ "peak_rss_mb": 2962.440192 |
|
1715 |
+ }, |
|
1716 |
+ { |
|
1717 |
+ "kernel": "regression_stats", |
|
1718 |
+ "S": 1, |
|
1719 |
+ "n": 390, |
|
1720 |
+ "elements": 390, |
|
1721 |
+ "backend": "metal", |
|
1722 |
+ "threads": 0, |
|
1723 |
+ "median_s": 0.000894167460501194, |
|
1724 |
+ "ci_lo": 0.00017508305609226227, |
|
1725 |
+ "ci_hi": 0.000988542102277279, |
|
1726 |
+ "device_s": 7.087492849677801e-05, |
|
1727 |
+ "elements_per_s": 436159.91100973333, |
|
1728 |
+ "reps": 5, |
|
1729 |
+ "precision": "fp32", |
|
1730 |
+ "peak_rss_mb": 3368.910848 |
|
1731 |
+ }, |
|
1732 |
+ { |
|
1733 |
+ "kernel": "regression_stats", |
|
1734 |
+ "S": 1, |
|
1735 |
+ "n": 3900, |
|
1736 |
+ "elements": 3900, |
|
1737 |
+ "backend": "cpu", |
|
1738 |
+ "threads": 1, |
|
1739 |
+ "median_s": 2.9958784580230713e-05, |
|
1740 |
+ "ci_lo": 2.950010821223259e-05, |
|
1741 |
+ "ci_hi": 3.0708033591508865e-05, |
|
1742 |
+ "device_s": 0.0, |
|
1743 |
+ "elements_per_s": 130178845.859239, |
|
1744 |
+ "reps": 5, |
|
1745 |
+ "precision": "fp64", |
|
1746 |
+ "peak_rss_mb": 3368.894464 |
|
1747 |
+ }, |
|
1748 |
+ { |
|
1749 |
+ "kernel": "regression_stats", |
|
1750 |
+ "S": 1, |
|
1751 |
+ "n": 3900, |
|
1752 |
+ "elements": 3900, |
|
1753 |
+ "backend": "cpu", |
|
1754 |
+ "threads": 18, |
|
1755 |
+ "median_s": 3.0207913368940353e-05, |
|
1756 |
+ "ci_lo": 3.008265048265457e-05, |
|
1757 |
+ "ci_hi": 3.0375085771083832e-05, |
|
1758 |
+ "device_s": 0.0, |
|
1759 |
+ "elements_per_s": 129105243.13175379, |
|
1760 |
+ "reps": 5, |
|
1761 |
+ "precision": "fp64", |
|
1762 |
+ "peak_rss_mb": 2962.440192 |
|
1763 |
+ }, |
|
1764 |
+ { |
|
1765 |
+ "kernel": "regression_stats", |
|
1766 |
+ "S": 1, |
|
1767 |
+ "n": 3900, |
|
1768 |
+ "elements": 3900, |
|
1769 |
+ "backend": "metal", |
|
1770 |
+ "threads": 0, |
|
1771 |
+ "median_s": 0.0003482499159872532, |
|
1772 |
+ "ci_lo": 0.0003069578669965267, |
|
1773 |
+ "ci_hi": 0.0003833337686955929, |
|
1774 |
+ "device_s": 0.00019212497863918543, |
|
1775 |
+ "elements_per_s": 11198854.101497471, |
|
1776 |
+ "reps": 5, |
|
1777 |
+ "precision": "fp32", |
|
1778 |
+ "peak_rss_mb": 2962.440192 |
|
1779 |
+ }, |
|
1780 |
+ { |
|
1781 |
+ "kernel": "regression_stats", |
|
1782 |
+ "S": 1, |
|
1783 |
+ "n": 39000, |
|
1784 |
+ "elements": 39000, |
|
1785 |
+ "backend": "cpu", |
|
1786 |
+ "threads": 1, |
|
1787 |
+ "median_s": 0.00030233291909098625, |
|
1788 |
+ "ci_lo": 0.00030054105445742607, |
|
1789 |
+ "ci_hi": 0.0003049168735742569, |
|
1790 |
+ "device_s": 0.0, |
|
1791 |
+ "elements_per_s": 128996869.13770398, |
|
1792 |
+ "reps": 5, |
|
1793 |
+ "precision": "fp64", |
|
1794 |
+ "peak_rss_mb": 2962.440192 |
|
1795 |
+ }, |
|
1796 |
+ { |
|
1797 |
+ "kernel": "regression_stats", |
|
1798 |
+ "S": 1, |
|
1799 |
+ "n": 39000, |
|
1800 |
+ "elements": 39000, |
|
1801 |
+ "backend": "cpu", |
|
1802 |
+ "threads": 18, |
|
1803 |
+ "median_s": 0.0003838753327727318, |
|
1804 |
+ "ci_lo": 0.0003343336284160614, |
|
1805 |
+ "ci_hi": 0.0006159590557217598, |
|
1806 |
+ "device_s": 0.0, |
|
1807 |
+ "elements_per_s": 101595483.4042161, |
|
1808 |
+ "reps": 5, |
|
1809 |
+ "precision": "fp64", |
|
1810 |
+ "peak_rss_mb": 578.486272 |
|
1811 |
+ }, |
|
1812 |
+ { |
|
1813 |
+ "kernel": "regression_stats", |
|
1814 |
+ "S": 1, |
|
1815 |
+ "n": 39000, |
|
1816 |
+ "elements": 39000, |
|
1817 |
+ "backend": "metal", |
|
1818 |
+ "threads": 0, |
|
1819 |
+ "median_s": 0.0004085828550159931, |
|
1820 |
+ "ci_lo": 0.0003508748486638069, |
|
1821 |
+ "ci_hi": 0.00041229184716939926, |
|
1822 |
+ "device_s": 0.00018866662867367268, |
|
1823 |
+ "elements_per_s": 95451875.96888623, |
|
1824 |
+ "reps": 5, |
|
1825 |
+ "precision": "fp32", |
|
1826 |
+ "peak_rss_mb": 3359.932416 |
|
1827 |
+ }, |
|
1828 |
+ { |
|
1829 |
+ "kernel": "regression_stats", |
|
1830 |
+ "S": 1, |
|
1831 |
+ "n": 390000, |
|
1832 |
+ "elements": 390000, |
|
1833 |
+ "backend": "cpu", |
|
1834 |
+ "threads": 1, |
|
1835 |
+ "median_s": 0.0029733749106526375, |
|
1836 |
+ "ci_lo": 0.002949208952486515, |
|
1837 |
+ "ci_hi": 0.0029905838891863823, |
|
1838 |
+ "device_s": 0.0, |
|
1839 |
+ "elements_per_s": 131164085.16220291, |
|
1840 |
+ "reps": 5, |
|
1841 |
+ "precision": "fp64", |
|
1842 |
+ "peak_rss_mb": 3368.943616 |
|
1843 |
+ }, |
|
1844 |
+ { |
|
1845 |
+ "kernel": "regression_stats", |
|
1846 |
+ "S": 1, |
|
1847 |
+ "n": 390000, |
|
1848 |
+ "elements": 390000, |
|
1849 |
+ "backend": "cpu", |
|
1850 |
+ "threads": 18, |
|
1851 |
+ "median_s": 0.0030428748577833176, |
|
1852 |
+ "ci_lo": 0.0030017499811947346, |
|
1853 |
+ "ci_hi": 0.003628334030508995, |
|
1854 |
+ "device_s": 0.0, |
|
1855 |
+ "elements_per_s": 128168267.9136231, |
|
1856 |
+ "reps": 5, |
|
1857 |
+ "precision": "fp64", |
|
1858 |
+ "peak_rss_mb": 572.112896 |
|
1859 |
+ }, |
|
1860 |
+ { |
|
1861 |
+ "kernel": "regression_stats", |
|
1862 |
+ "S": 1, |
|
1863 |
+ "n": 390000, |
|
1864 |
+ "elements": 390000, |
|
1865 |
+ "backend": "metal", |
|
1866 |
+ "threads": 0, |
|
1867 |
+ "median_s": 0.0007901252247393131, |
|
1868 |
+ "ci_lo": 0.0007615000940859318, |
|
1869 |
+ "ci_hi": 0.0008232500404119492, |
|
1870 |
+ "device_s": 9.650003630667925e-05, |
|
1871 |
+ "elements_per_s": 493592645.5564979, |
|
1872 |
+ "reps": 5, |
|
1873 |
+ "precision": "fp32", |
|
1874 |
+ "peak_rss_mb": 2920.12032 |
|
1875 |
+ }, |
|
1876 |
+ { |
|
1877 |
+ "kernel": "regression_stats", |
|
1878 |
+ "S": 10, |
|
1879 |
+ "n": 390, |
|
1880 |
+ "elements": 3900, |
|
1881 |
+ "backend": "cpu", |
|
1882 |
+ "threads": 1, |
|
1883 |
+ "median_s": 3.1250063329935074e-05, |
|
1884 |
+ "ci_lo": 3.095809370279312e-05, |
|
1885 |
+ "ci_hi": 4.149973392486572e-05, |
|
1886 |
+ "device_s": 0.0, |
|
1887 |
+ "elements_per_s": 124799747.08608383, |
|
1888 |
+ "reps": 5, |
|
1889 |
+ "precision": "fp64", |
|
1890 |
+ "peak_rss_mb": 2920.185856 |
|
1891 |
+ }, |
|
1892 |
+ { |
|
1893 |
+ "kernel": "regression_stats", |
|
1894 |
+ "S": 10, |
|
1895 |
+ "n": 390, |
|
1896 |
+ "elements": 3900, |
|
1897 |
+ "backend": "cpu", |
|
1898 |
+ "threads": 18, |
|
1899 |
+ "median_s": 4.133302718400955e-05, |
|
1900 |
+ "ci_lo": 2.475036308169365e-05, |
|
1901 |
+ "ci_hi": 4.3540727347135544e-05, |
|
1902 |
+ "device_s": 0.0, |
|
1903 |
+ "elements_per_s": 94355537.58590388, |
|
1904 |
+ "reps": 5, |
|
1905 |
+ "precision": "fp64", |
|
1906 |
+ "peak_rss_mb": 3359.932416 |
|
1907 |
+ }, |
|
1908 |
+ { |
|
1909 |
+ "kernel": "regression_stats", |
|
1910 |
+ "S": 10, |
|
1911 |
+ "n": 390, |
|
1912 |
+ "elements": 3900, |
|
1913 |
+ "backend": "metal", |
|
1914 |
+ "threads": 0, |
|
1915 |
+ "median_s": 0.0006523327901959419, |
|
1916 |
+ "ci_lo": 0.0003105420619249344, |
|
1917 |
+ "ci_hi": 0.0007279999554157257, |
|
1918 |
+ "device_s": 9.250000584870577e-05, |
|
1919 |
+ "elements_per_s": 5978543.557236411, |
|
1920 |
+ "reps": 5, |
|
1921 |
+ "precision": "fp32", |
|
1922 |
+ "peak_rss_mb": 2962.440192 |
|
1923 |
+ }, |
|
1924 |
+ { |
|
1925 |
+ "kernel": "regression_stats", |
|
1926 |
+ "S": 10, |
|
1927 |
+ "n": 3900, |
|
1928 |
+ "elements": 39000, |
|
1929 |
+ "backend": "cpu", |
|
1930 |
+ "threads": 1, |
|
1931 |
+ "median_s": 0.0002997498959302902, |
|
1932 |
+ "ci_lo": 0.0002982090227305889, |
|
1933 |
+ "ci_hi": 0.000300500076264143, |
|
1934 |
+ "device_s": 0.0, |
|
1935 |
+ "elements_per_s": 130108468.85855077, |
|
1936 |
+ "reps": 5, |
|
1937 |
+ "precision": "fp64", |
|
1938 |
+ "peak_rss_mb": 2962.440192 |
|
1939 |
+ }, |
|
1940 |
+ { |
|
1941 |
+ "kernel": "regression_stats", |
|
1942 |
+ "S": 10, |
|
1943 |
+ "n": 3900, |
|
1944 |
+ "elements": 39000, |
|
1945 |
+ "backend": "cpu", |
|
1946 |
+ "threads": 18, |
|
1947 |
+ "median_s": 7.625017315149307e-05, |
|
1948 |
+ "ci_lo": 7.187481969594955e-05, |
|
1949 |
+ "ci_hi": 8.49580392241478e-05, |
|
1950 |
+ "device_s": 0.0, |
|
1951 |
+ "elements_per_s": 511474248.3602653, |
|
1952 |
+ "reps": 5, |
|
1953 |
+ "precision": "fp64", |
|
1954 |
+ "peak_rss_mb": 3432.742912 |
|
1955 |
+ }, |
|
1956 |
+ { |
|
1957 |
+ "kernel": "regression_stats", |
|
1958 |
+ "S": 10, |
|
1959 |
+ "n": 3900, |
|
1960 |
+ "elements": 39000, |
|
1961 |
+ "backend": "metal", |
|
1962 |
+ "threads": 0, |
|
1963 |
+ "median_s": 0.00036174990236759186, |
|
1964 |
+ "ci_lo": 0.0003430834040045738, |
|
1965 |
+ "ci_hi": 0.0005066245794296265, |
|
1966 |
+ "device_s": 0.00018737500067800283, |
|
1967 |
+ "elements_per_s": 107809289.63560627, |
|
1968 |
+ "reps": 5, |
|
1969 |
+ "precision": "fp32", |
|
1970 |
+ "peak_rss_mb": 3431.514112 |
|
1971 |
+ }, |
|
1972 |
+ { |
|
1973 |
+ "kernel": "regression_stats", |
|
1974 |
+ "S": 10, |
|
1975 |
+ "n": 39000, |
|
1976 |
+ "elements": 390000, |
|
1977 |
+ "backend": "cpu", |
|
1978 |
+ "threads": 1, |
|
1979 |
+ "median_s": 0.003083667252212763, |
|
1980 |
+ "ci_lo": 0.0030186669901013374, |
|
1981 |
+ "ci_hi": 0.003116208128631115, |
|
1982 |
+ "device_s": 0.0, |
|
1983 |
+ "elements_per_s": 126472789.73441304, |
|
1984 |
+ "reps": 5, |
|
1985 |
+ "precision": "fp64", |
|
1986 |
+ "peak_rss_mb": 3431.530496 |
|
1987 |
+ }, |
|
1988 |
+ { |
|
1989 |
+ "kernel": "regression_stats", |
|
1990 |
+ "S": 10, |
|
1991 |
+ "n": 39000, |
|
1992 |
+ "elements": 390000, |
|
1993 |
+ "backend": "cpu", |
|
1994 |
+ "threads": 18, |
|
1995 |
+ "median_s": 0.0005624173209071159, |
|
1996 |
+ "ci_lo": 0.0005049579776823521, |
|
1997 |
+ "ci_hi": 0.0006032092496752739, |
|
1998 |
+ "device_s": 0.0, |
|
1999 |
+ "elements_per_s": 693435257.9521801, |
|
2000 |
+ "reps": 5, |
|
2001 |
+ "precision": "fp64", |
|
2002 |
+ "peak_rss_mb": 3431.563264 |
|
2003 |
+ }, |
|
2004 |
+ { |
|
2005 |
+ "kernel": "regression_stats", |
|
2006 |
+ "S": 10, |
|
2007 |
+ "n": 39000, |
|
2008 |
+ "elements": 390000, |
|
2009 |
+ "backend": "metal", |
|
2010 |
+ "threads": 0, |
|
2011 |
+ "median_s": 0.0006961673498153687, |
|
2012 |
+ "ci_lo": 0.0006541251204907894, |
|
2013 |
+ "ci_hi": 0.0008656666614115238, |
|
2014 |
+ "device_s": 0.0002501250710338354, |
|
2015 |
+ "elements_per_s": 560210127.7852694, |
|
2016 |
+ "reps": 5, |
|
2017 |
+ "precision": "fp32", |
|
2018 |
+ "peak_rss_mb": 576.421888 |
|
2019 |
+ }, |
|
2020 |
+ { |
|
2021 |
+ "kernel": "regression_stats", |
|
2022 |
+ "S": 10, |
|
2023 |
+ "n": 390000, |
|
2024 |
+ "elements": 3900000, |
|
2025 |
+ "backend": "cpu", |
|
2026 |
+ "threads": 1, |
|
2027 |
+ "median_s": 0.032662583980709314, |
|
2028 |
+ "ci_lo": 0.030701291747391224, |
|
2029 |
+ "ci_hi": 0.03406220907345414, |
|
2030 |
+ "device_s": 0.0, |
|
2031 |
+ "elements_per_s": 119402678.0705213, |
|
2032 |
+ "reps": 5, |
|
2033 |
+ "precision": "fp64", |
|
2034 |
+ "peak_rss_mb": 3431.858176 |
|
2035 |
+ }, |
|
2036 |
+ { |
|
2037 |
+ "kernel": "regression_stats", |
|
2038 |
+ "S": 10, |
|
2039 |
+ "n": 390000, |
|
2040 |
+ "elements": 3900000, |
|
2041 |
+ "backend": "cpu", |
|
2042 |
+ "threads": 18, |
|
2043 |
+ "median_s": 0.006654791999608278, |
|
2044 |
+ "ci_lo": 0.006012291181832552, |
|
2045 |
+ "ci_hi": 0.007818708196282387, |
|
2046 |
+ "device_s": 0.0, |
|
2047 |
+ "elements_per_s": 586043861.3602898, |
|
2048 |
+ "reps": 5, |
|
2049 |
+ "precision": "fp64", |
|
2050 |
+ "peak_rss_mb": 3431.46496 |
|
2051 |
+ }, |
|
2052 |
+ { |
|
2053 |
+ "kernel": "regression_stats", |
|
2054 |
+ "S": 10, |
|
2055 |
+ "n": 390000, |
|
2056 |
+ "elements": 3900000, |
|
2057 |
+ "backend": "metal", |
|
2058 |
+ "threads": 0, |
|
2059 |
+ "median_s": 0.004117042291909456, |
|
2060 |
+ "ci_lo": 0.002989500295370817, |
|
2061 |
+ "ci_hi": 0.004763709381222725, |
|
2062 |
+ "device_s": 0.000529208336956799, |
|
2063 |
+ "elements_per_s": 947281986.3094499, |
|
2064 |
+ "reps": 5, |
|
2065 |
+ "precision": "fp32", |
|
2066 |
+ "peak_rss_mb": 2962.440192 |
|
2067 |
+ }, |
|
2068 |
+ { |
|
2069 |
+ "kernel": "regression_stats", |
|
2070 |
+ "S": 100, |
|
2071 |
+ "n": 390, |
|
2072 |
+ "elements": 39000, |
|
2073 |
+ "backend": "cpu", |
|
2074 |
+ "threads": 1, |
|
2075 |
+ "median_s": 0.00036137504503130913, |
|
2076 |
+ "ci_lo": 0.00033475039526820183, |
|
2077 |
+ "ci_hi": 0.00036225002259016037, |
|
2078 |
+ "device_s": 0.0, |
|
2079 |
+ "elements_per_s": 107921121.10735561, |
|
2080 |
+ "reps": 5, |
|
2081 |
+ "precision": "fp64", |
|
2082 |
+ "peak_rss_mb": 2962.440192 |
|
2083 |
+ }, |
|
2084 |
+ { |
|
2085 |
+ "kernel": "regression_stats", |
|
2086 |
+ "S": 100, |
|
2087 |
+ "n": 390, |
|
2088 |
+ "elements": 39000, |
|
2089 |
+ "backend": "cpu", |
|
2090 |
+ "threads": 18, |
|
2091 |
+ "median_s": 0.00017625000327825546, |
|
2092 |
+ "ci_lo": 9.350012987852097e-05, |
|
2093 |
+ "ci_hi": 0.00018370803445577621, |
|
2094 |
+ "device_s": 0.0, |
|
2095 |
+ "elements_per_s": 221276591.62892938, |
|
2096 |
+ "reps": 5, |
|
2097 |
+ "precision": "fp64", |
|
2098 |
+ "peak_rss_mb": 3359.932416 |
|
2099 |
+ }, |
|
2100 |
+ { |
|
2101 |
+ "kernel": "regression_stats", |
|
2102 |
+ "S": 100, |
|
2103 |
+ "n": 390, |
|
2104 |
+ "elements": 39000, |
|
2105 |
+ "backend": "metal", |
|
2106 |
+ "threads": 0, |
|
2107 |
+ "median_s": 0.0003363746218383312, |
|
2108 |
+ "ci_lo": 0.00026350002735853195, |
|
2109 |
+ "ci_hi": 0.0005579171702265739, |
|
2110 |
+ "device_s": 0.00019220833200961351, |
|
2111 |
+ "elements_per_s": 115942159.33074829, |
|
2112 |
+ "reps": 5, |
|
2113 |
+ "precision": "fp32", |
|
2114 |
+ "peak_rss_mb": 3255.451648 |
|
2115 |
+ }, |
|
2116 |
+ { |
|
2117 |
+ "kernel": "regression_stats", |
|
2118 |
+ "S": 100, |
|
2119 |
+ "n": 3900, |
|
2120 |
+ "elements": 390000, |
|
2121 |
+ "backend": "cpu", |
|
2122 |
+ "threads": 1, |
|
2123 |
+ "median_s": 0.0029982919804751873, |
|
2124 |
+ "ci_lo": 0.0029679168947041035, |
|
2125 |
+ "ci_hi": 0.003063875250518322, |
|
2126 |
+ "device_s": 0.0, |
|
2127 |
+ "elements_per_s": 130074056.34263493, |
|
2128 |
+ "reps": 5, |
|
2129 |
+ "precision": "fp64", |
|
2130 |
+ "peak_rss_mb": 3432.742912 |
|
2131 |
+ }, |
|
2132 |
+ { |
|
2133 |
+ "kernel": "regression_stats", |
|
2134 |
+ "S": 100, |
|
2135 |
+ "n": 3900, |
|
2136 |
+ "elements": 390000, |
|
2137 |
+ "backend": "cpu", |
|
2138 |
+ "threads": 18, |
|
2139 |
+ "median_s": 0.0004399162717163563, |
|
2140 |
+ "ci_lo": 0.00042741699144244194, |
|
2141 |
+ "ci_hi": 0.00046166684478521347, |
|
2142 |
+ "device_s": 0.0, |
|
2143 |
+ "elements_per_s": 886532335.9792868, |
|
2144 |
+ "reps": 5, |
|
2145 |
+ "precision": "fp64", |
|
2146 |
+ "peak_rss_mb": 781.484032 |
|
2147 |
+ }, |
|
2148 |
+ { |
|
2149 |
+ "kernel": "regression_stats", |
|
2150 |
+ "S": 100, |
|
2151 |
+ "n": 3900, |
|
2152 |
+ "elements": 390000, |
|
2153 |
+ "backend": "metal", |
|
2154 |
+ "threads": 0, |
|
2155 |
+ "median_s": 0.0005946666933596134, |
|
2156 |
+ "ci_lo": 0.0005814996547996998, |
|
2157 |
+ "ci_hi": 0.0005976245738565922, |
|
2158 |
+ "device_s": 0.00023925001733005047, |
|
2159 |
+ "elements_per_s": 655829566.9741753, |
|
2160 |
+ "reps": 5, |
|
2161 |
+ "precision": "fp32", |
|
2162 |
+ "peak_rss_mb": 2962.440192 |
|
2163 |
+ }, |
|
2164 |
+ { |
|
2165 |
+ "kernel": "regression_stats", |
|
2166 |
+ "S": 100, |
|
2167 |
+ "n": 39000, |
|
2168 |
+ "elements": 3900000, |
|
2169 |
+ "backend": "cpu", |
|
2170 |
+ "threads": 1, |
|
2171 |
+ "median_s": 0.03219050029292703, |
|
2172 |
+ "ci_lo": 0.03135691722854972, |
|
2173 |
+ "ci_hi": 0.03299033408984542, |
|
2174 |
+ "device_s": 0.0, |
|
2175 |
+ "elements_per_s": 121153755.44060485, |
|
2176 |
+ "reps": 5, |
|
2177 |
+ "precision": "fp64", |
|
2178 |
+ "peak_rss_mb": 3355.901952 |
|
2179 |
+ }, |
|
2180 |
+ { |
|
2181 |
+ "kernel": "regression_stats", |
|
2182 |
+ "S": 100, |
|
2183 |
+ "n": 39000, |
|
2184 |
+ "elements": 3900000, |
|
2185 |
+ "backend": "cpu", |
|
2186 |
+ "threads": 18, |
|
2187 |
+ "median_s": 0.0031737093813717365, |
|
2188 |
+ "ci_lo": 0.003017541952431202, |
|
2189 |
+ "ci_hi": 0.0036639999598264694, |
|
2190 |
+ "device_s": 0.0, |
|
2191 |
+ "elements_per_s": 1228845975.2777827, |
|
2192 |
+ "reps": 5, |
|
2193 |
+ "precision": "fp64", |
|
2194 |
+ "peak_rss_mb": 3355.901952 |
|
2195 |
+ }, |
|
2196 |
+ { |
|
2197 |
+ "kernel": "regression_stats", |
|
2198 |
+ "S": 100, |
|
2199 |
+ "n": 39000, |
|
2200 |
+ "elements": 3900000, |
|
2201 |
+ "backend": "metal", |
|
2202 |
+ "threads": 0, |
|
2203 |
+ "median_s": 0.0044694580137729645, |
|
2204 |
+ "ci_lo": 0.0031338329426944256, |
|
2205 |
+ "ci_hi": 0.004542499780654907, |
|
2206 |
+ "device_s": 0.0016885417280718684, |
|
2207 |
+ "elements_per_s": 872589022.6470106, |
|
2208 |
+ "reps": 5, |
|
2209 |
+ "precision": "fp32", |
|
2210 |
+ "peak_rss_mb": 3431.46496 |
|
2211 |
+ }, |
|
2212 |
+ { |
|
2213 |
+ "kernel": "regression_stats", |
|
2214 |
+ "S": 100, |
|
2215 |
+ "n": 390000, |
|
2216 |
+ "elements": 39000000, |
|
2217 |
+ "backend": "cpu", |
|
2218 |
+ "threads": 1, |
|
2219 |
+ "median_s": 0.3013692502863705, |
|
2220 |
+ "ci_lo": 0.2989709582179785, |
|
2221 |
+ "ci_hi": 0.3020119168795645, |
|
2222 |
+ "device_s": 0.0, |
|
2223 |
+ "elements_per_s": 129409354.01651289, |
|
2224 |
+ "reps": 5, |
|
2225 |
+ "precision": "fp64", |
|
2226 |
+ "peak_rss_mb": 3431.87456 |
|
2227 |
+ }, |
|
2228 |
+ { |
|
2229 |
+ "kernel": "regression_stats", |
|
2230 |
+ "S": 100, |
|
2231 |
+ "n": 390000, |
|
2232 |
+ "elements": 39000000, |
|
2233 |
+ "backend": "cpu", |
|
2234 |
+ "threads": 18, |
|
2235 |
+ "median_s": 0.033760249614715576, |
|
2236 |
+ "ci_lo": 0.0324889593757689, |
|
2237 |
+ "ci_hi": 0.03822179138660431, |
|
2238 |
+ "device_s": 0.0, |
|
2239 |
+ "elements_per_s": 1155204728.7885127, |
|
2240 |
+ "reps": 5, |
|
2241 |
+ "precision": "fp64", |
|
2242 |
+ "peak_rss_mb": 3359.932416 |
|
2243 |
+ }, |
|
2244 |
+ { |
|
2245 |
+ "kernel": "regression_stats", |
|
2246 |
+ "S": 100, |
|
2247 |
+ "n": 390000, |
|
2248 |
+ "elements": 39000000, |
|
2249 |
+ "backend": "metal", |
|
2250 |
+ "threads": 0, |
|
2251 |
+ "median_s": 0.03070899983868003, |
|
2252 |
+ "ci_lo": 0.027952750213444233, |
|
2253 |
+ "ci_hi": 0.031758958008140326, |
|
2254 |
+ "device_s": 0.005229625036008656, |
|
2255 |
+ "elements_per_s": 1269986004.2617507, |
|
2256 |
+ "reps": 5, |
|
2257 |
+ "precision": "fp32", |
|
2258 |
+ "peak_rss_mb": 2913.845248 |
|
2259 |
+ }, |
|
2260 |
+ { |
|
2261 |
+ "kernel": "regression_stats", |
|
2262 |
+ "S": 1000, |
|
2263 |
+ "n": 390, |
|
2264 |
+ "elements": 390000, |
|
2265 |
+ "backend": "cpu", |
|
2266 |
+ "threads": 1, |
|
2267 |
+ "median_s": 0.0031211250461637974, |
|
2268 |
+ "ci_lo": 0.0030487077310681343, |
|
2269 |
+ "ci_hi": 0.0040359580889344215, |
|
2270 |
+ "device_s": 0.0, |
|
2271 |
+ "elements_per_s": 124954942.28254408, |
|
2272 |
+ "reps": 5, |
|
2273 |
+ "precision": "fp64", |
|
2274 |
+ "peak_rss_mb": 3432.742912 |
|
2275 |
+ }, |
|
2276 |
+ { |
|
2277 |
+ "kernel": "regression_stats", |
|
2278 |
+ "S": 1000, |
|
2279 |
+ "n": 390, |
|
2280 |
+ "elements": 390000, |
|
2281 |
+ "backend": "cpu", |
|
2282 |
+ "threads": 18, |
|
2283 |
+ "median_s": 0.0006971252150833607, |
|
2284 |
+ "ci_lo": 0.0005761669017374516, |
|
2285 |
+ "ci_hi": 0.0007857088930904865, |
|
2286 |
+ "device_s": 0.0, |
|
2287 |
+ "elements_per_s": 559440386.8369108, |
|
2288 |
+ "reps": 5, |
|
2289 |
+ "precision": "fp64", |
|
2290 |
+ "peak_rss_mb": 2962.440192 |
|
2291 |
+ }, |
|
2292 |
+ { |
|
2293 |
+ "kernel": "regression_stats", |
|
2294 |
+ "S": 1000, |
|
2295 |
+ "n": 390, |
|
2296 |
+ "elements": 390000, |
|
2297 |
+ "backend": "metal", |
|
2298 |
+ "threads": 0, |
|
2299 |
+ "median_s": 0.0005814996547996998, |
|
2300 |
+ "ci_lo": 0.0005787923000752926, |
|
2301 |
+ "ci_hi": 0.0009665000252425671, |
|
2302 |
+ "device_s": 0.00020362494979053736, |
|
2303 |
+ "elements_per_s": 670679675.870723, |
|
2304 |
+ "reps": 5, |
|
2305 |
+ "precision": "fp32", |
|
2306 |
+ "peak_rss_mb": 3431.858176 |
|
2307 |
+ }, |
|
2308 |
+ { |
|
2309 |
+ "kernel": "regression_stats", |
|
2310 |
+ "S": 1000, |
|
2311 |
+ "n": 3900, |
|
2312 |
+ "elements": 3900000, |
|
2313 |
+ "backend": "cpu", |
|
2314 |
+ "threads": 1, |
|
2315 |
+ "median_s": 0.03439616598188877, |
|
2316 |
+ "ci_lo": 0.033030624967068434, |
|
2317 |
+ "ci_hi": 0.03468058304861188, |
|
2318 |
+ "device_s": 0.0, |
|
2319 |
+ "elements_per_s": 113384730.20666131, |
|
2320 |
+ "reps": 5, |
|
2321 |
+ "precision": "fp64", |
|
2322 |
+ "peak_rss_mb": 781.484032 |
|
2323 |
+ }, |
|
2324 |
+ { |
|
2325 |
+ "kernel": "regression_stats", |
|
2326 |
+ "S": 1000, |
|
2327 |
+ "n": 3900, |
|
2328 |
+ "elements": 3900000, |
|
2329 |
+ "backend": "cpu", |
|
2330 |
+ "threads": 18, |
|
2331 |
+ "median_s": 0.003421790897846222, |
|
2332 |
+ "ci_lo": 0.0031987917609512806, |
|
2333 |
+ "ci_hi": 0.003632874693721533, |
|
2334 |
+ "device_s": 0.0, |
|
2335 |
+ "elements_per_s": 1139754040.0422413, |
|
2336 |
+ "reps": 5, |
|
2337 |
+ "precision": "fp64", |
|
2338 |
+ "peak_rss_mb": 3431.514112 |
|
2339 |
+ }, |
|
2340 |
+ { |
|
2341 |
+ "kernel": "regression_stats", |
|
2342 |
+ "S": 1000, |
|
2343 |
+ "n": 3900, |
|
2344 |
+ "elements": 3900000, |
|
2345 |
+ "backend": "metal", |
|
2346 |
+ "threads": 0, |
|
2347 |
+ "median_s": 0.003796167206019163, |
|
2348 |
+ "ci_lo": 0.0033167502842843533, |
|
2349 |
+ "ci_hi": 0.004350459203124046, |
|
2350 |
+ "device_s": 0.000579125015065074, |
|
2351 |
+ "elements_per_s": 1027352007.5238521, |
|
2352 |
+ "reps": 5, |
|
2353 |
+ "precision": "fp32", |
|
2354 |
+ "peak_rss_mb": 781.1072 |
|
2355 |
+ }, |
|
2356 |
+ { |
|
2357 |
+ "kernel": "regression_stats", |
|
2358 |
+ "S": 1000, |
|
2359 |
+ "n": 39000, |
|
2360 |
+ "elements": 39000000, |
|
2361 |
+ "backend": "cpu", |
|
2362 |
+ "threads": 1, |
|
2363 |
+ "median_s": 0.3240363751538098, |
|
2364 |
+ "ci_lo": 0.3117389581166208, |
|
2365 |
+ "ci_hi": 0.326583041343838, |
|
2366 |
+ "device_s": 0.0, |
|
2367 |
+ "elements_per_s": 120356858.02709013, |
|
2368 |
+ "reps": 5, |
|
2369 |
+ "precision": "fp64", |
|
2370 |
+ "peak_rss_mb": 3431.46496 |
|
2371 |
+ }, |
|
2372 |
+ { |
|
2373 |
+ "kernel": "regression_stats", |
|
2374 |
+ "S": 1000, |
|
2375 |
+ "n": 39000, |
|
2376 |
+ "elements": 39000000, |
|
2377 |
+ "backend": "cpu", |
|
2378 |
+ "threads": 18, |
|
2379 |
+ "median_s": 0.031240916810929775, |
|
2380 |
+ "ci_lo": 0.029546833131462336, |
|
2381 |
+ "ci_hi": 0.03264595801010728, |
|
2382 |
+ "device_s": 0.0, |
|
2383 |
+ "elements_per_s": 1248362851.7059293, |
|
2384 |
+ "reps": 5, |
|
2385 |
+ "precision": "fp64", |
|
2386 |
+ "peak_rss_mb": 3431.87456 |
|
2387 |
+ }, |
|
2388 |
+ { |
|
2389 |
+ "kernel": "regression_stats", |
|
2390 |
+ "S": 1000, |
|
2391 |
+ "n": 39000, |
|
2392 |
+ "elements": 39000000, |
|
2393 |
+ "backend": "metal", |
|
2394 |
+ "threads": 0, |
|
2395 |
+ "median_s": 0.026743208058178425, |
|
2396 |
+ "ci_lo": 0.025766875129193068, |
|
2397 |
+ "ci_hi": 0.02711204206570983, |
|
2398 |
+ "device_s": 0.004475083318538964, |
|
2399 |
+ "elements_per_s": 1458314197.5771036, |
|
2400 |
+ "reps": 5, |
|
2401 |
+ "precision": "fp32", |
|
2402 |
+ "peak_rss_mb": 3360.11264 |
|
2403 |
+ }, |
|
2404 |
+ { |
|
2405 |
+ "kernel": "regression_stats", |
|
2406 |
+ "S": 10000, |
|
2407 |
+ "n": 390, |
|
2408 |
+ "elements": 3900000, |
|
2409 |
+ "backend": "cpu", |
|
2410 |
+ "threads": 1, |
|
2411 |
+ "median_s": 0.030644499696791172, |
|
2412 |
+ "ci_lo": 0.030419666320085526, |
|
2413 |
+ "ci_hi": 0.030872833915054798, |
|
2414 |
+ "device_s": 0.0, |
|
2415 |
+ "elements_per_s": 127265905.41820379, |
|
2416 |
+ "reps": 5, |
|
2417 |
+ "precision": "fp64", |
|
2418 |
+ "peak_rss_mb": 3431.87456 |
|
2419 |
+ }, |
|
2420 |
+ { |
|
2421 |
+ "kernel": "regression_stats", |
|
2422 |
+ "S": 10000, |
|
2423 |
+ "n": 390, |
|
2424 |
+ "elements": 3900000, |
|
2425 |
+ "backend": "cpu", |
|
2426 |
+ "threads": 18, |
|
2427 |
+ "median_s": 0.003959249705076218, |
|
2428 |
+ "ci_lo": 0.0036838343366980553, |
|
2429 |
+ "ci_hi": 0.00489212479442358, |
|
2430 |
+ "device_s": 0.0, |
|
2431 |
+ "elements_per_s": 985035117.8910861, |
|
2432 |
+ "reps": 5, |
|
2433 |
+ "precision": "fp64", |
|
2434 |
+ "peak_rss_mb": 2962.440192 |
|
2435 |
+ }, |
|
2436 |
+ { |
|
2437 |
+ "kernel": "regression_stats", |
|
2438 |
+ "S": 10000, |
|
2439 |
+ "n": 390, |
|
2440 |
+ "elements": 3900000, |
|
2441 |
+ "backend": "metal", |
|
2442 |
+ "threads": 0, |
|
2443 |
+ "median_s": 0.004190749954432249, |
|
2444 |
+ "ci_lo": 0.00392800010740757, |
|
2445 |
+ "ci_hi": 0.005979666020721197, |
|
2446 |
+ "device_s": 0.0011161250295117497, |
|
2447 |
+ "elements_per_s": 930621020.6779948, |
|
2448 |
+ "reps": 5, |
|
2449 |
+ "precision": "fp32", |
|
2450 |
+ "peak_rss_mb": 3432.742912 |
|
2451 |
+ }, |
|
2452 |
+ { |
|
2453 |
+ "kernel": "regression_stats", |
|
2454 |
+ "S": 10000, |
|
2455 |
+ "n": 3900, |
|
2456 |
+ "elements": 39000000, |
|
2457 |
+ "backend": "cpu", |
|
2458 |
+ "threads": 1, |
|
2459 |
+ "median_s": 0.3569141672924161, |
|
2460 |
+ "ci_lo": 0.3479222496971488, |
|
2461 |
+ "ci_hi": 0.35834929207339883, |
|
2462 |
+ "device_s": 0.0, |
|
2463 |
+ "elements_per_s": 109269969.01203898, |
|
2464 |
+ "reps": 5, |
|
2465 |
+ "precision": "fp64", |
|
2466 |
+ "peak_rss_mb": 2962.440192 |
|
2467 |
+ }, |
|
2468 |
+ { |
|
2469 |
+ "kernel": "regression_stats", |
|
2470 |
+ "S": 10000, |
|
2471 |
+ "n": 3900, |
|
2472 |
+ "elements": 39000000, |
|
2473 |
+ "backend": "cpu", |
|
2474 |
+ "threads": 18, |
|
2475 |
+ "median_s": 0.03749012481421232, |
|
2476 |
+ "ci_lo": 0.03214179212227464, |
|
2477 |
+ "ci_hi": 0.03947866568341851, |
|
2478 |
+ "device_s": 0.0, |
|
2479 |
+ "elements_per_s": 1040273943.9591113, |
|
2480 |
+ "reps": 5, |
|
2481 |
+ "precision": "fp64", |
|
2482 |
+ "peak_rss_mb": 2962.440192 |
|
2483 |
+ }, |
|
2484 |
+ { |
|
2485 |
+ "kernel": "regression_stats", |
|
2486 |
+ "S": 10000, |
|
2487 |
+ "n": 3900, |
|
2488 |
+ "elements": 39000000, |
|
2489 |
+ "backend": "metal", |
|
2490 |
+ "threads": 0, |
|
2491 |
+ "median_s": 0.026574499905109406, |
|
2492 |
+ "ci_lo": 0.026411292143166065, |
|
2493 |
+ "ci_hi": 0.026990290731191635, |
|
2494 |
+ "device_s": 0.004499250091612339, |
|
2495 |
+ "elements_per_s": 1467572301.9909616, |
|
2496 |
+ "reps": 5, |
|
2497 |
+ "precision": "fp32", |
|
2498 |
+ "peak_rss_mb": 3221.83168 |
|
2499 |
+ }, |
|
2500 |
+ { |
|
2501 |
+ "kernel": "rolling_sumsq", |
|
2502 |
+ "S": 1, |
|
2503 |
+ "n": 390, |
|
2504 |
+ "elements": 390, |
|
2505 |
+ "backend": "cpu", |
|
2506 |
+ "threads": 1, |
|
2507 |
+ "median_s": 9.578652679920197e-07, |
|
2508 |
+ "ci_lo": 8.330680429935455e-07, |
|
2509 |
+ "ci_hi": 1.0831281542778015e-06, |
|
2510 |
+ "device_s": 0.0, |
|
2511 |
+ "elements_per_s": 407155382.94603795, |
|
2512 |
+ "reps": 5, |
|
2513 |
+ "precision": "fp64", |
|
2514 |
+ "peak_rss_mb": 3431.497728 |
|
2515 |
+ }, |
|
2516 |
+ { |
|
2517 |
+ "kernel": "rolling_sumsq", |
|
2518 |
+ "S": 1, |
|
2519 |
+ "n": 390, |
|
2520 |
+ "elements": 390, |
|
2521 |
+ "backend": "cpu", |
|
2522 |
+ "threads": 18, |
|
2523 |
+ "median_s": 7.920898497104645e-07, |
|
2524 |
+ "ci_lo": 7.920898497104645e-07, |
|
2525 |
+ "ci_hi": 8.749775588512421e-07, |
|
2526 |
+ "device_s": 0.0, |
|
2527 |
+ "elements_per_s": 492368384.9029982, |
|
2528 |
+ "reps": 5, |
|
2529 |
+ "precision": "fp64", |
|
2530 |
+ "peak_rss_mb": 3431.87456 |
|
2531 |
+ }, |
|
2532 |
+ { |
|
2533 |
+ "kernel": "rolling_sumsq", |
|
2534 |
+ "S": 1, |
|
2535 |
+ "n": 390, |
|
2536 |
+ "elements": 390, |
|
2537 |
+ "backend": "metal", |
|
2538 |
+ "threads": 0, |
|
2539 |
+ "median_s": 0.0002839169465005398, |
|
2540 |
+ "ci_lo": 0.0001594587229192257, |
|
2541 |
+ "ci_hi": 0.0008917916566133499, |
|
2542 |
+ "device_s": 1.8750084564089775e-05, |
|
2543 |
+ "elements_per_s": 1373641.146845944, |
|
2544 |
+ "reps": 5, |
|
2545 |
+ "precision": "fp32", |
|
2546 |
+ "peak_rss_mb": 3253.567488 |
|
2547 |
+ }, |
|
2548 |
+ { |
|
2549 |
+ "kernel": "rolling_sumsq", |
|
2550 |
+ "S": 1, |
|
2551 |
+ "n": 3900, |
|
2552 |
+ "elements": 3900, |
|
2553 |
+ "backend": "cpu", |
|
2554 |
+ "threads": 1, |
|
2555 |
+ "median_s": 7.4999406933784485e-06, |
|
2556 |
+ "ci_lo": 7.33276829123497e-06, |
|
2557 |
+ "ci_hi": 7.542315870523453e-06, |
|
2558 |
+ "device_s": 0.0, |
|
2559 |
+ "elements_per_s": 520004111.9582764, |
|
2560 |
+ "reps": 5, |
|
2561 |
+ "precision": "fp64", |
|
2562 |
+ "peak_rss_mb": 3431.530496 |
|
2563 |
+ }, |
|
2564 |
+ { |
|
2565 |
+ "kernel": "rolling_sumsq", |
|
2566 |
+ "S": 1, |
|
2567 |
+ "n": 3900, |
|
2568 |
+ "elements": 3900, |
|
2569 |
+ "backend": "cpu", |
|
2570 |
+ "threads": 18, |
|
2571 |
+ "median_s": 7.4999406933784485e-06, |
|
2572 |
+ "ci_lo": 7.415656000375748e-06, |
|
2573 |
+ "ci_hi": 8.250121027231216e-06, |
|
2574 |
+ "device_s": 0.0, |
|
2575 |
+ "elements_per_s": 520004111.9582764, |
|
2576 |
+ "reps": 5, |
|
2577 |
+ "precision": "fp64", |
|
2578 |
+ "peak_rss_mb": 3255.468032 |
|
2579 |
+ }, |
|
2580 |
+ { |
|
2581 |
+ "kernel": "rolling_sumsq", |
|
2582 |
+ "S": 1, |
|
2583 |
+ "n": 3900, |
|
2584 |
+ "elements": 3900, |
|
2585 |
+ "backend": "metal", |
|
2586 |
+ "threads": 0, |
|
2587 |
+ "median_s": 0.0002416251227259636, |
|
2588 |
+ "ci_lo": 0.0001499168574810028, |
|
2589 |
+ "ci_hi": 0.0002560419961810112, |
|
2590 |
+ "device_s": 4.958361387252808e-06, |
|
2591 |
+ "elements_per_s": 16140705.718018986, |
|
2592 |
+ "reps": 5, |
|
2593 |
+ "precision": "fp32", |
|
2594 |
+ "peak_rss_mb": 2962.440192 |
|
2595 |
+ }, |
|
2596 |
+ { |
|
2597 |
+ "kernel": "rolling_sumsq", |
|
2598 |
+ "S": 1, |
|
2599 |
+ "n": 39000, |
|
2600 |
+ "elements": 39000, |
|
2601 |
+ "backend": "cpu", |
|
2602 |
+ "threads": 1, |
|
2603 |
+ "median_s": 6.93327747285366e-05, |
|
2604 |
+ "ci_lo": 6.899982690811157e-05, |
|
2605 |
+ "ci_hi": 7.020775228738785e-05, |
|
2606 |
+ "device_s": 0.0, |
|
2607 |
+ "elements_per_s": 562504531.9864868, |
|
2608 |
+ "reps": 5, |
|
2609 |
+ "precision": "fp64", |
|
2610 |
+ "peak_rss_mb": 3355.8528 |
|
2611 |
+ }, |
|
2612 |
+ { |
|
2613 |
+ "kernel": "rolling_sumsq", |
|
2614 |
+ "S": 1, |
|
2615 |
+ "n": 39000, |
|
2616 |
+ "elements": 39000, |
|
2617 |
+ "backend": "cpu", |
|
2618 |
+ "threads": 18, |
|
2619 |
+ "median_s": 7.025012746453285e-05, |
|
2620 |
+ "ci_lo": 6.979191675782204e-05, |
|
2621 |
+ "ci_hi": 8.300039917230606e-05, |
|
2622 |
+ "device_s": 0.0, |
|
2623 |
+ "elements_per_s": 555159135.0448426, |
|
2624 |
+ "reps": 5, |
|
2625 |
+ "precision": "fp64", |
|
2626 |
+ "peak_rss_mb": 781.1072 |
|
2627 |
+ }, |
|
2628 |
+ { |
|
2629 |
+ "kernel": "rolling_sumsq", |
|
2630 |
+ "S": 1, |
|
2631 |
+ "n": 39000, |
|
2632 |
+ "elements": 39000, |
|
2633 |
+ "backend": "metal", |
|
2634 |
+ "threads": 0, |
|
2635 |
+ "median_s": 0.00016458332538604736, |
|
2636 |
+ "ci_lo": 0.00015858327969908714, |
|
2637 |
+ "ci_hi": 0.00017341692000627518, |
|
2638 |
+ "device_s": 1.9583385437726974e-05, |
|
2639 |
+ "elements_per_s": 236962036.75871435, |
|
2640 |
+ "reps": 5, |
|
2641 |
+ "precision": "fp32", |
|
2642 |
+ "peak_rss_mb": 2962.440192 |
|
2643 |
+ }, |
|
2644 |
+ { |
|
2645 |
+ "kernel": "rolling_sumsq", |
|
2646 |
+ "S": 1, |
|
2647 |
+ "n": 390000, |
|
2648 |
+ "elements": 390000, |
|
2649 |
+ "backend": "cpu", |
|
2650 |
+ "threads": 1, |
|
2651 |
+ "median_s": 0.0006914162077009678, |
|
2652 |
+ "ci_lo": 0.000687750056385994, |
|
2653 |
+ "ci_hi": 0.0007007499225437641, |
|
2654 |
+ "device_s": 0.0, |
|
2655 |
+ "elements_per_s": 564059672.9671572, |
|
2656 |
+ "reps": 5, |
|
2657 |
+ "precision": "fp64", |
|
2658 |
+ "peak_rss_mb": 3432.742912 |
|
2659 |
+ }, |
|
2660 |
+ { |
|
2661 |
+ "kernel": "rolling_sumsq", |
|
2662 |
+ "S": 1, |
|
2663 |
+ "n": 390000, |
|
2664 |
+ "elements": 390000, |
|
2665 |
+ "backend": "cpu", |
|
2666 |
+ "threads": 18, |
|
2667 |
+ "median_s": 0.000718916766345501, |
|
2668 |
+ "ci_lo": 0.0007105418480932713, |
|
2669 |
+ "ci_hi": 0.0012256246991455555, |
|
2670 |
+ "device_s": 0.0, |
|
2671 |
+ "elements_per_s": 542482827.2993312, |
|
2672 |
+ "reps": 5, |
|
2673 |
+ "precision": "fp64", |
|
2674 |
+ "peak_rss_mb": 2962.440192 |
|
2675 |
+ }, |
|
2676 |
+ { |
|
2677 |
+ "kernel": "rolling_sumsq", |
|
2678 |
+ "S": 1, |
|
2679 |
+ "n": 390000, |
|
2680 |
+ "elements": 390000, |
|
2681 |
+ "backend": "metal", |
|
2682 |
+ "threads": 0, |
|
2683 |
+ "median_s": 0.0007903752848505974, |
|
2684 |
+ "ci_lo": 0.000574291218072176, |
|
2685 |
+ "ci_hi": 0.0009351670742034912, |
|
2686 |
+ "device_s": 6.225006654858589e-05, |
|
2687 |
+ "elements_per_s": 493436481.97921664, |
|
2688 |
+ "reps": 5, |
|
2689 |
+ "precision": "fp32", |
|
2690 |
+ "peak_rss_mb": 2962.440192 |
|
2691 |
+ }, |
|
2692 |
+ { |
|
2693 |
+ "kernel": "rolling_sumsq", |
|
2694 |
+ "S": 10, |
|
2695 |
+ "n": 390, |
|
2696 |
+ "elements": 3900, |
|
2697 |
+ "backend": "cpu", |
|
2698 |
+ "threads": 1, |
|
2699 |
+ "median_s": 7.1660615503787994e-06, |
|
2700 |
+ "ci_lo": 7.000286132097244e-06, |
|
2701 |
+ "ci_hi": 7.166992872953415e-06, |
|
2702 |
+ "device_s": 0.0, |
|
2703 |
+ "elements_per_s": 544231998.6483852, |
|
2704 |
+ "reps": 5, |
|
2705 |
+ "precision": "fp64", |
|
2706 |
+ "peak_rss_mb": 3432.742912 |
|
2707 |
+ }, |
|
2708 |
+ { |
|
2709 |
+ "kernel": "rolling_sumsq", |
|
2710 |
+ "S": 10, |
|
2711 |
+ "n": 390, |
|
2712 |
+ "elements": 3900, |
|
2713 |
+ "backend": "cpu", |
|
2714 |
+ "threads": 18, |
|
2715 |
+ "median_s": 1.800013706088066e-05, |
|
2716 |
+ "ci_lo": 1.5374738723039627e-05, |
|
2717 |
+ "ci_hi": 2.3958273231983185e-05, |
|
2718 |
+ "device_s": 0.0, |
|
2719 |
+ "elements_per_s": 216665016.87233216, |
|
2720 |
+ "reps": 5, |
|
2721 |
+ "precision": "fp64", |
|
2722 |
+ "peak_rss_mb": 3432.742912 |
|
2723 |
+ }, |
|
2724 |
+ { |
|
2725 |
+ "kernel": "rolling_sumsq", |
|
2726 |
+ "S": 10, |
|
2727 |
+ "n": 390, |
|
2728 |
+ "elements": 3900, |
|
2729 |
+ "backend": "metal", |
|
2730 |
+ "threads": 0, |
|
2731 |
+ "median_s": 0.0002032076008617878, |
|
2732 |
+ "ci_lo": 0.00014958297833800316, |
|
2733 |
+ "ci_hi": 0.0006746253930032253, |
|
2734 |
+ "device_s": 1.4499993994832039e-05, |
|
2735 |
+ "elements_per_s": 19192195.486095995, |
|
2736 |
+ "reps": 5, |
|
2737 |
+ "precision": "fp32", |
|
2738 |
+ "peak_rss_mb": 17.170432 |
|
2739 |
+ }, |
|
2740 |
+ { |
|
2741 |
+ "kernel": "rolling_sumsq", |
|
2742 |
+ "S": 10, |
|
2743 |
+ "n": 3900, |
|
2744 |
+ "elements": 39000, |
|
2745 |
+ "backend": "cpu", |
|
2746 |
+ "threads": 1, |
|
2747 |
+ "median_s": 6.929086521267891e-05, |
|
2748 |
+ "ci_lo": 6.908271461725235e-05, |
|
2749 |
+ "ci_hi": 6.937514990568161e-05, |
|
2750 |
+ "device_s": 0.0, |
|
2751 |
+ "elements_per_s": 562844754.2153615, |
|
2752 |
+ "reps": 5, |
|
2753 |
+ "precision": "fp64", |
|
2754 |
+ "peak_rss_mb": 2962.440192 |
|
2755 |
+ }, |
|
2756 |
+ { |
|
2757 |
+ "kernel": "rolling_sumsq", |
|
2758 |
+ "S": 10, |
|
2759 |
+ "n": 3900, |
|
2760 |
+ "elements": 39000, |
|
2761 |
+ "backend": "cpu", |
|
2762 |
+ "threads": 18, |
|
2763 |
+ "median_s": 4.487484693527222e-05, |
|
2764 |
+ "ci_lo": 3.987457603216171e-05, |
|
2765 |
+ "ci_hi": 5.0374772399663925e-05, |
|
2766 |
+ "device_s": 0.0, |
|
2767 |
+ "elements_per_s": 869083744.313465, |
|
2768 |
+ "reps": 5, |
|
2769 |
+ "precision": "fp64", |
|
2770 |
+ "peak_rss_mb": 2962.440192 |
|
2771 |
+ }, |
|
2772 |
+ { |
|
2773 |
+ "kernel": "rolling_sumsq", |
|
2774 |
+ "S": 10, |
|
2775 |
+ "n": 3900, |
|
2776 |
+ "elements": 39000, |
|
2777 |
+ "backend": "metal", |
|
2778 |
+ "threads": 0, |
|
2779 |
+ "median_s": 0.00016070762649178505, |
|
2780 |
+ "ci_lo": 0.00014404207468032837, |
|
2781 |
+ "ci_hi": 0.00017450004816055298, |
|
2782 |
+ "device_s": 1.9625062122941017e-05, |
|
2783 |
+ "elements_per_s": 242676722.01601195, |
|
2784 |
+ "reps": 5, |
|
2785 |
+ "precision": "fp32", |
|
2786 |
+ "peak_rss_mb": 2962.440192 |
|
2787 |
+ }, |
|
2788 |
+ { |
|
2789 |
+ "kernel": "rolling_sumsq", |
|
2790 |
+ "S": 10, |
|
2791 |
+ "n": 39000, |
|
2792 |
+ "elements": 390000, |
|
2793 |
+ "backend": "cpu", |
|
2794 |
+ "threads": 1, |
|
2795 |
+ "median_s": 0.0007095411419868469, |
|
2796 |
+ "ci_lo": 0.0007064170204102993, |
|
2797 |
+ "ci_hi": 0.000905290711671114, |
|
2798 |
+ "device_s": 0.0, |
|
2799 |
+ "elements_per_s": 549651002.4886332, |
|
2800 |
+ "reps": 5, |
|
2801 |
+ "precision": "fp64", |
|
2802 |
+ "peak_rss_mb": 3432.742912 |
|
2803 |
+ }, |
|
2804 |
+ { |
|
2805 |
+ "kernel": "rolling_sumsq", |
|
2806 |
+ "S": 10, |
|
2807 |
+ "n": 39000, |
|
2808 |
+ "elements": 390000, |
|
2809 |
+ "backend": "cpu", |
|
2810 |
+ "threads": 18, |
|
2811 |
+ "median_s": 0.000132707878947258, |
|
2812 |
+ "ci_lo": 0.00013195769861340523, |
|
2813 |
+ "ci_hi": 0.00013837497681379318, |
|
2814 |
+ "device_s": 0.0, |
|
2815 |
+ "elements_per_s": 2938785572.4451556, |
|
2816 |
+ "reps": 5, |
|
2817 |
+ "precision": "fp64", |
|
2818 |
+ "peak_rss_mb": 3358.88384 |
|
2819 |
+ }, |
|
2820 |
+ { |
|
2821 |
+ "kernel": "rolling_sumsq", |
|
2822 |
+ "S": 10, |
|
2823 |
+ "n": 39000, |
|
2824 |
+ "elements": 390000, |
|
2825 |
+ "backend": "metal", |
|
2826 |
+ "threads": 0, |
|
2827 |
+ "median_s": 0.0007357923313975334, |
|
2828 |
+ "ci_lo": 0.0007097921334207058, |
|
2829 |
+ "ci_hi": 0.0007738331332802773, |
|
2830 |
+ "device_s": 9.062490426003933e-05, |
|
2831 |
+ "elements_per_s": 530040859.8432253, |
|
2832 |
+ "reps": 5, |
|
2833 |
+ "precision": "fp32", |
|
2834 |
+ "peak_rss_mb": 3431.46496 |
|
2835 |
+ }, |
|
2836 |
+ { |
|
2837 |
+ "kernel": "rolling_sumsq", |
|
2838 |
+ "S": 10, |
|
2839 |
+ "n": 390000, |
|
2840 |
+ "elements": 3900000, |
|
2841 |
+ "backend": "cpu", |
|
2842 |
+ "threads": 1, |
|
2843 |
+ "median_s": 0.006913874763995409, |
|
2844 |
+ "ci_lo": 0.00687399972230196, |
|
2845 |
+ "ci_hi": 0.006919416133314371, |
|
2846 |
+ "device_s": 0.0, |
|
2847 |
+ "elements_per_s": 564083113.033748, |
|
2848 |
+ "reps": 5, |
|
2849 |
+ "precision": "fp64", |
|
2850 |
+ "peak_rss_mb": 3368.943616 |
|
2851 |
+ }, |
|
2852 |
+ { |
|
2853 |
+ "kernel": "rolling_sumsq", |
|
2854 |
+ "S": 10, |
|
2855 |
+ "n": 390000, |
|
2856 |
+ "elements": 3900000, |
|
2857 |
+ "backend": "cpu", |
|
2858 |
+ "threads": 18, |
|
2859 |
+ "median_s": 0.0017658751457929611, |
|
2860 |
+ "ci_lo": 0.0013864999637007713, |
|
2861 |
+ "ci_hi": 0.0021367911249399185, |
|
2862 |
+ "device_s": 0.0, |
|
2863 |
+ "elements_per_s": 2208536662.0009346, |
|
2864 |
+ "reps": 5, |
|
2865 |
+ "precision": "fp64", |
|
2866 |
+ "peak_rss_mb": 2962.440192 |
|
2867 |
+ }, |
|
2868 |
+ { |
|
2869 |
+ "kernel": "rolling_sumsq", |
|
2870 |
+ "S": 10, |
|
2871 |
+ "n": 390000, |
|
2872 |
+ "elements": 3900000, |
|
2873 |
+ "backend": "metal", |
|
2874 |
+ "threads": 0, |
|
2875 |
+ "median_s": 0.002544207964092493, |
|
2876 |
+ "ci_lo": 0.0024965000338852406, |
|
2877 |
+ "ci_hi": 0.0026084999553859234, |
|
2878 |
+ "device_s": 0.00076149997767061, |
|
2879 |
+ "elements_per_s": 1532893558.6407974, |
|
2880 |
+ "reps": 5, |
|
2881 |
+ "precision": "fp32", |
|
2882 |
+ "peak_rss_mb": 3253.567488 |
|
2883 |
+ }, |
|
2884 |
+ { |
|
2885 |
+ "kernel": "rolling_sumsq", |
|
2886 |
+ "S": 100, |
|
2887 |
+ "n": 390, |
|
2888 |
+ "elements": 39000, |
|
2889 |
+ "backend": "cpu", |
|
2890 |
+ "threads": 1, |
|
2891 |
+ "median_s": 6.991717964410782e-05, |
|
2892 |
+ "ci_lo": 6.962474435567856e-05, |
|
2893 |
+ "ci_hi": 7.033301517367363e-05, |
|
2894 |
+ "device_s": 0.0, |
|
2895 |
+ "elements_per_s": 557802820.4014759, |
|
2896 |
+ "reps": 5, |
|
2897 |
+ "precision": "fp64", |
|
2898 |
+ "peak_rss_mb": 3368.943616 |
|
2899 |
+ }, |
|
2900 |
+ { |
|
2901 |
+ "kernel": "rolling_sumsq", |
|
2902 |
+ "S": 100, |
|
2903 |
+ "n": 390, |
|
2904 |
+ "elements": 39000, |
|
2905 |
+ "backend": "cpu", |
|
2906 |
+ "threads": 18, |
|
2907 |
+ "median_s": 0.00017983326688408852, |
|
2908 |
+ "ci_lo": 0.00014462508261203766, |
|
2909 |
+ "ci_hi": 0.0002232920378446579, |
|
2910 |
+ "device_s": 0.0, |
|
2911 |
+ "elements_per_s": 216867550.01307648, |
|
2912 |
+ "reps": 5, |
|
2913 |
+ "precision": "fp64", |
|
2914 |
+ "peak_rss_mb": 2962.440192 |
|
2915 |
+ }, |
|
2916 |
+ { |
|
2917 |
+ "kernel": "rolling_sumsq", |
|
2918 |
+ "S": 100, |
|
2919 |
+ "n": 390, |
|
2920 |
+ "elements": 39000, |
|
2921 |
+ "backend": "metal", |
|
2922 |
+ "threads": 0, |
|
2923 |
+ "median_s": 0.0002676667645573616, |
|
2924 |
+ "ci_lo": 0.00017749983817338943, |
|
2925 |
+ "ci_hi": 0.0007679169066250324, |
|
2926 |
+ "device_s": 9.541632607579231e-06, |
|
2927 |
+ "elements_per_s": 145703558.1705259, |
|
2928 |
+ "reps": 5, |
|
2929 |
+ "precision": "fp32", |
|
2930 |
+ "peak_rss_mb": 2962.440192 |
|
2931 |
+ }, |
|
2932 |
+ { |
|
2933 |
+ "kernel": "rolling_sumsq", |
|
2934 |
+ "S": 100, |
|
2935 |
+ "n": 3900, |
|
2936 |
+ "elements": 390000, |
|
2937 |
+ "backend": "cpu", |
|
2938 |
+ "threads": 1, |
|
2939 |
+ "median_s": 0.000806666910648346, |
|
2940 |
+ "ci_lo": 0.0007096659392118454, |
|
2941 |
+ "ci_hi": 0.0011533750221133232, |
|
2942 |
+ "device_s": 0.0, |
|
2943 |
+ "elements_per_s": 483470928.151179, |
|
2944 |
+ "reps": 5, |
|
2945 |
+ "precision": "fp64", |
|
2946 |
+ "peak_rss_mb": 2962.440192 |
|
2947 |
+ }, |
|
2948 |
+ { |
|
2949 |
+ "kernel": "rolling_sumsq", |
|
2950 |
+ "S": 100, |
|
2951 |
+ "n": 3900, |
|
2952 |
+ "elements": 390000, |
|
2953 |
+ "backend": "cpu", |
|
2954 |
+ "threads": 18, |
|
2955 |
+ "median_s": 0.00020312517881393433, |
|
2956 |
+ "ci_lo": 0.00012504169717431068, |
|
2957 |
+ "ci_hi": 0.0002259998582303524, |
|
2958 |
+ "device_s": 0.0, |
|
2959 |
+ "elements_per_s": 1919998309.797161, |
|
2960 |
+ "reps": 5, |
|
2961 |
+ "precision": "fp64", |
|
2962 |
+ "peak_rss_mb": 781.484032 |
|
2963 |
+ }, |
|
2964 |
+ { |
|
2965 |
+ "kernel": "rolling_sumsq", |
|
2966 |
+ "S": 100, |
|
2967 |
+ "n": 3900, |
|
2968 |
+ "elements": 390000, |
|
2969 |
+ "backend": "metal", |
|
2970 |
+ "threads": 0, |
|
2971 |
+ "median_s": 0.0006820829585194588, |
|
2972 |
+ "ci_lo": 0.0003593750298023224, |
|
2973 |
+ "ci_hi": 0.0008333330042660236, |
|
2974 |
+ "device_s": 9.058334399014711e-05, |
|
2975 |
+ "elements_per_s": 571777956.2277012, |
|
2976 |
+ "reps": 5, |
|
2977 |
+ "precision": "fp32", |
|
2978 |
+ "peak_rss_mb": 3431.530496 |
|
2979 |
+ }, |
|
2980 |
+ { |
|
2981 |
+ "kernel": "rolling_sumsq", |
|
2982 |
+ "S": 100, |
|
2983 |
+ "n": 39000, |
|
2984 |
+ "elements": 3900000, |
|
2985 |
+ "backend": "cpu", |
|
2986 |
+ "threads": 1, |
|
2987 |
+ "median_s": 0.007338124793022871, |
|
2988 |
+ "ci_lo": 0.007089000195264816, |
|
2989 |
+ "ci_hi": 0.008123625069856644, |
|
2990 |
+ "device_s": 0.0, |
|
2991 |
+ "elements_per_s": 531470928.88201374, |
|
2992 |
+ "reps": 5, |
|
2993 |
+ "precision": "fp64", |
|
2994 |
+ "peak_rss_mb": 2962.440192 |
|
2995 |
+ }, |
|
2996 |
+ { |
|
2997 |
+ "kernel": "rolling_sumsq", |
|
2998 |
+ "S": 100, |
|
2999 |
+ "n": 39000, |
|
3000 |
+ "elements": 3900000, |
|
3001 |
+ "backend": "cpu", |
|
3002 |
+ "threads": 18, |
|
3003 |
+ "median_s": 0.0010874588042497635, |
|
3004 |
+ "ci_lo": 0.0009993752464652061, |
|
3005 |
+ "ci_hi": 0.0013045421801507473, |
|
3006 |
+ "device_s": 0.0, |
|
3007 |
+ "elements_per_s": 3586342751.3381577, |
|
3008 |
+ "reps": 5, |
|
3009 |
+ "precision": "fp64", |
|
3010 |
+ "peak_rss_mb": 2962.440192 |
|
3011 |
+ }, |
|
3012 |
+ { |
|
3013 |
+ "kernel": "rolling_sumsq", |
|
3014 |
+ "S": 100, |
|
3015 |
+ "n": 39000, |
|
3016 |
+ "elements": 3900000, |
|
3017 |
+ "backend": "metal", |
|
3018 |
+ "threads": 0, |
|
3019 |
+ "median_s": 0.002226833254098892, |
|
3020 |
+ "ci_lo": 0.0021508331410586834, |
|
3021 |
+ "ci_hi": 0.002632542047649622, |
|
3022 |
+ "device_s": 0.00043350004125386477, |
|
3023 |
+ "elements_per_s": 1751365978.0413911, |
|
3024 |
+ "reps": 5, |
|
3025 |
+ "precision": "fp32", |
|
3026 |
+ "peak_rss_mb": 3431.87456 |
|
3027 |
+ }, |
|
3028 |
+ { |
|
3029 |
+ "kernel": "rolling_sumsq", |
|
3030 |
+ "S": 100, |
|
3031 |
+ "n": 390000, |
|
3032 |
+ "elements": 39000000, |
|
3033 |
+ "backend": "cpu", |
|
3034 |
+ "threads": 1, |
|
3035 |
+ "median_s": 0.06962170917540789, |
|
3036 |
+ "ci_lo": 0.06953629199415445, |
|
3037 |
+ "ci_hi": 0.06967033399268985, |
|
3038 |
+ "device_s": 0.0, |
|
3039 |
+ "elements_per_s": 560170103.0025239, |
|
3040 |
+ "reps": 5, |
|
3041 |
+ "precision": "fp64", |
|
3042 |
+ "peak_rss_mb": 3222.339584 |
|
3043 |
+ }, |
|
3044 |
+ { |
|
3045 |
+ "kernel": "rolling_sumsq", |
|
3046 |
+ "S": 100, |
|
3047 |
+ "n": 390000, |
|
3048 |
+ "elements": 39000000, |
|
3049 |
+ "backend": "cpu", |
|
3050 |
+ "threads": 18, |
|
3051 |
+ "median_s": 0.009413291700184345, |
|
3052 |
+ "ci_lo": 0.009286124724894762, |
|
3053 |
+ "ci_hi": 0.010024874936789274, |
|
3054 |
+ "device_s": 0.0, |
|
3055 |
+ "elements_per_s": 4143077814.027185, |
|
3056 |
+ "reps": 5, |
|
3057 |
+ "precision": "fp64", |
|
3058 |
+ "peak_rss_mb": 3355.8528 |
|
3059 |
+ }, |
|
3060 |
+ { |
|
3061 |
+ "kernel": "rolling_sumsq", |
|
3062 |
+ "S": 100, |
|
3063 |
+ "n": 390000, |
|
3064 |
+ "elements": 39000000, |
|
3065 |
+ "backend": "metal", |
|
3066 |
+ "threads": 0, |
|
3067 |
+ "median_s": 0.014852333813905716, |
|
3068 |
+ "ci_lo": 0.014340042136609554, |
|
3069 |
+ "ci_hi": 0.01528970804065466, |
|
3070 |
+ "device_s": 0.0023322500055655837, |
|
3071 |
+ "elements_per_s": 2625849949.823083, |
|
3072 |
+ "reps": 5, |
|
3073 |
+ "precision": "fp32", |
|
3074 |
+ "peak_rss_mb": 3255.451648 |
|
3075 |
+ }, |
|
3076 |
+ { |
|
3077 |
+ "kernel": "rolling_sumsq", |
|
3078 |
+ "S": 1000, |
|
3079 |
+ "n": 390, |
|
3080 |
+ "elements": 390000, |
|
3081 |
+ "backend": "cpu", |
|
3082 |
+ "threads": 1, |
|
3083 |
+ "median_s": 0.0007188748568296432, |
|
3084 |
+ "ci_lo": 0.0007158750668168068, |
|
3085 |
+ "ci_hi": 0.0007281671278178692, |
|
3086 |
+ "device_s": 0.0, |
|
3087 |
+ "elements_per_s": 542514453.3778304, |
|
3088 |
+ "reps": 5, |
|
3089 |
+ "precision": "fp64", |
|
3090 |
+ "peak_rss_mb": 3431.563264 |
|
3091 |
+ }, |
|
3092 |
+ { |
|
3093 |
+ "kernel": "rolling_sumsq", |
|
3094 |
+ "S": 1000, |
|
3095 |
+ "n": 390, |
|
3096 |
+ "elements": 390000, |
|
3097 |
+ "backend": "cpu", |
|
3098 |
+ "threads": 18, |
|
3099 |
+ "median_s": 0.0002710837870836258, |
|
3100 |
+ "ci_lo": 0.0002649589441716671, |
|
3101 |
+ "ci_hi": 0.00028412509709596634, |
|
3102 |
+ "device_s": 0.0, |
|
3103 |
+ "elements_per_s": 1438669586.977882, |
|
3104 |
+ "reps": 5, |
|
3105 |
+ "precision": "fp64", |
|
3106 |
+ "peak_rss_mb": 3431.858176 |
|
3107 |
+ }, |
|
3108 |
+ { |
|
3109 |
+ "kernel": "rolling_sumsq", |
|
3110 |
+ "S": 1000, |
|
3111 |
+ "n": 390, |
|
3112 |
+ "elements": 390000, |
|
3113 |
+ "backend": "metal", |
|
3114 |
+ "threads": 0, |
|
3115 |
+ "median_s": 0.0009075421839952469, |
|
3116 |
+ "ci_lo": 0.000882917083799839, |
|
3117 |
+ "ci_hi": 0.000995416659861803, |
|
3118 |
+ "device_s": 2.3708329536020756e-05, |
|
3119 |
+ "elements_per_s": 429732090.5603684, |
|
3120 |
+ "reps": 5, |
|
3121 |
+ "precision": "fp32", |
|
3122 |
+ "peak_rss_mb": 2962.440192 |
|
3123 |
+ }, |
|
3124 |
+ { |
|
3125 |
+ "kernel": "rolling_sumsq", |
|
3126 |
+ "S": 1000, |
|
3127 |
+ "n": 3900, |
|
3128 |
+ "elements": 3900000, |
|
3129 |
+ "backend": "cpu", |
|
3130 |
+ "threads": 1, |
|
3131 |
+ "median_s": 0.00695441709831357, |
|
3132 |
+ "ci_lo": 0.006937959231436253, |
|
3133 |
+ "ci_hi": 0.006972583010792732, |
|
3134 |
+ "device_s": 0.0, |
|
3135 |
+ "elements_per_s": 560794664.0050883, |
|
3136 |
+ "reps": 5, |
|
3137 |
+ "precision": "fp64", |
|
3138 |
+ "peak_rss_mb": 3432.742912 |
|
3139 |
+ }, |
|
3140 |
+ { |
|
3141 |
+ "kernel": "rolling_sumsq", |
|
3142 |
+ "S": 1000, |
|
3143 |
+ "n": 3900, |
|
3144 |
+ "elements": 3900000, |
|
3145 |
+ "backend": "cpu", |
|
3146 |
+ "threads": 18, |
|
3147 |
+ "median_s": 0.0010273326188325882, |
|
3148 |
+ "ci_lo": 0.0008542081341147423, |
|
3149 |
+ "ci_hi": 0.0010719997808337212, |
|
3150 |
+ "device_s": 0.0, |
|
3151 |
+ "elements_per_s": 3796238850.5017724, |
|
3152 |
+ "reps": 5, |
|
3153 |
+ "precision": "fp64", |
|
3154 |
+ "peak_rss_mb": 556.466176 |
|
3155 |
+ }, |
|
3156 |
+ { |
|
3157 |
+ "kernel": "rolling_sumsq", |
|
3158 |
+ "S": 1000, |
|
3159 |
+ "n": 3900, |
|
3160 |
+ "elements": 3900000, |
|
3161 |
+ "backend": "metal", |
|
3162 |
+ "threads": 0, |
|
3163 |
+ "median_s": 0.002144791651517153, |
|
3164 |
+ "ci_lo": 0.0021287081763148308, |
|
3165 |
+ "ci_hi": 0.0034982911311089993, |
|
3166 |
+ "device_s": 0.0007578750373795629, |
|
3167 |
+ "elements_per_s": 1818358439.264379, |
|
3168 |
+ "reps": 5, |
|
3169 |
+ "precision": "fp32", |
|
3170 |
+ "peak_rss_mb": 3431.497728 |
|
3171 |
+ }, |
|
3172 |
+ { |
|
3173 |
+ "kernel": "rolling_sumsq", |
|
3174 |
+ "S": 1000, |
|
3175 |
+ "n": 39000, |
|
3176 |
+ "elements": 39000000, |
|
3177 |
+ "backend": "cpu", |
|
3178 |
+ "threads": 1, |
|
3179 |
+ "median_s": 0.07026320835575461, |
|
3180 |
+ "ci_lo": 0.0701742498204112, |
|
3181 |
+ "ci_hi": 0.07056499971076846, |
|
3182 |
+ "device_s": 0.0, |
|
3183 |
+ "elements_per_s": 555055781.1498778, |
|
3184 |
+ "reps": 5, |
|
3185 |
+ "precision": "fp64", |
|
3186 |
+ "peak_rss_mb": 2962.440192 |
|
3187 |
+ }, |
|
3188 |
+ { |
|
3189 |
+ "kernel": "rolling_sumsq", |
|
3190 |
+ "S": 1000, |
|
3191 |
+ "n": 39000, |
|
3192 |
+ "elements": 39000000, |
|
3193 |
+ "backend": "cpu", |
|
3194 |
+ "threads": 18, |
|
3195 |
+ "median_s": 0.00831229193136096, |
|
3196 |
+ "ci_lo": 0.007511000148952007, |
|
3197 |
+ "ci_hi": 0.008729041088372469, |
|
3198 |
+ "device_s": 0.0, |
|
3199 |
+ "elements_per_s": 4691846764.05062, |
|
3200 |
+ "reps": 5, |
|
3201 |
+ "precision": "fp64", |
|
3202 |
+ "peak_rss_mb": 3368.894464 |
|
3203 |
+ }, |
|
3204 |
+ { |
|
3205 |
+ "kernel": "rolling_sumsq", |
|
3206 |
+ "S": 1000, |
|
3207 |
+ "n": 39000, |
|
3208 |
+ "elements": 39000000, |
|
3209 |
+ "backend": "metal", |
|
3210 |
+ "threads": 0, |
|
3211 |
+ "median_s": 0.014728832989931107, |
|
3212 |
+ "ci_lo": 0.014530166983604431, |
|
3213 |
+ "ci_hi": 0.01593674998730421, |
|
3214 |
+ "device_s": 0.002570083364844322, |
|
3215 |
+ "elements_per_s": 2647867623.094178, |
|
3216 |
+ "reps": 5, |
|
3217 |
+ "precision": "fp32", |
|
3218 |
+ "peak_rss_mb": 3368.894464 |
|
3219 |
+ }, |
|
3220 |
+ { |
|
3221 |
+ "kernel": "rolling_sumsq", |
|
3222 |
+ "S": 10000, |
|
3223 |
+ "n": 390, |
|
3224 |
+ "elements": 3900000, |
|
3225 |
+ "backend": "cpu", |
|
3226 |
+ "threads": 1, |
|
3227 |
+ "median_s": 0.007047916762530804, |
|
3228 |
+ "ci_lo": 0.007002290803939104, |
|
3229 |
+ "ci_hi": 0.007088833022862673, |
|
3230 |
+ "device_s": 0.0, |
|
3231 |
+ "elements_per_s": 553355002.8192397, |
|
3232 |
+ "reps": 5, |
|
3233 |
+ "precision": "fp64", |
|
3234 |
+ "peak_rss_mb": 3431.858176 |
|
3235 |
+ }, |
|
3236 |
+ { |
|
3237 |
+ "kernel": "rolling_sumsq", |
|
3238 |
+ "S": 10000, |
|
3239 |
+ "n": 390, |
|
3240 |
+ "elements": 3900000, |
|
3241 |
+ "backend": "cpu", |
|
3242 |
+ "threads": 18, |
|
3243 |
+ "median_s": 0.00107216602191329, |
|
3244 |
+ "ci_lo": 0.001034500077366829, |
|
3245 |
+ "ci_hi": 0.0011164997704327106, |
|
3246 |
+ "device_s": 0.0, |
|
3247 |
+ "elements_per_s": 3637496358.111046, |
|
3248 |
+ "reps": 5, |
|
3249 |
+ "precision": "fp64", |
|
3250 |
+ "peak_rss_mb": 2962.440192 |
|
3251 |
+ }, |
|
3252 |
+ { |
|
3253 |
+ "kernel": "rolling_sumsq", |
|
3254 |
+ "S": 10000, |
|
3255 |
+ "n": 390, |
|
3256 |
+ "elements": 3900000, |
|
3257 |
+ "backend": "metal", |
|
3258 |
+ "threads": 0, |
|
3259 |
+ "median_s": 0.0021627498790621758, |
|
3260 |
+ "ci_lo": 0.002053916919976473, |
|
3261 |
+ "ci_hi": 0.0022570830769836903, |
|
3262 |
+ "device_s": 0.0002617916325107217, |
|
3263 |
+ "elements_per_s": 1803259839.5941842, |
|
3264 |
+ "reps": 5, |
|
3265 |
+ "precision": "fp32", |
|
3266 |
+ "peak_rss_mb": 3431.858176 |
|
3267 |
+ }, |
|
3268 |
+ { |
|
3269 |
+ "kernel": "rolling_sumsq", |
|
3270 |
+ "S": 10000, |
|
3271 |
+ "n": 3900, |
|
3272 |
+ "elements": 39000000, |
|
3273 |
+ "backend": "cpu", |
|
3274 |
+ "threads": 1, |
|
3275 |
+ "median_s": 0.06922604190185666, |
|
3276 |
+ "ci_lo": 0.06907229218631983, |
|
3277 |
+ "ci_hi": 0.06939475005492568, |
|
3278 |
+ "device_s": 0.0, |
|
3279 |
+ "elements_per_s": 563371802.4105898, |
|
3280 |
+ "reps": 5, |
|
3281 |
+ "precision": "fp64", |
|
3282 |
+ "peak_rss_mb": 3360.096256 |
|
3283 |
+ }, |
|
3284 |
+ { |
|
3285 |
+ "kernel": "rolling_sumsq", |
|
3286 |
+ "S": 10000, |
|
3287 |
+ "n": 3900, |
|
3288 |
+ "elements": 39000000, |
|
3289 |
+ "backend": "cpu", |
|
3290 |
+ "threads": 18, |
|
3291 |
+ "median_s": 0.00654304213821888, |
|
3292 |
+ "ci_lo": 0.006384790875017643, |
|
3293 |
+ "ci_hi": 0.00675958301872015, |
|
3294 |
+ "device_s": 0.0, |
|
3295 |
+ "elements_per_s": 5960530159.540807, |
|
3296 |
+ "reps": 5, |
|
3297 |
+ "precision": "fp64", |
|
3298 |
+ "peak_rss_mb": 3432.742912 |
|
3299 |
+ }, |
|
3300 |
+ { |
|
3301 |
+ "kernel": "rolling_sumsq", |
|
3302 |
+ "S": 10000, |
|
3303 |
+ "n": 3900, |
|
3304 |
+ "elements": 39000000, |
|
3305 |
+ "backend": "metal", |
|
3306 |
+ "threads": 0, |
|
3307 |
+ "median_s": 0.014753291849046946, |
|
3308 |
+ "ci_lo": 0.01457533286884427, |
|
3309 |
+ "ci_hi": 0.01564762508496642, |
|
3310 |
+ "device_s": 0.0025377500569447875, |
|
3311 |
+ "elements_per_s": 2643477835.254739, |
|
3312 |
+ "reps": 5, |
|
3313 |
+ "precision": "fp32", |
|
3314 |
+ "peak_rss_mb": 2962.440192 |
|
3315 |
+ } |
|
3316 |
+ ], |
|
3317 |
+ "metal_summary": [ |
|
3318 |
+ { |
|
3319 |
+ "kernel": "garch_nll_P1", |
|
3320 |
+ "S": 1, |
|
3321 |
+ "n": 390, |
|
3322 |
+ "elements": 390, |
|
3323 |
+ "backend": "metal", |
|
3324 |
+ "threads": 0, |
|
3325 |
+ "median_s": 0.0009180000051856041, |
|
3326 |
+ "ci_lo": 0.00044724997133016586, |
|
3327 |
+ "ci_hi": 0.0009358339011669159, |
|
3328 |
+ "device_s": 0.00032679166179150343, |
|
3329 |
+ "elements_per_s": 424836.59890736995, |
|
3330 |
+ "reps": 5, |
|
3331 |
+ "precision": "fp32", |
|
3332 |
+ "peak_rss_mb": 2962.440192, |
|
3333 |
+ "speedup_vs_cpu_mt": 0.0019062691806288963, |
|
3334 |
+ "speedup_vs_cpu_1t": 0.00195090773515134, |
|
3335 |
+ "cpu_mt_median_s": 1.7499551177024841e-06, |
|
3336 |
+ "cpu_1t_median_s": 1.7909333109855652e-06, |
|
3337 |
+ "metal_wins_vs_mt": false, |
|
3338 |
+ "cpu_wins_vs_mt": true |
|
3339 |
+ }, |
|
3340 |
+ { |
|
3341 |
+ "kernel": "garch_nll_P1", |
|
3342 |
+ "S": 1, |
|
3343 |
+ "n": 3900, |
|
3344 |
+ "elements": 3900, |
|
3345 |
+ "backend": "metal", |
|
3346 |
+ "threads": 0, |
|
3347 |
+ "median_s": 0.001348957885056734, |
|
3348 |
+ "ci_lo": 0.0010095001198351383, |
|
3349 |
+ "ci_hi": 0.0015331669710576534, |
|
3350 |
+ "device_s": 0.0011987084290012717, |
|
3351 |
+ "elements_per_s": 2891120.6518771155, |
|
3352 |
+ "reps": 5, |
|
3353 |
+ "precision": "fp32", |
|
3354 |
+ "peak_rss_mb": 2962.440192, |
|
3355 |
+ "speedup_vs_cpu_mt": 0.012571176081729732, |
|
3356 |
+ "speedup_vs_cpu_1t": 0.01204647092632898, |
|
3357 |
+ "cpu_mt_median_s": 1.695798709988594e-05, |
|
3358 |
+ "cpu_1t_median_s": 1.6250181943178177e-05, |
|
3359 |
+ "metal_wins_vs_mt": false, |
|
3360 |
+ "cpu_wins_vs_mt": true |
|
3361 |
+ }, |
|
3362 |
+ { |
|
3363 |
+ "kernel": "garch_nll_P1", |
|
3364 |
+ "S": 10, |
|
3365 |
+ "n": 390, |
|
3366 |
+ "elements": 3900, |
|
3367 |
+ "backend": "metal", |
|
3368 |
+ "threads": 0, |
|
3369 |
+ "median_s": 0.0003432091325521469, |
|
3370 |
+ "ci_lo": 0.0003193751908838749, |
|
3371 |
+ "ci_hi": 0.0009956671856343746, |
|
3372 |
+ "device_s": 0.00019762502051889896, |
|
3373 |
+ "elements_per_s": 11363333.98531415, |
|
3374 |
+ "reps": 5, |
|
3375 |
+ "precision": "fp32", |
|
3376 |
+ "peak_rss_mb": 2920.169472, |
|
3377 |
+ "speedup_vs_cpu_mt": 0.08534725576498299, |
|
3378 |
+ "speedup_vs_cpu_1t": 0.06385848181092918, |
|
3379 |
+ "cpu_mt_median_s": 2.929195761680603e-05, |
|
3380 |
+ "cpu_1t_median_s": 2.1916814148426056e-05, |
|
3381 |
+ "metal_wins_vs_mt": false, |
|
3382 |
+ "cpu_wins_vs_mt": true |
|
3383 |
+ }, |
|
3384 |
+ { |
|
3385 |
+ "kernel": "garch_nll_P1", |
|
3386 |
+ "S": 10, |
|
3387 |
+ "n": 3900, |
|
3388 |
+ "elements": 39000, |
|
3389 |
+ "backend": "metal", |
|
3390 |
+ "threads": 0, |
|
3391 |
+ "median_s": 0.0014300826005637646, |
|
3392 |
+ "ci_lo": 0.0012115412391722202, |
|
3393 |
+ "ci_hi": 0.0016847080551087856, |
|
3394 |
+ "device_s": 0.0010766249615699053, |
|
3395 |
+ "elements_per_s": 27271152.019208886, |
|
3396 |
+ "reps": 5, |
|
3397 |
+ "precision": "fp32", |
|
3398 |
+ "peak_rss_mb": 3360.11264, |
|
3399 |
+ "speedup_vs_cpu_mt": 0.04836508601699924, |
|
3400 |
+ "speedup_vs_cpu_1t": 0.15071999124737592, |
|
3401 |
+ "cpu_mt_median_s": 6.916606798768044e-05, |
|
3402 |
+ "cpu_1t_median_s": 0.0002155420370399952, |
|
3403 |
+ "metal_wins_vs_mt": false, |
|
3404 |
+ "cpu_wins_vs_mt": true |
|
3405 |
+ }, |
|
3406 |
+ { |
|
3407 |
+ "kernel": "garch_nll_P1", |
|
3408 |
+ "S": 100, |
|
3409 |
+ "n": 390, |
|
3410 |
+ "elements": 39000, |
|
3411 |
+ "backend": "metal", |
|
3412 |
+ "threads": 0, |
|
3413 |
+ "median_s": 0.0006238752976059914, |
|
3414 |
+ "ci_lo": 0.0006115422584116459, |
|
3415 |
+ "ci_hi": 0.0006384579464793205, |
|
3416 |
+ "device_s": 0.0004310833755880594, |
|
3417 |
+ "elements_per_s": 62512492.720348835, |
|
3418 |
+ "reps": 5, |
|
3419 |
+ "precision": "fp32", |
|
3420 |
+ "peak_rss_mb": 3355.901952, |
|
3421 |
+ "speedup_vs_cpu_mt": 0.2583317036906555, |
|
3422 |
+ "speedup_vs_cpu_1t": 0.30722023762429446, |
|
3423 |
+ "cpu_mt_median_s": 0.00016116676852107048, |
|
3424 |
+ "cpu_1t_median_s": 0.0001916671171784401, |
|
3425 |
+ "metal_wins_vs_mt": false, |
|
3426 |
+ "cpu_wins_vs_mt": true |
|
3427 |
+ }, |
|
3428 |
+ { |
|
3429 |
+ "kernel": "garch_nll_P1", |
|
3430 |
+ "S": 100, |
|
3431 |
+ "n": 3900, |
|
3432 |
+ "elements": 390000, |
|
3433 |
+ "backend": "metal", |
|
3434 |
+ "threads": 0, |
|
3435 |
+ "median_s": 0.0016493331640958786, |
|
3436 |
+ "ci_lo": 0.0015722080133855343, |
|
3437 |
+ "ci_hi": 0.004429208114743233, |
|
3438 |
+ "device_s": 0.0009533748961985111, |
|
3439 |
+ "elements_per_s": 236459199.68740082, |
|
3440 |
+ "reps": 5, |
|
3441 |
+ "precision": "fp32", |
|
3442 |
+ "peak_rss_mb": 2962.440192, |
|
3443 |
+ "speedup_vs_cpu_mt": 0.12547982504384633, |
|
3444 |
+ "speedup_vs_cpu_1t": 0.9794619635248267, |
|
3445 |
+ "cpu_mt_median_s": 0.00020695803686976433, |
|
3446 |
+ "cpu_1t_median_s": 0.0016154590994119644, |
|
3447 |
+ "metal_wins_vs_mt": false, |
|
3448 |
+ "cpu_wins_vs_mt": true |
|
3449 |
+ }, |
|
3450 |
+ { |
|
3451 |
+ "kernel": "garch_nll_P1", |
|
3452 |
+ "S": 1000, |
|
3453 |
+ "n": 390, |
|
3454 |
+ "elements": 390000, |
|
3455 |
+ "backend": "metal", |
|
3456 |
+ "threads": 0, |
|
3457 |
+ "median_s": 0.0011531668715178967, |
|
3458 |
+ "ci_lo": 0.0010962923988699913, |
|
3459 |
+ "ci_hi": 0.0011774590238928795, |
|
3460 |
+ "device_s": 0.00017799995839595795, |
|
3461 |
+ "elements_per_s": 338199101.65009224, |
|
3462 |
+ "reps": 5, |
|
3463 |
+ "precision": "fp32", |
|
3464 |
+ "peak_rss_mb": 3222.339584, |
|
3465 |
+ "speedup_vs_cpu_mt": 0.23984627728802252, |
|
3466 |
+ "speedup_vs_cpu_1t": 1.4213035256320952, |
|
3467 |
+ "cpu_mt_median_s": 0.0002765827812254429, |
|
3468 |
+ "cpu_1t_median_s": 0.0016390001401305199, |
|
3469 |
+ "metal_wins_vs_mt": false, |
|
3470 |
+ "cpu_wins_vs_mt": true |
|
3471 |
+ }, |
|
3472 |
+ { |
|
3473 |
+ "kernel": "garch_nll_P1", |
|
3474 |
+ "S": 1000, |
|
3475 |
+ "n": 3900, |
|
3476 |
+ "elements": 3900000, |
|
3477 |
+ "backend": "metal", |
|
3478 |
+ "threads": 0, |
|
3479 |
+ "median_s": 0.0072068748995661736, |
|
3480 |
+ "ci_lo": 0.007158916909247637, |
|
3481 |
+ "ci_hi": 0.009398084133863449, |
|
3482 |
+ "device_s": 0.0010924999369308352, |
|
3483 |
+ "elements_per_s": 541149951.171591, |
|
3484 |
+ "reps": 5, |
|
3485 |
+ "precision": "fp32", |
|
3486 |
+ "peak_rss_mb": 3360.11264, |
|
3487 |
+ "speedup_vs_cpu_mt": 0.20783391957146272, |
|
3488 |
+ "speedup_vs_cpu_1t": 2.5406528003548057, |
|
3489 |
+ "cpu_mt_median_s": 0.0014978330582380295, |
|
3490 |
+ "cpu_1t_median_s": 0.018310166895389557, |
|
3491 |
+ "metal_wins_vs_mt": false, |
|
3492 |
+ "cpu_wins_vs_mt": true |
|
3493 |
+ }, |
|
3494 |
+ { |
|
3495 |
+ "kernel": "garch_nll_P1", |
|
3496 |
+ "S": 10000, |
|
3497 |
+ "n": 390, |
|
3498 |
+ "elements": 3900000, |
|
3499 |
+ "backend": "metal", |
|
3500 |
+ "threads": 0, |
|
3501 |
+ "median_s": 0.00675466563552618, |
|
3502 |
+ "ci_lo": 0.006540417205542326, |
|
3503 |
+ "ci_hi": 0.007071124855428934, |
|
3504 |
+ "device_s": 0.00046787504106760025, |
|
3505 |
+ "elements_per_s": 577378690.5880197, |
|
3506 |
+ "reps": 5, |
|
3507 |
+ "precision": "fp32", |
|
3508 |
+ "peak_rss_mb": 2962.440192, |
|
3509 |
+ "speedup_vs_cpu_mt": 0.33211607376881125, |
|
3510 |
+ "speedup_vs_cpu_1t": 2.6265426009135546, |
|
3511 |
+ "cpu_mt_median_s": 0.0022433330304920673, |
|
3512 |
+ "cpu_1t_median_s": 0.017741417046636343, |
|
3513 |
+ "metal_wins_vs_mt": false, |
|
3514 |
+ "cpu_wins_vs_mt": true |
|
3515 |
+ }, |
|
3516 |
+ { |
|
3517 |
+ "kernel": "garch_nll_P1", |
|
3518 |
+ "S": 10000, |
|
3519 |
+ "n": 3900, |
|
3520 |
+ "elements": 39000000, |
|
3521 |
+ "backend": "metal", |
|
3522 |
+ "threads": 0, |
|
3523 |
+ "median_s": 0.06106641702353954, |
|
3524 |
+ "ci_lo": 0.05950908316299319, |
|
3525 |
+ "ci_hi": 0.0616582497023046, |
|
3526 |
+ "device_s": 0.004054000019095838, |
|
3527 |
+ "elements_per_s": 638648899.0334327, |
|
3528 |
+ "reps": 5, |
|
3529 |
+ "precision": "fp32", |
|
3530 |
+ "peak_rss_mb": 3355.901952, |
|
3531 |
+ "speedup_vs_cpu_mt": 0.22653068193252948, |
|
3532 |
+ "speedup_vs_cpu_1t": 2.6571710799488897, |
|
3533 |
+ "cpu_mt_median_s": 0.01383341709151864, |
|
3534 |
+ "cpu_1t_median_s": 0.16226391727104783, |
|
3535 |
+ "metal_wins_vs_mt": false, |
|
3536 |
+ "cpu_wins_vs_mt": true |
|
3537 |
+ }, |
|
3538 |
+ { |
|
3539 |
+ "kernel": "garch_nll_P64", |
|
3540 |
+ "S": 1, |
|
3541 |
+ "n": 390, |
|
3542 |
+ "elements": 390, |
|
3543 |
+ "backend": "metal", |
|
3544 |
+ "threads": 0, |
|
3545 |
+ "median_s": 0.0005012080073356628, |
|
3546 |
+ "ci_lo": 0.00047737499698996544, |
|
3547 |
+ "ci_hi": 0.0006123748607933521, |
|
3548 |
+ "device_s": 0.0003255000337958336, |
|
3549 |
+ "elements_per_s": 778120.0505418383, |
|
3550 |
+ "reps": 5, |
|
3551 |
+ "precision": "fp32", |
|
3552 |
+ "peak_rss_mb": 3431.46496, |
|
3553 |
+ "speedup_vs_cpu_mt": 0.3436696347608925, |
|
3554 |
+ "speedup_vs_cpu_1t": 0.16535078265523034, |
|
3555 |
+ "cpu_mt_median_s": 0.00017224997282028198, |
|
3556 |
+ "cpu_1t_median_s": 8.287513628602028e-05, |
|
3557 |
+ "metal_wins_vs_mt": false, |
|
3558 |
+ "cpu_wins_vs_mt": true |
|
3559 |
+ }, |
|
3560 |
+ { |
|
3561 |
+ "kernel": "garch_nll_P64", |
|
3562 |
+ "S": 1, |
|
3563 |
+ "n": 3900, |
|
3564 |
+ "elements": 3900, |
|
3565 |
+ "backend": "metal", |
|
3566 |
+ "threads": 0, |
|
3567 |
+ "median_s": 0.0014235423877835274, |
|
3568 |
+ "ci_lo": 0.00134983379393816, |
|
3569 |
+ "ci_hi": 0.0033927499316632748, |
|
3570 |
+ "device_s": 0.00122337497305125, |
|
3571 |
+ "elements_per_s": 2739644.4485733556, |
|
3572 |
+ "reps": 5, |
|
3573 |
+ "precision": "fp32", |
|
3574 |
+ "peak_rss_mb": 3431.87456, |
|
3575 |
+ "speedup_vs_cpu_mt": 0.09966326838366861, |
|
3576 |
+ "speedup_vs_cpu_1t": 0.5674807673058265, |
|
3577 |
+ "cpu_mt_median_s": 0.00014187488704919815, |
|
3578 |
+ "cpu_1t_median_s": 0.0008078329265117645, |
|
3579 |
+ "metal_wins_vs_mt": false, |
|
3580 |
+ "cpu_wins_vs_mt": true |
|
3581 |
+ }, |
|
3582 |
+ { |
|
3583 |
+ "kernel": "garch_nll_P64", |
|
3584 |
+ "S": 10, |
|
3585 |
+ "n": 390, |
|
3586 |
+ "elements": 3900, |
|
3587 |
+ "backend": "metal", |
|
3588 |
+ "threads": 0, |
|
3589 |
+ "median_s": 0.0010179998353123665, |
|
3590 |
+ "ci_lo": 0.0004632081836462021, |
|
3591 |
+ "ci_hi": 0.0010751672089099884, |
|
3592 |
+ "device_s": 0.00032300001475960016, |
|
3593 |
+ "elements_per_s": 3831041.877136759, |
|
3594 |
+ "reps": 5, |
|
3595 |
+ "precision": "fp32", |
|
3596 |
+ "peak_rss_mb": 3431.530496, |
|
3597 |
+ "speedup_vs_cpu_mt": 0.23956310168891443, |
|
3598 |
+ "speedup_vs_cpu_1t": 0.8111084478655968, |
|
3599 |
+ "cpu_mt_median_s": 0.0002438751980662346, |
|
3600 |
+ "cpu_1t_median_s": 0.0008257082663476467, |
|
3601 |
+ "metal_wins_vs_mt": false, |
|
3602 |
+ "cpu_wins_vs_mt": true |
|
3603 |
+ }, |
|
3604 |
+ { |
|
3605 |
+ "kernel": "garch_nll_P64", |
|
3606 |
+ "S": 10, |
|
3607 |
+ "n": 3900, |
|
3608 |
+ "elements": 39000, |
|
3609 |
+ "backend": "metal", |
|
3610 |
+ "threads": 0, |
|
3611 |
+ "median_s": 0.0013822498731315136, |
|
3612 |
+ "ci_lo": 0.0008970410563051701, |
|
3613 |
+ "ci_hi": 0.0033571659587323666, |
|
3614 |
+ "device_s": 0.0006641249638050795, |
|
3615 |
+ "elements_per_s": 28214869.654243305, |
|
3616 |
+ "reps": 5, |
|
3617 |
+ "precision": "fp32", |
|
3618 |
+ "peak_rss_mb": 3431.530496, |
|
3619 |
+ "speedup_vs_cpu_mt": 0.5610419763916696, |
|
3620 |
+ "speedup_vs_cpu_1t": 5.848345499988377, |
|
3621 |
+ "cpu_mt_median_s": 0.000775500200688839, |
|
3622 |
+ "cpu_1t_median_s": 0.008083874825388193, |
|
3623 |
+ "metal_wins_vs_mt": false, |
|
3624 |
+ "cpu_wins_vs_mt": true |
|
3625 |
+ }, |
|
3626 |
+ { |
|
3627 |
+ "kernel": "garch_nll_P64", |
|
3628 |
+ "S": 100, |
|
3629 |
+ "n": 390, |
|
3630 |
+ "elements": 39000, |
|
3631 |
+ "backend": "metal", |
|
3632 |
+ "threads": 0, |
|
3633 |
+ "median_s": 0.0005332920700311661, |
|
3634 |
+ "ci_lo": 0.0005230000242590904, |
|
3635 |
+ "ci_hi": 0.0005429168231785297, |
|
3636 |
+ "device_s": 0.00033650000113993883, |
|
3637 |
+ "elements_per_s": 73130658.02332444, |
|
3638 |
+ "reps": 5, |
|
3639 |
+ "precision": "fp32", |
|
3640 |
+ "peak_rss_mb": 2962.440192, |
|
3641 |
+ "speedup_vs_cpu_mt": 1.8859274420294159, |
|
3642 |
+ "speedup_vs_cpu_1t": 15.650977615094181, |
|
3643 |
+ "cpu_mt_median_s": 0.001005750149488449, |
|
3644 |
+ "cpu_1t_median_s": 0.008346542250365019, |
|
3645 |
+ "metal_wins_vs_mt": true, |
|
3646 |
+ "cpu_wins_vs_mt": false |
|
3647 |
+ }, |
|
3648 |
+ { |
|
3649 |
+ "kernel": "garch_nll_P64", |
|
3650 |
+ "S": 100, |
|
3651 |
+ "n": 3900, |
|
3652 |
+ "elements": 390000, |
|
3653 |
+ "backend": "metal", |
|
3654 |
+ "threads": 0, |
|
3655 |
+ "median_s": 0.0021704169921576977, |
|
3656 |
+ "ci_lo": 0.0018634586594998837, |
|
3657 |
+ "ci_hi": 0.0022297906689345837, |
|
3658 |
+ "device_s": 0.0010580417001619935, |
|
3659 |
+ "elements_per_s": 179688972.86059555, |
|
3660 |
+ "reps": 5, |
|
3661 |
+ "precision": "fp32", |
|
3662 |
+ "peak_rss_mb": 3431.858176, |
|
3663 |
+ "speedup_vs_cpu_mt": 2.84455693975565, |
|
3664 |
+ "speedup_vs_cpu_1t": 36.920938824506244, |
|
3665 |
+ "cpu_mt_median_s": 0.006173874717205763, |
|
3666 |
+ "cpu_1t_median_s": 0.0801338329911232, |
|
3667 |
+ "metal_wins_vs_mt": true, |
|
3668 |
+ "cpu_wins_vs_mt": false |
|
3669 |
+ }, |
|
3670 |
+ { |
|
3671 |
+ "kernel": "garch_nll_P64", |
|
3672 |
+ "S": 1000, |
|
3673 |
+ "n": 390, |
|
3674 |
+ "elements": 390000, |
|
3675 |
+ "backend": "metal", |
|
3676 |
+ "threads": 0, |
|
3677 |
+ "median_s": 0.002336665987968445, |
|
3678 |
+ "ci_lo": 0.002312499564141035, |
|
3679 |
+ "ci_hi": 0.0027117920108139515, |
|
3680 |
+ "device_s": 0.001452916651032865, |
|
3681 |
+ "elements_per_s": 166904470.73228282, |
|
3682 |
+ "reps": 5, |
|
3683 |
+ "precision": "fp32", |
|
3684 |
+ "peak_rss_mb": 3359.932416, |
|
3685 |
+ "speedup_vs_cpu_mt": 3.632133587567199, |
|
3686 |
+ "speedup_vs_cpu_1t": 41.4259215711908, |
|
3687 |
+ "cpu_mt_median_s": 0.00848708301782608, |
|
3688 |
+ "cpu_1t_median_s": 0.09679854195564985, |
|
3689 |
+ "metal_wins_vs_mt": true, |
|
3690 |
+ "cpu_wins_vs_mt": false |
|
3691 |
+ }, |
|
3692 |
+ { |
|
3693 |
+ "kernel": "garch_nll_P64", |
|
3694 |
+ "S": 1000, |
|
3695 |
+ "n": 3900, |
|
3696 |
+ "elements": 3900000, |
|
3697 |
+ "backend": "metal", |
|
3698 |
+ "threads": 0, |
|
3699 |
+ "median_s": 0.010272707790136337, |
|
3700 |
+ "ci_lo": 0.009604125283658504, |
|
3701 |
+ "ci_hi": 0.010956583078950644, |
|
3702 |
+ "device_s": 0.0029698750004172325, |
|
3703 |
+ "elements_per_s": 379646737.7125929, |
|
3704 |
+ "reps": 5, |
|
3705 |
+ "precision": "fp32", |
|
3706 |
+ "peak_rss_mb": 2962.440192, |
|
3707 |
+ "speedup_vs_cpu_mt": 7.934195016316967, |
|
3708 |
+ "speedup_vs_cpu_1t": 83.34503273547365, |
|
3709 |
+ "cpu_mt_median_s": 0.08150566695258021, |
|
3710 |
+ "cpu_1t_median_s": 0.8561791670508683, |
|
3711 |
+ "metal_wins_vs_mt": true, |
|
3712 |
+ "cpu_wins_vs_mt": false |
|
3713 |
+ }, |
|
3714 |
+ { |
|
3715 |
+ "kernel": "realized_fused", |
|
3716 |
+ "S": 1, |
|
3717 |
+ "n": 390, |
|
3718 |
+ "elements": 390, |
|
3719 |
+ "backend": "metal", |
|
3720 |
+ "threads": 0, |
|
3721 |
+ "median_s": 0.0002344171516597271, |
|
3722 |
+ "ci_lo": 0.00019499985501170158, |
|
3723 |
+ "ci_hi": 0.00025337468832731247, |
|
3724 |
+ "device_s": 3.199989441782236e-05, |
|
3725 |
+ "elements_per_s": 1663700.7882687368, |
|
3726 |
+ "reps": 5, |
|
3727 |
+ "precision": "fp32", |
|
3728 |
+ "peak_rss_mb": 3432.742912, |
|
3729 |
+ "speedup_vs_cpu_mt": 0.006398401293585508, |
|
3730 |
+ "speedup_vs_cpu_1t": 0.006398401293585508, |
|
3731 |
+ "cpu_mt_median_s": 1.4998950064182281e-06, |
|
3732 |
+ "cpu_1t_median_s": 1.4998950064182281e-06, |
|
3733 |
+ "metal_wins_vs_mt": false, |
|
3734 |
+ "cpu_wins_vs_mt": true |
|
3735 |
+ }, |
|
3736 |
+ { |
|
3737 |
+ "kernel": "realized_fused", |
|
3738 |
+ "S": 1, |
|
3739 |
+ "n": 3900, |
|
3740 |
+ "elements": 3900, |
|
3741 |
+ "backend": "metal", |
|
3742 |
+ "threads": 0, |
|
3743 |
+ "median_s": 0.0006333747878670692, |
|
3744 |
+ "ci_lo": 0.0001420830376446247, |
|
3745 |
+ "ci_hi": 0.000777125358581543, |
|
3746 |
+ "device_s": 2.037500962615013e-05, |
|
3747 |
+ "elements_per_s": 6157491.7011356, |
|
3748 |
+ "reps": 5, |
|
3749 |
+ "precision": "fp32", |
|
3750 |
+ "peak_rss_mb": 2913.878016, |
|
3751 |
+ "speedup_vs_cpu_mt": 0.017629517660396336, |
|
3752 |
+ "speedup_vs_cpu_1t": 0.018353696103846455, |
|
3753 |
+ "cpu_mt_median_s": 1.116609200835228e-05, |
|
3754 |
+ "cpu_1t_median_s": 1.1624768376350403e-05, |
|
3755 |
+ "metal_wins_vs_mt": false, |
|
3756 |
+ "cpu_wins_vs_mt": true |
|
3757 |
+ }, |
|
3758 |
+ { |
|
3759 |
+ "kernel": "realized_fused", |
|
3760 |
+ "S": 1, |
|
3761 |
+ "n": 39000, |
|
3762 |
+ "elements": 39000, |
|
3763 |
+ "backend": "metal", |
|
3764 |
+ "threads": 0, |
|
3765 |
+ "median_s": 0.000206624623388052, |
|
3766 |
+ "ci_lo": 0.0001971670426428318, |
|
3767 |
+ "ci_hi": 0.00024229194968938828, |
|
3768 |
+ "device_s": 4.3874955736100674e-05, |
|
3769 |
+ "elements_per_s": 188748075.42543435, |
|
3770 |
+ "reps": 5, |
|
3771 |
+ "precision": "fp32", |
|
3772 |
+ "peak_rss_mb": 3355.901952, |
|
3773 |
+ "speedup_vs_cpu_mt": 0.8090362681222294, |
|
3774 |
+ "speedup_vs_cpu_1t": 0.8836458781717422, |
|
3775 |
+ "cpu_mt_median_s": 0.0001671668142080307, |
|
3776 |
+ "cpu_1t_median_s": 0.00018258299678564072, |
|
3777 |
+ "metal_wins_vs_mt": false, |
|
3778 |
+ "cpu_wins_vs_mt": true |
|
3779 |
+ }, |
|
3780 |
+ { |
|
3781 |
+ "kernel": "realized_fused", |
|
3782 |
+ "S": 1, |
|
3783 |
+ "n": 390000, |
|
3784 |
+ "elements": 390000, |
|
3785 |
+ "backend": "metal", |
|
3786 |
+ "threads": 0, |
|
3787 |
+ "median_s": 0.0009353337809443474, |
|
3788 |
+ "ci_lo": 0.00017445813864469528, |
|
3789 |
+ "ci_hi": 0.0009425836615264416, |
|
3790 |
+ "device_s": 1.2583332136273384e-05, |
|
3791 |
+ "elements_per_s": 416963449.78178984, |
|
3792 |
+ "reps": 5, |
|
3793 |
+ "precision": "fp32", |
|
3794 |
+ "peak_rss_mb": 781.1072, |
|
3795 |
+ "speedup_vs_cpu_mt": 2.2300860195139536, |
|
3796 |
+ "speedup_vs_cpu_1t": 2.1728878719355733, |
|
3797 |
+ "cpu_mt_median_s": 0.0020858747884631157, |
|
3798 |
+ "cpu_1t_median_s": 0.002032375428825617, |
|
3799 |
+ "metal_wins_vs_mt": true, |
|
3800 |
+ "cpu_wins_vs_mt": false |
|
3801 |
+ }, |
|
3802 |
+ { |
|
3803 |
+ "kernel": "realized_fused", |
|
3804 |
+ "S": 10, |
|
3805 |
+ "n": 390, |
|
3806 |
+ "elements": 3900, |
|
3807 |
+ "backend": "metal", |
|
3808 |
+ "threads": 0, |
|
3809 |
+ "median_s": 0.0002327919937670231, |
|
3810 |
+ "ci_lo": 0.00019591627642512321, |
|
3811 |
+ "ci_hi": 0.0002467092126607895, |
|
3812 |
+ "device_s": 3.124994691461325e-05, |
|
3813 |
+ "elements_per_s": 16753153.477877328, |
|
3814 |
+ "reps": 5, |
|
3815 |
+ "precision": "fp32", |
|
3816 |
+ "peak_rss_mb": 3255.451648, |
|
3817 |
+ "speedup_vs_cpu_mt": 0.6099872578848089, |
|
3818 |
+ "speedup_vs_cpu_1t": 0.04850805233668789, |
|
3819 |
+ "cpu_mt_median_s": 0.00014200014993548393, |
|
3820 |
+ "cpu_1t_median_s": 1.1292286217212677e-05, |
|
3821 |
+ "metal_wins_vs_mt": false, |
|
3822 |
+ "cpu_wins_vs_mt": true |
|
3823 |
+ }, |
|
3824 |
+ { |
|
3825 |
+ "kernel": "realized_fused", |
|
3826 |
+ "S": 10, |
|
3827 |
+ "n": 3900, |
|
3828 |
+ "elements": 39000, |
|
3829 |
+ "backend": "metal", |
|
3830 |
+ "threads": 0, |
|
3831 |
+ "median_s": 0.00016404176130890846, |
|
3832 |
+ "ci_lo": 0.00015954114496707916, |
|
3833 |
+ "ci_hi": 0.0009339582175016403, |
|
3834 |
+ "device_s": 1.6249949112534523e-05, |
|
3835 |
+ "elements_per_s": 237744338.32467064, |
|
3836 |
+ "reps": 5, |
|
3837 |
+ "precision": "fp32", |
|
3838 |
+ "peak_rss_mb": 3222.339584, |
|
3839 |
+ "speedup_vs_cpu_mt": 0.8229631795433707, |
|
3840 |
+ "speedup_vs_cpu_1t": 1.145538879915521, |
|
3841 |
+ "cpu_mt_median_s": 0.000135000329464674, |
|
3842 |
+ "cpu_1t_median_s": 0.00018791621550917625, |
|
3843 |
+ "metal_wins_vs_mt": false, |
|
3844 |
+ "cpu_wins_vs_mt": true |
|
3845 |
+ }, |
|
3846 |
+ { |
|
3847 |
+ "kernel": "realized_fused", |
|
3848 |
+ "S": 10, |
|
3849 |
+ "n": 39000, |
|
3850 |
+ "elements": 390000, |
|
3851 |
+ "backend": "metal", |
|
3852 |
+ "threads": 0, |
|
3853 |
+ "median_s": 0.0007184999994933605, |
|
3854 |
+ "ci_lo": 0.000268666073679924, |
|
3855 |
+ "ci_hi": 0.0007987502031028271, |
|
3856 |
+ "device_s": 5.52500132471323e-05, |
|
3857 |
+ "elements_per_s": 542797495.1635388, |
|
3858 |
+ "reps": 5, |
|
3859 |
+ "precision": "fp32", |
|
3860 |
+ "peak_rss_mb": 3355.901952, |
|
3861 |
+ "speedup_vs_cpu_mt": 0.5059149029110798, |
|
3862 |
+ "speedup_vs_cpu_1t": 3.5805503293330316, |
|
3863 |
+ "cpu_mt_median_s": 0.00036349985748529434, |
|
3864 |
+ "cpu_1t_median_s": 0.002572625409811735, |
|
3865 |
+ "metal_wins_vs_mt": false, |
|
3866 |
+ "cpu_wins_vs_mt": false |
|
3867 |
+ }, |
|
3868 |
+ { |
|
3869 |
+ "kernel": "realized_fused", |
|
3870 |
+ "S": 10, |
|
3871 |
+ "n": 390000, |
|
3872 |
+ "elements": 3900000, |
|
3873 |
+ "backend": "metal", |
|
3874 |
+ "threads": 0, |
|
3875 |
+ "median_s": 0.0010219174437224865, |
|
3876 |
+ "ci_lo": 0.001003749668598175, |
|
3877 |
+ "ci_hi": 0.0010474580340087414, |
|
3878 |
+ "device_s": 8.649996016174555e-05, |
|
3879 |
+ "elements_per_s": 3816355248.6134977, |
|
3880 |
+ "reps": 5, |
|
3881 |
+ "precision": "fp32", |
|
3882 |
+ "peak_rss_mb": 3222.339584, |
|
3883 |
+ "speedup_vs_cpu_mt": 2.4725987229278337, |
|
3884 |
+ "speedup_vs_cpu_1t": 20.444125928265052, |
|
3885 |
+ "cpu_mt_median_s": 0.0025267917662858963, |
|
3886 |
+ "cpu_1t_median_s": 0.02089220890775323, |
|
3887 |
+ "metal_wins_vs_mt": true, |
|
3888 |
+ "cpu_wins_vs_mt": false |
|
3889 |
+ }, |
|
3890 |
+ { |
|
3891 |
+ "kernel": "realized_fused", |
|
3892 |
+ "S": 100, |
|
3893 |
+ "n": 390, |
|
3894 |
+ "elements": 39000, |
|
3895 |
+ "backend": "metal", |
|
3896 |
+ "threads": 0, |
|
3897 |
+ "median_s": 0.00022633420303463936, |
|
3898 |
+ "ci_lo": 0.00017816666513681412, |
|
3899 |
+ "ci_hi": 0.00027566729113459587, |
|
3900 |
+ "device_s": 3.15000070258975e-05, |
|
3901 |
+ "elements_per_s": 172311561.73966, |
|
3902 |
+ "reps": 5, |
|
3903 |
+ "precision": "fp32", |
|
3904 |
+ "peak_rss_mb": 3368.943616, |
|
3905 |
+ "speedup_vs_cpu_mt": 2.4392376077309077, |
|
3906 |
+ "speedup_vs_cpu_1t": 0.8267643797230321, |
|
3907 |
+ "cpu_mt_median_s": 0.0005520828999578953, |
|
3908 |
+ "cpu_1t_median_s": 0.0001871250569820404, |
|
3909 |
+ "metal_wins_vs_mt": true, |
|
3910 |
+ "cpu_wins_vs_mt": false |
|
3911 |
+ }, |
|
3912 |
+ { |
|
3913 |
+ "kernel": "realized_fused", |
|
3914 |
+ "S": 100, |
|
3915 |
+ "n": 3900, |
|
3916 |
+ "elements": 390000, |
|
3917 |
+ "backend": "metal", |
|
3918 |
+ "threads": 0, |
|
3919 |
+ "median_s": 0.0006413329392671585, |
|
3920 |
+ "ci_lo": 0.000292791984975338, |
|
3921 |
+ "ci_hi": 0.0008833748288452625, |
|
3922 |
+ "device_s": 5.287490785121918e-05, |
|
3923 |
+ "elements_per_s": 608108481.7593294, |
|
3924 |
+ "reps": 5, |
|
3925 |
+ "precision": "fp32", |
|
3926 |
+ "peak_rss_mb": 490.962944, |
|
3927 |
+ "speedup_vs_cpu_mt": 0.9380200573315559, |
|
3928 |
+ "speedup_vs_cpu_1t": 3.1862033963283407, |
|
3929 |
+ "cpu_mt_median_s": 0.0006015831604599953, |
|
3930 |
+ "cpu_1t_median_s": 0.002043417189270258, |
|
3931 |
+ "metal_wins_vs_mt": false, |
|
3932 |
+ "cpu_wins_vs_mt": false |
|
3933 |
+ }, |
|
3934 |
+ { |
|
3935 |
+ "kernel": "realized_fused", |
|
3936 |
+ "S": 100, |
|
3937 |
+ "n": 39000, |
|
3938 |
+ "elements": 3900000, |
|
3939 |
+ "backend": "metal", |
|
3940 |
+ "threads": 0, |
|
3941 |
+ "median_s": 0.0011692089028656483, |
|
3942 |
+ "ci_lo": 0.0008370000869035721, |
|
3943 |
+ "ci_hi": 0.0011960407719016075, |
|
3944 |
+ "device_s": 0.000259208376519382, |
|
3945 |
+ "elements_per_s": 3335588696.289753, |
|
3946 |
+ "reps": 5, |
|
3947 |
+ "precision": "fp32", |
|
3948 |
+ "peak_rss_mb": 3360.096256, |
|
3949 |
+ "speedup_vs_cpu_mt": 1.8734535658542084, |
|
3950 |
+ "speedup_vs_cpu_1t": 17.61073211258148, |
|
3951 |
+ "cpu_mt_median_s": 0.0021904585883021355, |
|
3952 |
+ "cpu_1t_median_s": 0.020590624772012234, |
|
3953 |
+ "metal_wins_vs_mt": true, |
|
3954 |
+ "cpu_wins_vs_mt": false |
|
3955 |
+ }, |
|
3956 |
+ { |
|
3957 |
+ "kernel": "realized_fused", |
|
3958 |
+ "S": 100, |
|
3959 |
+ "n": 390000, |
|
3960 |
+ "elements": 39000000, |
|
3961 |
+ "backend": "metal", |
|
3962 |
+ "threads": 0, |
|
3963 |
+ "median_s": 0.008720249868929386, |
|
3964 |
+ "ci_lo": 0.007397250272333622, |
|
3965 |
+ "ci_hi": 0.008947291877120733, |
|
3966 |
+ "device_s": 0.0021910000359639525, |
|
3967 |
+ "elements_per_s": 4472348910.43187, |
|
3968 |
+ "reps": 5, |
|
3969 |
+ "precision": "fp32", |
|
3970 |
+ "peak_rss_mb": 486.178816, |
|
3971 |
+ "speedup_vs_cpu_mt": 2.1550509398559075, |
|
3972 |
+ "speedup_vs_cpu_1t": 26.67203779822428, |
|
3973 |
+ "cpu_mt_median_s": 0.01879258267581463, |
|
3974 |
+ "cpu_1t_median_s": 0.2325868341140449, |
|
3975 |
+ "metal_wins_vs_mt": true, |
|
3976 |
+ "cpu_wins_vs_mt": false |
|
3977 |
+ }, |
|
3978 |
+ { |
|
3979 |
+ "kernel": "realized_fused", |
|
3980 |
+ "S": 1000, |
|
3981 |
+ "n": 390, |
|
3982 |
+ "elements": 390000, |
|
3983 |
+ "backend": "metal", |
|
3984 |
+ "threads": 0, |
|
3985 |
+ "median_s": 0.00033845799043774605, |
|
3986 |
+ "ci_lo": 0.00033012498170137405, |
|
3987 |
+ "ci_hi": 0.00035137496888637543, |
|
3988 |
+ "device_s": 0.00013987498823553324, |
|
3989 |
+ "elements_per_s": 1152284806.4410944, |
|
3990 |
+ "reps": 5, |
|
3991 |
+ "precision": "fp32", |
|
3992 |
+ "peak_rss_mb": 3431.87456, |
|
3993 |
+ "speedup_vs_cpu_mt": 2.4815989367571367, |
|
3994 |
+ "speedup_vs_cpu_1t": 6.605815916448483, |
|
3995 |
+ "cpu_mt_median_s": 0.0008399169892072678, |
|
3996 |
+ "cpu_1t_median_s": 0.002235791180282831, |
|
3997 |
+ "metal_wins_vs_mt": true, |
|
3998 |
+ "cpu_wins_vs_mt": false |
|
3999 |
+ }, |
|
4000 |
+ { |
|
4001 |
+ "kernel": "realized_fused", |
|
4002 |
+ "S": 1000, |
|
4003 |
+ "n": 3900, |
|
4004 |
+ "elements": 3900000, |
|
4005 |
+ "backend": "metal", |
|
4006 |
+ "threads": 0, |
|
4007 |
+ "median_s": 0.0008750832639634609, |
|
4008 |
+ "ci_lo": 0.0008294158615171909, |
|
4009 |
+ "ci_hi": 0.0015468327328562737, |
|
4010 |
+ "device_s": 0.0002547500189393759, |
|
4011 |
+ "elements_per_s": 4456718761.065055, |
|
4012 |
+ "reps": 5, |
|
4013 |
+ "precision": "fp32", |
|
4014 |
+ "peak_rss_mb": 3432.742912, |
|
4015 |
+ "speedup_vs_cpu_mt": 1.9909537272506195, |
|
4016 |
+ "speedup_vs_cpu_1t": 24.27716502583243, |
|
4017 |
+ "cpu_mt_median_s": 0.0017422502860426903, |
|
4018 |
+ "cpu_1t_median_s": 0.021244540810585022, |
|
4019 |
+ "metal_wins_vs_mt": true, |
|
4020 |
+ "cpu_wins_vs_mt": false |
|
4021 |
+ }, |
|
4022 |
+ { |
|
4023 |
+ "kernel": "realized_fused", |
|
4024 |
+ "S": 1000, |
|
4025 |
+ "n": 39000, |
|
4026 |
+ "elements": 39000000, |
|
4027 |
+ "backend": "metal", |
|
4028 |
+ "threads": 0, |
|
4029 |
+ "median_s": 0.005891874898225069, |
|
4030 |
+ "ci_lo": 0.005617166869342327, |
|
4031 |
+ "ci_hi": 0.00844891695305705, |
|
4032 |
+ "device_s": 0.0009469999931752682, |
|
4033 |
+ "elements_per_s": 6619285146.693929, |
|
4034 |
+ "reps": 5, |
|
4035 |
+ "precision": "fp32", |
|
4036 |
+ "peak_rss_mb": 3369.04192, |
|
4037 |
+ "speedup_vs_cpu_mt": 3.4364769430726474, |
|
4038 |
+ "speedup_vs_cpu_1t": 40.52558334364075, |
|
4039 |
+ "cpu_mt_median_s": 0.02024729223921895, |
|
4040 |
+ "cpu_1t_median_s": 0.23877166723832488, |
|
4041 |
+ "metal_wins_vs_mt": true, |
|
4042 |
+ "cpu_wins_vs_mt": false |
|
4043 |
+ }, |
|
4044 |
+ { |
|
4045 |
+ "kernel": "realized_fused", |
|
4046 |
+ "S": 10000, |
|
4047 |
+ "n": 390, |
|
4048 |
+ "elements": 3900000, |
|
4049 |
+ "backend": "metal", |
|
4050 |
+ "threads": 0, |
|
4051 |
+ "median_s": 0.0022132499143481255, |
|
4052 |
+ "ci_lo": 0.0018930002115666866, |
|
4053 |
+ "ci_hi": 0.0032122922129929066, |
|
4054 |
+ "device_s": 0.001203041640110314, |
|
4055 |
+ "elements_per_s": 1762114605.6380522, |
|
4056 |
+ "reps": 5, |
|
4057 |
+ "precision": "fp32", |
|
4058 |
+ "peak_rss_mb": 3431.87456, |
|
4059 |
+ "speedup_vs_cpu_mt": 0.9605408719443508, |
|
4060 |
+ "speedup_vs_cpu_1t": 9.595994502745471, |
|
4061 |
+ "cpu_mt_median_s": 0.002125917002558708, |
|
4062 |
+ "cpu_1t_median_s": 0.021238334011286497, |
|
4063 |
+ "metal_wins_vs_mt": false, |
|
4064 |
+ "cpu_wins_vs_mt": false |
|
4065 |
+ }, |
|
4066 |
+ { |
|
4067 |
+ "kernel": "realized_fused", |
|
4068 |
+ "S": 10000, |
|
4069 |
+ "n": 3900, |
|
4070 |
+ "elements": 39000000, |
|
4071 |
+ "backend": "metal", |
|
4072 |
+ "threads": 0, |
|
4073 |
+ "median_s": 0.0078027499839663506, |
|
4074 |
+ "ci_lo": 0.006132957991212606, |
|
4075 |
+ "ci_hi": 0.008690916933119297, |
|
4076 |
+ "device_s": 0.0019207500154152513, |
|
4077 |
+ "elements_per_s": 4998237811.046104, |
|
4078 |
+ "reps": 5, |
|
4079 |
+ "precision": "fp32", |
|
4080 |
+ "peak_rss_mb": 577.1264, |
|
4081 |
+ "speedup_vs_cpu_mt": 2.0113315140749037, |
|
4082 |
+ "speedup_vs_cpu_1t": 29.947449069536802, |
|
4083 |
+ "cpu_mt_median_s": 0.01569391693919897, |
|
4084 |
+ "cpu_1t_median_s": 0.2336724577471614, |
|
4085 |
+ "metal_wins_vs_mt": true, |
|
4086 |
+ "cpu_wins_vs_mt": false |
|
4087 |
+ }, |
|
4088 |
+ { |
|
4089 |
+ "kernel": "regression_stats", |
|
4090 |
+ "S": 1, |
|
4091 |
+ "n": 390, |
|
4092 |
+ "elements": 390, |
|
4093 |
+ "backend": "metal", |
|
4094 |
+ "threads": 0, |
|
4095 |
+ "median_s": 0.000894167460501194, |
|
4096 |
+ "ci_lo": 0.00017508305609226227, |
|
4097 |
+ "ci_hi": 0.000988542102277279, |
|
4098 |
+ "device_s": 7.087492849677801e-05, |
|
4099 |
+ "elements_per_s": 436159.91100973333, |
|
4100 |
+ "reps": 5, |
|
4101 |
+ "precision": "fp32", |
|
4102 |
+ "peak_rss_mb": 3368.910848, |
|
4103 |
+ "speedup_vs_cpu_mt": 0.003588669989219929, |
|
4104 |
+ "speedup_vs_cpu_1t": 0.003541800115612355, |
|
4105 |
+ "cpu_mt_median_s": 3.2088719308376312e-06, |
|
4106 |
+ "cpu_1t_median_s": 3.1669624149799347e-06, |
|
4107 |
+ "metal_wins_vs_mt": false, |
|
4108 |
+ "cpu_wins_vs_mt": true |
|
4109 |
+ }, |
|
4110 |
+ { |
|
4111 |
+ "kernel": "regression_stats", |
|
4112 |
+ "S": 1, |
|
4113 |
+ "n": 3900, |
|
4114 |
+ "elements": 3900, |
|
4115 |
+ "backend": "metal", |
|
4116 |
+ "threads": 0, |
|
4117 |
+ "median_s": 0.0003482499159872532, |
|
4118 |
+ "ci_lo": 0.0003069578669965267, |
|
4119 |
+ "ci_hi": 0.0003833337686955929, |
|
4120 |
+ "device_s": 0.00019212497863918543, |
|
4121 |
+ "elements_per_s": 11198854.101497471, |
|
4122 |
+ "reps": 5, |
|
4123 |
+ "precision": "fp32", |
|
4124 |
+ "peak_rss_mb": 2962.440192, |
|
4125 |
+ "speedup_vs_cpu_mt": 0.0867420550075482, |
|
4126 |
+ "speedup_vs_cpu_1t": 0.08602668142876818, |
|
4127 |
+ "cpu_mt_median_s": 3.0207913368940353e-05, |
|
4128 |
+ "cpu_1t_median_s": 2.9958784580230713e-05, |
|
4129 |
+ "metal_wins_vs_mt": false, |
|
4130 |
+ "cpu_wins_vs_mt": true |
|
4131 |
+ }, |
|
4132 |
+ { |
|
4133 |
+ "kernel": "regression_stats", |
|
4134 |
+ "S": 1, |
|
4135 |
+ "n": 39000, |
|
4136 |
+ "elements": 39000, |
|
4137 |
+ "backend": "metal", |
|
4138 |
+ "threads": 0, |
|
4139 |
+ "median_s": 0.0004085828550159931, |
|
4140 |
+ "ci_lo": 0.0003508748486638069, |
|
4141 |
+ "ci_hi": 0.00041229184716939926, |
|
4142 |
+ "device_s": 0.00018866662867367268, |
|
4143 |
+ "elements_per_s": 95451875.96888623, |
|
4144 |
+ "reps": 5, |
|
4145 |
+ "precision": "fp32", |
|
4146 |
+ "peak_rss_mb": 3359.932416, |
|
4147 |
+ "speedup_vs_cpu_mt": 0.9395287346496851, |
|
4148 |
+ "speedup_vs_cpu_1t": 0.7399549819072855, |
|
4149 |
+ "cpu_mt_median_s": 0.0003838753327727318, |
|
4150 |
+ "cpu_1t_median_s": 0.00030233291909098625, |
|
4151 |
+ "metal_wins_vs_mt": false, |
|
4152 |
+ "cpu_wins_vs_mt": false |
|
4153 |
+ }, |
|
4154 |
+ { |
|
4155 |
+ "kernel": "regression_stats", |
|
4156 |
+ "S": 1, |
|
4157 |
+ "n": 390000, |
|
4158 |
+ "elements": 390000, |
|
4159 |
+ "backend": "metal", |
|
4160 |
+ "threads": 0, |
|
4161 |
+ "median_s": 0.0007901252247393131, |
|
4162 |
+ "ci_lo": 0.0007615000940859318, |
|
4163 |
+ "ci_hi": 0.0008232500404119492, |
|
4164 |
+ "device_s": 9.650003630667925e-05, |
|
4165 |
+ "elements_per_s": 493592645.5564979, |
|
4166 |
+ "reps": 5, |
|
4167 |
+ "precision": "fp32", |
|
4168 |
+ "peak_rss_mb": 2920.12032, |
|
4169 |
+ "speedup_vs_cpu_mt": 3.851129874745179, |
|
4170 |
+ "speedup_vs_cpu_1t": 3.7631692009752586, |
|
4171 |
+ "cpu_mt_median_s": 0.0030428748577833176, |
|
4172 |
+ "cpu_1t_median_s": 0.0029733749106526375, |
|
4173 |
+ "metal_wins_vs_mt": true, |
|
4174 |
+ "cpu_wins_vs_mt": false |
|
4175 |
+ }, |
|
4176 |
+ { |
|
4177 |
+ "kernel": "regression_stats", |
|
4178 |
+ "S": 10, |
|
4179 |
+ "n": 390, |
|
4180 |
+ "elements": 3900, |
|
4181 |
+ "backend": "metal", |
|
4182 |
+ "threads": 0, |
|
4183 |
+ "median_s": 0.0006523327901959419, |
|
4184 |
+ "ci_lo": 0.0003105420619249344, |
|
4185 |
+ "ci_hi": 0.0007279999554157257, |
|
4186 |
+ "device_s": 9.250000584870577e-05, |
|
4187 |
+ "elements_per_s": 5978543.557236411, |
|
4188 |
+ "reps": 5, |
|
4189 |
+ "precision": "fp32", |
|
4190 |
+ "peak_rss_mb": 2962.440192, |
|
4191 |
+ "speedup_vs_cpu_mt": 0.06336187265949686, |
|
4192 |
+ "speedup_vs_cpu_1t": 0.04790509353446491, |
|
4193 |
+ "cpu_mt_median_s": 4.133302718400955e-05, |
|
4194 |
+ "cpu_1t_median_s": 3.1250063329935074e-05, |
|
4195 |
+ "metal_wins_vs_mt": false, |
|
4196 |
+ "cpu_wins_vs_mt": true |
|
4197 |
+ }, |
|
4198 |
+ { |
|
4199 |
+ "kernel": "regression_stats", |
|
4200 |
+ "S": 10, |
|
4201 |
+ "n": 3900, |
|
4202 |
+ "elements": 39000, |
|
4203 |
+ "backend": "metal", |
|
4204 |
+ "threads": 0, |
|
4205 |
+ "median_s": 0.00036174990236759186, |
|
4206 |
+ "ci_lo": 0.0003430834040045738, |
|
4207 |
+ "ci_hi": 0.0005066245794296265, |
|
4208 |
+ "device_s": 0.00018737500067800283, |
|
4209 |
+ "elements_per_s": 107809289.63560627, |
|
4210 |
+ "reps": 5, |
|
4211 |
+ "precision": "fp32", |
|
4212 |
+ "peak_rss_mb": 3431.514112, |
|
4213 |
+ "speedup_vs_cpu_mt": 0.2107814615911396, |
|
4214 |
+ "speedup_vs_cpu_1t": 0.8286108550920896, |
|
4215 |
+ "cpu_mt_median_s": 7.625017315149307e-05, |
|
4216 |
+ "cpu_1t_median_s": 0.0002997498959302902, |
|
4217 |
+ "metal_wins_vs_mt": false, |
|
4218 |
+ "cpu_wins_vs_mt": true |
|
4219 |
+ }, |
|
4220 |
+ { |
|
4221 |
+ "kernel": "regression_stats", |
|
4222 |
+ "S": 10, |
|
4223 |
+ "n": 39000, |
|
4224 |
+ "elements": 390000, |
|
4225 |
+ "backend": "metal", |
|
4226 |
+ "threads": 0, |
|
4227 |
+ "median_s": 0.0006961673498153687, |
|
4228 |
+ "ci_lo": 0.0006541251204907894, |
|
4229 |
+ "ci_hi": 0.0008656666614115238, |
|
4230 |
+ "device_s": 0.0002501250710338354, |
|
4231 |
+ "elements_per_s": 560210127.7852694, |
|
4232 |
+ "reps": 5, |
|
4233 |
+ "precision": "fp32", |
|
4234 |
+ "peak_rss_mb": 576.421888, |
|
4235 |
+ "speedup_vs_cpu_mt": 0.8078766133692931, |
|
4236 |
+ "speedup_vs_cpu_1t": 4.429491347203493, |
|
4237 |
+ "cpu_mt_median_s": 0.0005624173209071159, |
|
4238 |
+ "cpu_1t_median_s": 0.003083667252212763, |
|
4239 |
+ "metal_wins_vs_mt": false, |
|
4240 |
+ "cpu_wins_vs_mt": true |
|
4241 |
+ }, |
|
4242 |
+ { |
|
4243 |
+ "kernel": "regression_stats", |
|
4244 |
+ "S": 10, |
|
4245 |
+ "n": 390000, |
|
4246 |
+ "elements": 3900000, |
|
4247 |
+ "backend": "metal", |
|
4248 |
+ "threads": 0, |
|
4249 |
+ "median_s": 0.004117042291909456, |
|
4250 |
+ "ci_lo": 0.002989500295370817, |
|
4251 |
+ "ci_hi": 0.004763709381222725, |
|
4252 |
+ "device_s": 0.000529208336956799, |
|
4253 |
+ "elements_per_s": 947281986.3094499, |
|
4254 |
+ "reps": 5, |
|
4255 |
+ "precision": "fp32", |
|
4256 |
+ "peak_rss_mb": 2962.440192, |
|
4257 |
+ "speedup_vs_cpu_mt": 1.6164011753500427, |
|
4258 |
+ "speedup_vs_cpu_1t": 7.9335070336527025, |
|
4259 |
+ "cpu_mt_median_s": 0.006654791999608278, |
|
4260 |
+ "cpu_1t_median_s": 0.032662583980709314, |
|
4261 |
+ "metal_wins_vs_mt": true, |
|
4262 |
+ "cpu_wins_vs_mt": false |
|
4263 |
+ }, |
|
4264 |
+ { |
|
4265 |
+ "kernel": "regression_stats", |
|
4266 |
+ "S": 100, |
|
4267 |
+ "n": 390, |
|
4268 |
+ "elements": 39000, |
|
4269 |
+ "backend": "metal", |
|
4270 |
+ "threads": 0, |
|
4271 |
+ "median_s": 0.0003363746218383312, |
|
4272 |
+ "ci_lo": 0.00026350002735853195, |
|
4273 |
+ "ci_hi": 0.0005579171702265739, |
|
4274 |
+ "device_s": 0.00019220833200961351, |
|
4275 |
+ "elements_per_s": 115942159.33074829, |
|
4276 |
+ "reps": 5, |
|
4277 |
+ "precision": "fp32", |
|
4278 |
+ "peak_rss_mb": 3255.451648, |
|
4279 |
+ "speedup_vs_cpu_mt": 0.5239693836444206, |
|
4280 |
+ "speedup_vs_cpu_1t": 1.0743231551070866, |
|
4281 |
+ "cpu_mt_median_s": 0.00017625000327825546, |
|
4282 |
+ "cpu_1t_median_s": 0.00036137504503130913, |
|
4283 |
+ "metal_wins_vs_mt": false, |
|
4284 |
+ "cpu_wins_vs_mt": true |
|
4285 |
+ }, |
|
4286 |
+ { |
|
4287 |
+ "kernel": "regression_stats", |
|
4288 |
+ "S": 100, |
|
4289 |
+ "n": 3900, |
|
4290 |
+ "elements": 390000, |
|
4291 |
+ "backend": "metal", |
|
4292 |
+ "threads": 0, |
|
4293 |
+ "median_s": 0.0005946666933596134, |
|
4294 |
+ "ci_lo": 0.0005814996547996998, |
|
4295 |
+ "ci_hi": 0.0005976245738565922, |
|
4296 |
+ "device_s": 0.00023925001733005047, |
|
4297 |
+ "elements_per_s": 655829566.9741753, |
|
4298 |
+ "reps": 5, |
|
4299 |
+ "precision": "fp32", |
|
4300 |
+ "peak_rss_mb": 2962.440192, |
|
4301 |
+ "speedup_vs_cpu_mt": 0.739769482011876, |
|
4302 |
+ "speedup_vs_cpu_1t": 5.041970592864576, |
|
4303 |
+ "cpu_mt_median_s": 0.0004399162717163563, |
|
4304 |
+ "cpu_1t_median_s": 0.0029982919804751873, |
|
4305 |
+ "metal_wins_vs_mt": false, |
|
4306 |
+ "cpu_wins_vs_mt": true |
|
4307 |
+ }, |
|
4308 |
+ { |
|
4309 |
+ "kernel": "regression_stats", |
|
4310 |
+ "S": 100, |
|
4311 |
+ "n": 39000, |
|
4312 |
+ "elements": 3900000, |
|
4313 |
+ "backend": "metal", |
|
4314 |
+ "threads": 0, |
|
4315 |
+ "median_s": 0.0044694580137729645, |
|
4316 |
+ "ci_lo": 0.0031338329426944256, |
|
4317 |
+ "ci_hi": 0.004542499780654907, |
|
4318 |
+ "device_s": 0.0016885417280718684, |
|
4319 |
+ "elements_per_s": 872589022.6470106, |
|
4320 |
+ "reps": 5, |
|
4321 |
+ "precision": "fp32", |
|
4322 |
+ "peak_rss_mb": 3431.46496, |
|
4323 |
+ "speedup_vs_cpu_mt": 0.7100881967325159, |
|
4324 |
+ "speedup_vs_cpu_1t": 7.202327484390641, |
|
4325 |
+ "cpu_mt_median_s": 0.0031737093813717365, |
|
4326 |
+ "cpu_1t_median_s": 0.03219050029292703, |
|
4327 |
+ "metal_wins_vs_mt": false, |
|
4328 |
+ "cpu_wins_vs_mt": false |
|
4329 |
+ }, |
|
4330 |
+ { |
|
4331 |
+ "kernel": "regression_stats", |
|
4332 |
+ "S": 100, |
|
4333 |
+ "n": 390000, |
|
4334 |
+ "elements": 39000000, |
|
4335 |
+ "backend": "metal", |
|
4336 |
+ "threads": 0, |
|
4337 |
+ "median_s": 0.03070899983868003, |
|
4338 |
+ "ci_lo": 0.027952750213444233, |
|
4339 |
+ "ci_hi": 0.031758958008140326, |
|
4340 |
+ "device_s": 0.005229625036008656, |
|
4341 |
+ "elements_per_s": 1269986004.2617507, |
|
4342 |
+ "reps": 5, |
|
4343 |
+ "precision": "fp32", |
|
4344 |
+ "peak_rss_mb": 2913.845248, |
|
4345 |
+ "speedup_vs_cpu_mt": 1.0993601156685116, |
|
4346 |
+ "speedup_vs_cpu_1t": 9.813711025090953, |
|
4347 |
+ "cpu_mt_median_s": 0.033760249614715576, |
|
4348 |
+ "cpu_1t_median_s": 0.3013692502863705, |
|
4349 |
+ "metal_wins_vs_mt": true, |
|
4350 |
+ "cpu_wins_vs_mt": false |
|
4351 |
+ }, |
|
4352 |
+ { |
|
4353 |
+ "kernel": "regression_stats", |
|
4354 |
+ "S": 1000, |
|
4355 |
+ "n": 390, |
|
4356 |
+ "elements": 390000, |
|
4357 |
+ "backend": "metal", |
|
4358 |
+ "threads": 0, |
|
4359 |
+ "median_s": 0.0005814996547996998, |
|
4360 |
+ "ci_lo": 0.0005787923000752926, |
|
4361 |
+ "ci_hi": 0.0009665000252425671, |
|
4362 |
+ "device_s": 0.00020362494979053736, |
|
4363 |
+ "elements_per_s": 670679675.870723, |
|
4364 |
+ "reps": 5, |
|
4365 |
+ "precision": "fp32", |
|
4366 |
+ "peak_rss_mb": 3431.858176, |
|
4367 |
+ "speedup_vs_cpu_mt": 1.1988402904959397, |
|
4368 |
+ "speedup_vs_cpu_1t": 5.367372139264439, |
|
4369 |
+ "cpu_mt_median_s": 0.0006971252150833607, |
|
4370 |
+ "cpu_1t_median_s": 0.0031211250461637974, |
|
4371 |
+ "metal_wins_vs_mt": false, |
|
4372 |
+ "cpu_wins_vs_mt": false |
|
4373 |
+ }, |
|
4374 |
+ { |
|
4375 |
+ "kernel": "regression_stats", |
|
4376 |
+ "S": 1000, |
|
4377 |
+ "n": 3900, |
|
4378 |
+ "elements": 3900000, |
|
4379 |
+ "backend": "metal", |
|
4380 |
+ "threads": 0, |
|
4381 |
+ "median_s": 0.003796167206019163, |
|
4382 |
+ "ci_lo": 0.0033167502842843533, |
|
4383 |
+ "ci_hi": 0.004350459203124046, |
|
4384 |
+ "device_s": 0.000579125015065074, |
|
4385 |
+ "elements_per_s": 1027352007.5238521, |
|
4386 |
+ "reps": 5, |
|
4387 |
+ "precision": "fp32", |
|
4388 |
+ "peak_rss_mb": 781.1072, |
|
4389 |
+ "speedup_vs_cpu_mt": 0.9013804482638873, |
|
4390 |
+ "speedup_vs_cpu_1t": 9.060761582722323, |
|
4391 |
+ "cpu_mt_median_s": 0.003421790897846222, |
|
4392 |
+ "cpu_1t_median_s": 0.03439616598188877, |
|
4393 |
+ "metal_wins_vs_mt": false, |
|
4394 |
+ "cpu_wins_vs_mt": false |
|
4395 |
+ }, |
|
4396 |
+ { |
|
4397 |
+ "kernel": "regression_stats", |
|
4398 |
+ "S": 1000, |
|
4399 |
+ "n": 39000, |
|
4400 |
+ "elements": 39000000, |
|
4401 |
+ "backend": "metal", |
|
4402 |
+ "threads": 0, |
|
4403 |
+ "median_s": 0.026743208058178425, |
|
4404 |
+ "ci_lo": 0.025766875129193068, |
|
4405 |
+ "ci_hi": 0.02711204206570983, |
|
4406 |
+ "device_s": 0.004475083318538964, |
|
4407 |
+ "elements_per_s": 1458314197.5771036, |
|
4408 |
+ "reps": 5, |
|
4409 |
+ "precision": "fp32", |
|
4410 |
+ "peak_rss_mb": 3360.11264, |
|
4411 |
+ "speedup_vs_cpu_mt": 1.1681813469411308, |
|
4412 |
+ "speedup_vs_cpu_1t": 12.11658580559542, |
|
4413 |
+ "cpu_mt_median_s": 0.031240916810929775, |
|
4414 |
+ "cpu_1t_median_s": 0.3240363751538098, |
|
4415 |
+ "metal_wins_vs_mt": true, |
|
4416 |
+ "cpu_wins_vs_mt": false |
|
4417 |
+ }, |
|
4418 |
+ { |
|
4419 |
+ "kernel": "regression_stats", |
|
4420 |
+ "S": 10000, |
|
4421 |
+ "n": 390, |
|
4422 |
+ "elements": 3900000, |
|
4423 |
+ "backend": "metal", |
|
4424 |
+ "threads": 0, |
|
4425 |
+ "median_s": 0.004190749954432249, |
|
4426 |
+ "ci_lo": 0.00392800010740757, |
|
4427 |
+ "ci_hi": 0.005979666020721197, |
|
4428 |
+ "device_s": 0.0011161250295117497, |
|
4429 |
+ "elements_per_s": 930621020.6779948, |
|
4430 |
+ "reps": 5, |
|
4431 |
+ "precision": "fp32", |
|
4432 |
+ "peak_rss_mb": 3432.742912, |
|
4433 |
+ "speedup_vs_cpu_mt": 0.944759231194123, |
|
4434 |
+ "speedup_vs_cpu_1t": 7.312414252819052, |
|
4435 |
+ "cpu_mt_median_s": 0.003959249705076218, |
|
4436 |
+ "cpu_1t_median_s": 0.030644499696791172, |
|
4437 |
+ "metal_wins_vs_mt": false, |
|
4438 |
+ "cpu_wins_vs_mt": false |
|
4439 |
+ }, |
|
4440 |
+ { |
|
4441 |
+ "kernel": "regression_stats", |
|
4442 |
+ "S": 10000, |
|
4443 |
+ "n": 3900, |
|
4444 |
+ "elements": 39000000, |
|
4445 |
+ "backend": "metal", |
|
4446 |
+ "threads": 0, |
|
4447 |
+ "median_s": 0.026574499905109406, |
|
4448 |
+ "ci_lo": 0.026411292143166065, |
|
4449 |
+ "ci_hi": 0.026990290731191635, |
|
4450 |
+ "device_s": 0.004499250091612339, |
|
4451 |
+ "elements_per_s": 1467572301.9909616, |
|
4452 |
+ "reps": 5, |
|
4453 |
+ "precision": "fp32", |
|
4454 |
+ "peak_rss_mb": 3221.83168, |
|
4455 |
+ "speedup_vs_cpu_mt": 1.4107556096287706, |
|
4456 |
+ "speedup_vs_cpu_1t": 13.430701182218417, |
|
4457 |
+ "cpu_mt_median_s": 0.03749012481421232, |
|
4458 |
+ "cpu_1t_median_s": 0.3569141672924161, |
|
4459 |
+ "metal_wins_vs_mt": true, |
|
4460 |
+ "cpu_wins_vs_mt": false |
|
4461 |
+ }, |
|
4462 |
+ { |
|
4463 |
+ "kernel": "rolling_sumsq", |
|
4464 |
+ "S": 1, |
|
4465 |
+ "n": 390, |
|
4466 |
+ "elements": 390, |
|
4467 |
+ "backend": "metal", |
|
4468 |
+ "threads": 0, |
|
4469 |
+ "median_s": 0.0002839169465005398, |
|
4470 |
+ "ci_lo": 0.0001594587229192257, |
|
4471 |
+ "ci_hi": 0.0008917916566133499, |
|
4472 |
+ "device_s": 1.8750084564089775e-05, |
|
4473 |
+ "elements_per_s": 1373641.146845944, |
|
4474 |
+ "reps": 5, |
|
4475 |
+ "precision": "fp32", |
|
4476 |
+ "peak_rss_mb": 3253.567488, |
|
4477 |
+ "speedup_vs_cpu_mt": 0.0027898646399008046, |
|
4478 |
+ "speedup_vs_cpu_1t": 0.003373751654483219, |
|
4479 |
+ "cpu_mt_median_s": 7.920898497104645e-07, |
|
4480 |
+ "cpu_1t_median_s": 9.578652679920197e-07, |
|
4481 |
+ "metal_wins_vs_mt": false, |
|
4482 |
+ "cpu_wins_vs_mt": true |
|
4483 |
+ }, |
|
4484 |
+ { |
|
4485 |
+ "kernel": "rolling_sumsq", |
|
4486 |
+ "S": 1, |
|
4487 |
+ "n": 3900, |
|
4488 |
+ "elements": 3900, |
|
4489 |
+ "backend": "metal", |
|
4490 |
+ "threads": 0, |
|
4491 |
+ "median_s": 0.0002416251227259636, |
|
4492 |
+ "ci_lo": 0.0001499168574810028, |
|
4493 |
+ "ci_hi": 0.0002560419961810112, |
|
4494 |
+ "device_s": 4.958361387252808e-06, |
|
4495 |
+ "elements_per_s": 16140705.718018986, |
|
4496 |
+ "reps": 5, |
|
4497 |
+ "precision": "fp32", |
|
4498 |
+ "peak_rss_mb": 2962.440192, |
|
4499 |
+ "speedup_vs_cpu_mt": 0.031039573239594054, |
|
4500 |
+ "speedup_vs_cpu_1t": 0.031039573239594054, |
|
4501 |
+ "cpu_mt_median_s": 7.4999406933784485e-06, |
|
4502 |
+ "cpu_1t_median_s": 7.4999406933784485e-06, |
|
4503 |
+ "metal_wins_vs_mt": false, |
|
4504 |
+ "cpu_wins_vs_mt": true |
|
4505 |
+ }, |
|
4506 |
+ { |
|
4507 |
+ "kernel": "rolling_sumsq", |
|
4508 |
+ "S": 1, |
|
4509 |
+ "n": 39000, |
|
4510 |
+ "elements": 39000, |
|
4511 |
+ "backend": "metal", |
|
4512 |
+ "threads": 0, |
|
4513 |
+ "median_s": 0.00016458332538604736, |
|
4514 |
+ "ci_lo": 0.00015858327969908714, |
|
4515 |
+ "ci_hi": 0.00017341692000627518, |
|
4516 |
+ "device_s": 1.9583385437726974e-05, |
|
4517 |
+ "elements_per_s": 236962036.75871435, |
|
4518 |
+ "reps": 5, |
|
4519 |
+ "precision": "fp32", |
|
4520 |
+ "peak_rss_mb": 2962.440192, |
|
4521 |
+ "speedup_vs_cpu_mt": 0.42683623811679494, |
|
4522 |
+ "speedup_vs_cpu_1t": 0.4212624490719783, |
|
4523 |
+ "cpu_mt_median_s": 7.025012746453285e-05, |
|
4524 |
+ "cpu_1t_median_s": 6.93327747285366e-05, |
|
4525 |
+ "metal_wins_vs_mt": false, |
|
4526 |
+ "cpu_wins_vs_mt": true |
|
4527 |
+ }, |
|
4528 |
+ { |
|
4529 |
+ "kernel": "rolling_sumsq", |
|
4530 |
+ "S": 1, |
|
4531 |
+ "n": 390000, |
|
4532 |
+ "elements": 390000, |
|
4533 |
+ "backend": "metal", |
|
4534 |
+ "threads": 0, |
|
4535 |
+ "median_s": 0.0007903752848505974, |
|
4536 |
+ "ci_lo": 0.000574291218072176, |
|
4537 |
+ "ci_hi": 0.0009351670742034912, |
|
4538 |
+ "device_s": 6.225006654858589e-05, |
|
4539 |
+ "elements_per_s": 493436481.97921664, |
|
4540 |
+ "reps": 5, |
|
4541 |
+ "precision": "fp32", |
|
4542 |
+ "peak_rss_mb": 2962.440192, |
|
4543 |
+ "speedup_vs_cpu_mt": 0.909589128259996, |
|
4544 |
+ "speedup_vs_cpu_1t": 0.8747948233625048, |
|
4545 |
+ "cpu_mt_median_s": 0.000718916766345501, |
|
4546 |
+ "cpu_1t_median_s": 0.0006914162077009678, |
|
4547 |
+ "metal_wins_vs_mt": false, |
|
4548 |
+ "cpu_wins_vs_mt": false |
|
4549 |
+ }, |
|
4550 |
+ { |
|
4551 |
+ "kernel": "rolling_sumsq", |
|
4552 |
+ "S": 10, |
|
4553 |
+ "n": 390, |
|
4554 |
+ "elements": 3900, |
|
4555 |
+ "backend": "metal", |
|
4556 |
+ "threads": 0, |
|
4557 |
+ "median_s": 0.0002032076008617878, |
|
4558 |
+ "ci_lo": 0.00014958297833800316, |
|
4559 |
+ "ci_hi": 0.0006746253930032253, |
|
4560 |
+ "device_s": 1.4499993994832039e-05, |
|
4561 |
+ "elements_per_s": 19192195.486095995, |
|
4562 |
+ "reps": 5, |
|
4563 |
+ "precision": "fp32", |
|
4564 |
+ "peak_rss_mb": 17.170432, |
|
4565 |
+ "speedup_vs_cpu_mt": 0.08858003826895974, |
|
4566 |
+ "speedup_vs_cpu_1t": 0.03526473183083745, |
|
4567 |
+ "cpu_mt_median_s": 1.800013706088066e-05, |
|
4568 |
+ "cpu_1t_median_s": 7.1660615503787994e-06, |
|
4569 |
+ "metal_wins_vs_mt": false, |
|
4570 |
+ "cpu_wins_vs_mt": true |
|
4571 |
+ }, |
|
4572 |
+ { |
|
4573 |
+ "kernel": "rolling_sumsq", |
|
4574 |
+ "S": 10, |
|
4575 |
+ "n": 3900, |
|
4576 |
+ "elements": 39000, |
|
4577 |
+ "backend": "metal", |
|
4578 |
+ "threads": 0, |
|
4579 |
+ "median_s": 0.00016070762649178505, |
|
4580 |
+ "ci_lo": 0.00014404207468032837, |
|
4581 |
+ "ci_hi": 0.00017450004816055298, |
|
4582 |
+ "device_s": 1.9625062122941017e-05, |
|
4583 |
+ "elements_per_s": 242676722.01601195, |
|
4584 |
+ "reps": 5, |
|
4585 |
+ "precision": "fp32", |
|
4586 |
+ "peak_rss_mb": 2962.440192, |
|
4587 |
+ "speedup_vs_cpu_mt": 0.2792328398774908, |
|
4588 |
+ "speedup_vs_cpu_1t": 0.4311610265504162, |
|
4589 |
+ "cpu_mt_median_s": 4.487484693527222e-05, |
|
4590 |
+ "cpu_1t_median_s": 6.929086521267891e-05, |
|
4591 |
+ "metal_wins_vs_mt": false, |
|
4592 |
+ "cpu_wins_vs_mt": true |
|
4593 |
+ }, |
|
4594 |
+ { |
|
4595 |
+ "kernel": "rolling_sumsq", |
|
4596 |
+ "S": 10, |
|
4597 |
+ "n": 39000, |
|
4598 |
+ "elements": 390000, |
|
4599 |
+ "backend": "metal", |
|
4600 |
+ "threads": 0, |
|
4601 |
+ "median_s": 0.0007357923313975334, |
|
4602 |
+ "ci_lo": 0.0007097921334207058, |
|
4603 |
+ "ci_hi": 0.0007738331332802773, |
|
4604 |
+ "device_s": 9.062490426003933e-05, |
|
4605 |
+ "elements_per_s": 530040859.8432253, |
|
4606 |
+ "reps": 5, |
|
4607 |
+ "precision": "fp32", |
|
4608 |
+ "peak_rss_mb": 3431.46496, |
|
4609 |
+ "speedup_vs_cpu_mt": 0.18036050837224432, |
|
4610 |
+ "speedup_vs_cpu_1t": 0.9643225563919291, |
|
4611 |
+ "cpu_mt_median_s": 0.000132707878947258, |
|
4612 |
+ "cpu_1t_median_s": 0.0007095411419868469, |
|
4613 |
+ "metal_wins_vs_mt": false, |
|
4614 |
+ "cpu_wins_vs_mt": true |
|
4615 |
+ }, |
|
4616 |
+ { |
|
4617 |
+ "kernel": "rolling_sumsq", |
|
4618 |
+ "S": 10, |
|
4619 |
+ "n": 390000, |
|
4620 |
+ "elements": 3900000, |
|
4621 |
+ "backend": "metal", |
|
4622 |
+ "threads": 0, |
|
4623 |
+ "median_s": 0.002544207964092493, |
|
4624 |
+ "ci_lo": 0.0024965000338852406, |
|
4625 |
+ "ci_hi": 0.0026084999553859234, |
|
4626 |
+ "device_s": 0.00076149997767061, |
|
4627 |
+ "elements_per_s": 1532893558.6407974, |
|
4628 |
+ "reps": 5, |
|
4629 |
+ "precision": "fp32", |
|
4630 |
+ "peak_rss_mb": 3253.567488, |
|
4631 |
+ "speedup_vs_cpu_mt": 0.6940765734230536, |
|
4632 |
+ "speedup_vs_cpu_1t": 2.7174959207635196, |
|
4633 |
+ "cpu_mt_median_s": 0.0017658751457929611, |
|
4634 |
+ "cpu_1t_median_s": 0.006913874763995409, |
|
4635 |
+ "metal_wins_vs_mt": false, |
|
4636 |
+ "cpu_wins_vs_mt": true |
|
4637 |
+ }, |
|
4638 |
+ { |
|
4639 |
+ "kernel": "rolling_sumsq", |
|
4640 |
+ "S": 100, |
|
4641 |
+ "n": 390, |
|
4642 |
+ "elements": 39000, |
|
4643 |
+ "backend": "metal", |
|
4644 |
+ "threads": 0, |
|
4645 |
+ "median_s": 0.0002676667645573616, |
|
4646 |
+ "ci_lo": 0.00017749983817338943, |
|
4647 |
+ "ci_hi": 0.0007679169066250324, |
|
4648 |
+ "device_s": 9.541632607579231e-06, |
|
4649 |
+ "elements_per_s": 145703558.1705259, |
|
4650 |
+ "reps": 5, |
|
4651 |
+ "precision": "fp32", |
|
4652 |
+ "peak_rss_mb": 2962.440192, |
|
4653 |
+ "speedup_vs_cpu_mt": 0.6718550477549103, |
|
4654 |
+ "speedup_vs_cpu_1t": 0.2612097910613942, |
|
4655 |
+ "cpu_mt_median_s": 0.00017983326688408852, |
|
4656 |
+ "cpu_1t_median_s": 6.991717964410782e-05, |
|
4657 |
+ "metal_wins_vs_mt": false, |
|
4658 |
+ "cpu_wins_vs_mt": false |
|
4659 |
+ }, |
|
4660 |
+ { |
|
4661 |
+ "kernel": "rolling_sumsq", |
|
4662 |
+ "S": 100, |
|
4663 |
+ "n": 3900, |
|
4664 |
+ "elements": 390000, |
|
4665 |
+ "backend": "metal", |
|
4666 |
+ "threads": 0, |
|
4667 |
+ "median_s": 0.0006820829585194588, |
|
4668 |
+ "ci_lo": 0.0003593750298023224, |
|
4669 |
+ "ci_hi": 0.0008333330042660236, |
|
4670 |
+ "device_s": 9.058334399014711e-05, |
|
4671 |
+ "elements_per_s": 571777956.2277012, |
|
4672 |
+ "reps": 5, |
|
4673 |
+ "precision": "fp32", |
|
4674 |
+ "peak_rss_mb": 3431.530496, |
|
4675 |
+ "speedup_vs_cpu_mt": 0.2978012810272249, |
|
4676 |
+ "speedup_vs_cpu_1t": 1.1826521987872431, |
|
4677 |
+ "cpu_mt_median_s": 0.00020312517881393433, |
|
4678 |
+ "cpu_1t_median_s": 0.000806666910648346, |
|
4679 |
+ "metal_wins_vs_mt": false, |
|
4680 |
+ "cpu_wins_vs_mt": true |
|
4681 |
+ }, |
|
4682 |
+ { |
|
4683 |
+ "kernel": "rolling_sumsq", |
|
4684 |
+ "S": 100, |
|
4685 |
+ "n": 39000, |
|
4686 |
+ "elements": 3900000, |
|
4687 |
+ "backend": "metal", |
|
4688 |
+ "threads": 0, |
|
4689 |
+ "median_s": 0.002226833254098892, |
|
4690 |
+ "ci_lo": 0.0021508331410586834, |
|
4691 |
+ "ci_hi": 0.002632542047649622, |
|
4692 |
+ "device_s": 0.00043350004125386477, |
|
4693 |
+ "elements_per_s": 1751365978.0413911, |
|
4694 |
+ "reps": 5, |
|
4695 |
+ "precision": "fp32", |
|
4696 |
+ "peak_rss_mb": 3431.87456, |
|
4697 |
+ "speedup_vs_cpu_mt": 0.4883431672524638, |
|
4698 |
+ "speedup_vs_cpu_1t": 3.2953184884928928, |
|
4699 |
+ "cpu_mt_median_s": 0.0010874588042497635, |
|
4700 |
+ "cpu_1t_median_s": 0.007338124793022871, |
|
4701 |
+ "metal_wins_vs_mt": false, |
|
4702 |
+ "cpu_wins_vs_mt": true |
|
4703 |
+ }, |
|
4704 |
+ { |
|
4705 |
+ "kernel": "rolling_sumsq", |
|
4706 |
+ "S": 100, |
|
4707 |
+ "n": 390000, |
|
4708 |
+ "elements": 39000000, |
|
4709 |
+ "backend": "metal", |
|
4710 |
+ "threads": 0, |
|
4711 |
+ "median_s": 0.014852333813905716, |
|
4712 |
+ "ci_lo": 0.014340042136609554, |
|
4713 |
+ "ci_hi": 0.01528970804065466, |
|
4714 |
+ "device_s": 0.0023322500055655837, |
|
4715 |
+ "elements_per_s": 2625849949.823083, |
|
4716 |
+ "reps": 5, |
|
4717 |
+ "precision": "fp32", |
|
4718 |
+ "peak_rss_mb": 3255.451648, |
|
4719 |
+ "speedup_vs_cpu_mt": 0.6337920907333103, |
|
4720 |
+ "speedup_vs_cpu_1t": 4.687593885765181, |
|
4721 |
+ "cpu_mt_median_s": 0.009413291700184345, |
|
4722 |
+ "cpu_1t_median_s": 0.06962170917540789, |
|
4723 |
+ "metal_wins_vs_mt": false, |
|
4724 |
+ "cpu_wins_vs_mt": true |
|
4725 |
+ }, |
|
4726 |
+ { |
|
4727 |
+ "kernel": "rolling_sumsq", |
|
4728 |
+ "S": 1000, |
|
4729 |
+ "n": 390, |
|
4730 |
+ "elements": 390000, |
|
4731 |
+ "backend": "metal", |
|
4732 |
+ "threads": 0, |
|
4733 |
+ "median_s": 0.0009075421839952469, |
|
4734 |
+ "ci_lo": 0.000882917083799839, |
|
4735 |
+ "ci_hi": 0.000995416659861803, |
|
4736 |
+ "device_s": 2.3708329536020756e-05, |
|
4737 |
+ "elements_per_s": 429732090.5603684, |
|
4738 |
+ "reps": 5, |
|
4739 |
+ "precision": "fp32", |
|
4740 |
+ "peak_rss_mb": 2962.440192, |
|
4741 |
+ "speedup_vs_cpu_mt": 0.29870103215504695, |
|
4742 |
+ "speedup_vs_cpu_1t": 0.7921117822479183, |
|
4743 |
+ "cpu_mt_median_s": 0.0002710837870836258, |
|
4744 |
+ "cpu_1t_median_s": 0.0007188748568296432, |
|
4745 |
+ "metal_wins_vs_mt": false, |
|
4746 |
+ "cpu_wins_vs_mt": true |
|
4747 |
+ }, |
|
4748 |
+ { |
|
4749 |
+ "kernel": "rolling_sumsq", |
|
4750 |
+ "S": 1000, |
|
4751 |
+ "n": 3900, |
|
4752 |
+ "elements": 3900000, |
|
4753 |
+ "backend": "metal", |
|
4754 |
+ "threads": 0, |
|
4755 |
+ "median_s": 0.002144791651517153, |
|
4756 |
+ "ci_lo": 0.0021287081763148308, |
|
4757 |
+ "ci_hi": 0.0034982911311089993, |
|
4758 |
+ "device_s": 0.0007578750373795629, |
|
4759 |
+ "elements_per_s": 1818358439.264379, |
|
4760 |
+ "reps": 5, |
|
4761 |
+ "precision": "fp32", |
|
4762 |
+ "peak_rss_mb": 3431.497728, |
|
4763 |
+ "speedup_vs_cpu_mt": 0.47898947112456725, |
|
4764 |
+ "speedup_vs_cpu_1t": 3.242467441252045, |
|
4765 |
+ "cpu_mt_median_s": 0.0010273326188325882, |
|
4766 |
+ "cpu_1t_median_s": 0.00695441709831357, |
|
4767 |
+ "metal_wins_vs_mt": false, |
|
4768 |
+ "cpu_wins_vs_mt": true |
|
4769 |
+ }, |
|
4770 |
+ { |
|
4771 |
+ "kernel": "rolling_sumsq", |
|
4772 |
+ "S": 1000, |
|
4773 |
+ "n": 39000, |
|
4774 |
+ "elements": 39000000, |
|
4775 |
+ "backend": "metal", |
|
4776 |
+ "threads": 0, |
|
4777 |
+ "median_s": 0.014728832989931107, |
|
4778 |
+ "ci_lo": 0.014530166983604431, |
|
4779 |
+ "ci_hi": 0.01593674998730421, |
|
4780 |
+ "device_s": 0.002570083364844322, |
|
4781 |
+ "elements_per_s": 2647867623.094178, |
|
4782 |
+ "reps": 5, |
|
4783 |
+ "precision": "fp32", |
|
4784 |
+ "peak_rss_mb": 3368.894464, |
|
4785 |
+ "speedup_vs_cpu_mt": 0.5643550943271196, |
|
4786 |
+ "speedup_vs_cpu_1t": 4.770453192305718, |
|
4787 |
+ "cpu_mt_median_s": 0.00831229193136096, |
|
4788 |
+ "cpu_1t_median_s": 0.07026320835575461, |
|
4789 |
+ "metal_wins_vs_mt": false, |
|
4790 |
+ "cpu_wins_vs_mt": true |
|
4791 |
+ }, |
|
4792 |
+ { |
|
4793 |
+ "kernel": "rolling_sumsq", |
|
4794 |
+ "S": 10000, |
|
4795 |
+ "n": 390, |
|
4796 |
+ "elements": 3900000, |
|
4797 |
+ "backend": "metal", |
|
4798 |
+ "threads": 0, |
|
4799 |
+ "median_s": 0.0021627498790621758, |
|
4800 |
+ "ci_lo": 0.002053916919976473, |
|
4801 |
+ "ci_hi": 0.0022570830769836903, |
|
4802 |
+ "device_s": 0.0002617916325107217, |
|
4803 |
+ "elements_per_s": 1803259839.5941842, |
|
4804 |
+ "reps": 5, |
|
4805 |
+ "precision": "fp32", |
|
4806 |
+ "peak_rss_mb": 3431.858176, |
|
4807 |
+ "speedup_vs_cpu_mt": 0.49574203299838304, |
|
4808 |
+ "speedup_vs_cpu_1t": 3.2587757053011432, |
|
4809 |
+ "cpu_mt_median_s": 0.00107216602191329, |
|
4810 |
+ "cpu_1t_median_s": 0.007047916762530804, |
|
4811 |
+ "metal_wins_vs_mt": false, |
|
4812 |
+ "cpu_wins_vs_mt": true |
|
4813 |
+ }, |
|
4814 |
+ { |
|
4815 |
+ "kernel": "rolling_sumsq", |
|
4816 |
+ "S": 10000, |
|
4817 |
+ "n": 3900, |
|
4818 |
+ "elements": 39000000, |
|
4819 |
+ "backend": "metal", |
|
4820 |
+ "threads": 0, |
|
4821 |
+ "median_s": 0.014753291849046946, |
|
4822 |
+ "ci_lo": 0.01457533286884427, |
|
4823 |
+ "ci_hi": 0.01564762508496642, |
|
4824 |
+ "device_s": 0.0025377500569447875, |
|
4825 |
+ "elements_per_s": 2643477835.254739, |
|
4826 |
+ "reps": 5, |
|
4827 |
+ "precision": "fp32", |
|
4828 |
+ "peak_rss_mb": 2962.440192, |
|
4829 |
+ "speedup_vs_cpu_mt": 0.4434970991671636, |
|
4830 |
+ "speedup_vs_cpu_1t": 4.6922437792300995, |
|
4831 |
+ "cpu_mt_median_s": 0.00654304213821888, |
|
4832 |
+ "cpu_1t_median_s": 0.06922604190185666, |
|
4833 |
+ "metal_wins_vs_mt": false, |
|
4834 |
+ "cpu_wins_vs_mt": true |
|
4835 |
+ } |
|
4836 |
+ ], |
|
4837 |
+ "breakeven": { |
|
4838 |
+ "garch_nll_P1": { |
|
4839 |
+ "smallest_metal_win_elements": null, |
|
4840 |
+ "largest_cpu_win_elements": 39000000, |
|
4841 |
+ "max_speedup_vs_mt": 0.33211607376881125, |
|
4842 |
+ "n_cases": 10 |
|
4843 |
+ }, |
|
4844 |
+ "garch_nll_P64": { |
|
4845 |
+ "smallest_metal_win_elements": 39000, |
|
4846 |
+ "largest_cpu_win_elements": 39000, |
|
4847 |
+ "max_speedup_vs_mt": 7.934195016316967, |
|
4848 |
+ "n_cases": 8 |
|
4849 |
+ }, |
|
4850 |
+ "realized_fused": { |
|
4851 |
+ "smallest_metal_win_elements": 39000, |
|
4852 |
+ "largest_cpu_win_elements": 39000, |
|
4853 |
+ "max_speedup_vs_mt": 3.4364769430726474, |
|
4854 |
+ "n_cases": 17 |
|
4855 |
+ }, |
|
4856 |
+ "regression_stats": { |
|
4857 |
+ "smallest_metal_win_elements": 390000, |
|
4858 |
+ "largest_cpu_win_elements": 390000, |
|
4859 |
+ "max_speedup_vs_mt": 3.851129874745179, |
|
4860 |
+ "n_cases": 17 |
|
4861 |
+ }, |
|
4862 |
+ "rolling_sumsq": { |
|
4863 |
+ "smallest_metal_win_elements": null, |
|
4864 |
+ "largest_cpu_win_elements": 39000000, |
|
4865 |
+ "max_speedup_vs_mt": 0.909589128259996, |
|
4866 |
+ "n_cases": 17 |
|
4867 |
+ } |
|
4868 |
+ }, |
|
4869 |
+ "shader_library": [ |
|
4870 |
+ { |
|
4871 |
+ "backend": "metal", |
|
4872 |
+ "compiled_now": false, |
|
4873 |
+ "kernel": "shader_library_load", |
|
4874 |
+ "note": "metallib:/Users/simon-pierreboucher/Desktop/UQO/Recherche/Recherche-UQO/finance/wp40_raid/build/macos-release/raid.metallib chunks=1 convert_s=0.000001", |
|
4875 |
+ "seconds": 0.000230708, |
|
4876 |
+ "t": 0.03212570771574974, |
|
4877 |
+ "wall_first_call": 0.013961625 |
|
4878 |
+ } |
|
4879 |
+ ] |
|
4880 |
+} |
|
|
\ No newline at end of file |