1{2 "primitives": {3 "realized_fused@1x390": {4 "cpu1_ms": 0.0014998950064182281,5 "cpuMT_ms": 0.0014998950064182281,6 "metal_ms": 0.2344171516597271,7 "speedup": 0.006398401293585508,8 "verdict": "CPU"9 },10 "realized_fused@1x3900": {11 "cpu1_ms": 0.011624768376350403,12 "cpuMT_ms": 0.01116609200835228,13 "metal_ms": 0.6333747878670692,14 "speedup": 0.017629517660396336,15 "verdict": "CPU"16 },17 "realized_fused@10x390": {18 "cpu1_ms": 0.011292286217212677,19 "cpuMT_ms": 0.14200014993548393,20 "metal_ms": 0.2327919937670231,21 "speedup": 0.6099872578848089,22 "verdict": "CPU"23 },24 "realized_fused@1x39000": {25 "cpu1_ms": 0.18258299678564072,26 "cpuMT_ms": 0.1671668142080307,27 "metal_ms": 0.206624623388052,28 "speedup": 0.8090362681222294,29 "verdict": "CPU"30 },31 "realized_fused@10x3900": {32 "cpu1_ms": 0.18791621550917625,33 "cpuMT_ms": 0.135000329464674,34 "metal_ms": 0.16404176130890846,35 "speedup": 0.8229631795433707,36 "verdict": "CPU"37 },38 "realized_fused@100x390": {39 "cpu1_ms": 0.1871250569820404,40 "cpuMT_ms": 0.5520828999578953,41 "metal_ms": 0.22633420303463936,42 "speedup": 2.4392376077309077,43 "verdict": "Metal"44 },45 "realized_fused@1x390000": {46 "cpu1_ms": 2.032375428825617,47 "cpuMT_ms": 2.0858747884631157,48 "metal_ms": 0.9353337809443474,49 "speedup": 2.2300860195139536,50 "verdict": "Metal"51 },52 "realized_fused@10x39000": {53 "cpu1_ms": 2.572625409811735,54 "cpuMT_ms": 0.36349985748529434,55 "metal_ms": 0.7184999994933605,56 "speedup": 0.5059149029110798,57 "verdict": "tie"58 },59 "realized_fused@100x3900": {60 "cpu1_ms": 2.043417189270258,61 "cpuMT_ms": 0.6015831604599953,62 "metal_ms": 0.6413329392671585,63 "speedup": 0.9380200573315559,64 "verdict": "tie"65 },66 "realized_fused@1000x390": {67 "cpu1_ms": 2.235791180282831,68 "cpuMT_ms": 0.8399169892072678,69 "metal_ms": 0.33845799043774605,70 "speedup": 2.4815989367571367,71 "verdict": "Metal"72 },73 "realized_fused@10x390000": {74 "cpu1_ms": 20.89220890775323,75 "cpuMT_ms": 2.5267917662858963,76 "metal_ms": 1.0219174437224865,77 "speedup": 2.4725987229278337,78 "verdict": "Metal"79 },80 "realized_fused@100x39000": {81 "cpu1_ms": 20.590624772012234,82 "cpuMT_ms": 2.1904585883021355,83 "metal_ms": 1.1692089028656483,84 "speedup": 1.8734535658542084,85 "verdict": "Metal"86 },87 "realized_fused@1000x3900": {88 "cpu1_ms": 21.244540810585022,89 "cpuMT_ms": 1.7422502860426903,90 "metal_ms": 0.8750832639634609,91 "speedup": 1.9909537272506195,92 "verdict": "Metal"93 },94 "realized_fused@10000x390": {95 "cpu1_ms": 21.238334011286497,96 "cpuMT_ms": 2.125917002558708,97 "metal_ms": 2.2132499143481255,98 "speedup": 0.9605408719443508,99 "verdict": "tie"100 },101 "realized_fused@100x390000": {102 "cpu1_ms": 232.5868341140449,103 "cpuMT_ms": 18.79258267581463,104 "metal_ms": 8.720249868929386,105 "speedup": 2.1550509398559075,106 "verdict": "Metal"107 },108 "realized_fused@1000x39000": {109 "cpu1_ms": 238.77166723832488,110 "cpuMT_ms": 20.24729223921895,111 "metal_ms": 5.891874898225069,112 "speedup": 3.4364769430726474,113 "verdict": "Metal"114 },115 "realized_fused@10000x3900": {116 "cpu1_ms": 233.6724577471614,117 "cpuMT_ms": 15.69391693919897,118 "metal_ms": 7.8027499839663506,119 "speedup": 2.0113315140749037,120 "verdict": "Metal"121 },122 "regression_stats@1x390": {123 "cpu1_ms": 0.0031669624149799347,124 "cpuMT_ms": 0.0032088719308376312,125 "metal_ms": 0.894167460501194,126 "speedup": 0.003588669989219929,127 "verdict": "CPU"128 },129 "regression_stats@1x3900": {130 "cpu1_ms": 0.029958784580230713,131 "cpuMT_ms": 0.030207913368940353,132 "metal_ms": 0.3482499159872532,133 "speedup": 0.0867420550075482,134 "verdict": "CPU"135 },136 "regression_stats@10x390": {137 "cpu1_ms": 0.031250063329935074,138 "cpuMT_ms": 0.04133302718400955,139 "metal_ms": 0.6523327901959419,140 "speedup": 0.06336187265949686,141 "verdict": "CPU"142 },143 "regression_stats@1x39000": {144 "cpu1_ms": 0.30233291909098625,145 "cpuMT_ms": 0.3838753327727318,146 "metal_ms": 0.4085828550159931,147 "speedup": 0.9395287346496851,148 "verdict": "tie"149 },150 "regression_stats@10x3900": {151 "cpu1_ms": 0.2997498959302902,152 "cpuMT_ms": 0.07625017315149307,153 "metal_ms": 0.36174990236759186,154 "speedup": 0.2107814615911396,155 "verdict": "CPU"156 },157 "regression_stats@100x390": {158 "cpu1_ms": 0.36137504503130913,159 "cpuMT_ms": 0.17625000327825546,160 "metal_ms": 0.3363746218383312,161 "speedup": 0.5239693836444206,162 "verdict": "CPU"163 },164 "regression_stats@1x390000": {165 "cpu1_ms": 2.9733749106526375,166 "cpuMT_ms": 3.0428748577833176,167 "metal_ms": 0.7901252247393131,168 "speedup": 3.851129874745179,169 "verdict": "Metal"170 },171 "regression_stats@10x39000": {172 "cpu1_ms": 3.083667252212763,173 "cpuMT_ms": 0.5624173209071159,174 "metal_ms": 0.6961673498153687,175 "speedup": 0.8078766133692931,176 "verdict": "CPU"177 },178 "regression_stats@100x3900": {179 "cpu1_ms": 2.9982919804751873,180 "cpuMT_ms": 0.4399162717163563,181 "metal_ms": 0.5946666933596134,182 "speedup": 0.739769482011876,183 "verdict": "CPU"184 },185 "regression_stats@1000x390": {186 "cpu1_ms": 3.1211250461637974,187 "cpuMT_ms": 0.6971252150833607,188 "metal_ms": 0.5814996547996998,189 "speedup": 1.1988402904959397,190 "verdict": "tie"191 },192 "regression_stats@10x390000": {193 "cpu1_ms": 32.662583980709314,194 "cpuMT_ms": 6.654791999608278,195 "metal_ms": 4.117042291909456,196 "speedup": 1.6164011753500427,197 "verdict": "Metal"198 },199 "regression_stats@100x39000": {200 "cpu1_ms": 32.19050029292703,201 "cpuMT_ms": 3.1737093813717365,202 "metal_ms": 4.4694580137729645,203 "speedup": 0.7100881967325159,204 "verdict": "tie"205 },206 "regression_stats@1000x3900": {207 "cpu1_ms": 34.39616598188877,208 "cpuMT_ms": 3.421790897846222,209 "metal_ms": 3.796167206019163,210 "speedup": 0.9013804482638873,211 "verdict": "tie"212 },213 "regression_stats@10000x390": {214 "cpu1_ms": 30.644499696791172,215 "cpuMT_ms": 3.9592497050762177,216 "metal_ms": 4.190749954432249,217 "speedup": 0.944759231194123,218 "verdict": "tie"219 },220 "regression_stats@100x390000": {221 "cpu1_ms": 301.3692502863705,222 "cpuMT_ms": 33.760249614715576,223 "metal_ms": 30.70899983868003,224 "speedup": 1.0993601156685116,225 "verdict": "Metal"226 },227 "regression_stats@1000x39000": {228 "cpu1_ms": 324.0363751538098,229 "cpuMT_ms": 31.240916810929775,230 "metal_ms": 26.743208058178425,231 "speedup": 1.1681813469411308,232 "verdict": "Metal"233 },234 "regression_stats@10000x3900": {235 "cpu1_ms": 356.9141672924161,236 "cpuMT_ms": 37.49012481421232,237 "metal_ms": 26.574499905109406,238 "speedup": 1.4107556096287706,239 "verdict": "Metal"240 },241 "rolling_sumsq@1x390": {242 "cpu1_ms": 0.0009578652679920197,243 "cpuMT_ms": 0.0007920898497104645,244 "metal_ms": 0.2839169465005398,245 "speedup": 0.0027898646399008046,246 "verdict": "CPU"247 },248 "rolling_sumsq@1x3900": {249 "cpu1_ms": 0.0074999406933784485,250 "cpuMT_ms": 0.0074999406933784485,251 "metal_ms": 0.2416251227259636,252 "speedup": 0.031039573239594054,253 "verdict": "CPU"254 },255 "rolling_sumsq@10x390": {256 "cpu1_ms": 0.0071660615503787994,257 "cpuMT_ms": 0.01800013706088066,258 "metal_ms": 0.2032076008617878,259 "speedup": 0.08858003826895974,260 "verdict": "CPU"261 },262 "rolling_sumsq@1x39000": {263 "cpu1_ms": 0.0693327747285366,264 "cpuMT_ms": 0.07025012746453285,265 "metal_ms": 0.16458332538604736,266 "speedup": 0.42683623811679494,267 "verdict": "CPU"268 },269 "rolling_sumsq@10x3900": {270 "cpu1_ms": 0.06929086521267891,271 "cpuMT_ms": 0.04487484693527222,272 "metal_ms": 0.16070762649178505,273 "speedup": 0.2792328398774908,274 "verdict": "CPU"275 },276 "rolling_sumsq@100x390": {277 "cpu1_ms": 0.06991717964410782,278 "cpuMT_ms": 0.17983326688408852,279 "metal_ms": 0.2676667645573616,280 "speedup": 0.6718550477549103,281 "verdict": "tie"282 },283 "rolling_sumsq@1x390000": {284 "cpu1_ms": 0.6914162077009678,285 "cpuMT_ms": 0.718916766345501,286 "metal_ms": 0.7903752848505974,287 "speedup": 0.909589128259996,288 "verdict": "tie"289 },290 "rolling_sumsq@10x39000": {291 "cpu1_ms": 0.7095411419868469,292 "cpuMT_ms": 0.132707878947258,293 "metal_ms": 0.7357923313975334,294 "speedup": 0.18036050837224432,295 "verdict": "CPU"296 },297 "rolling_sumsq@100x3900": {298 "cpu1_ms": 0.806666910648346,299 "cpuMT_ms": 0.20312517881393433,300 "metal_ms": 0.6820829585194588,301 "speedup": 0.2978012810272249,302 "verdict": "CPU"303 },304 "rolling_sumsq@1000x390": {305 "cpu1_ms": 0.7188748568296432,306 "cpuMT_ms": 0.2710837870836258,307 "metal_ms": 0.9075421839952469,308 "speedup": 0.29870103215504695,309 "verdict": "CPU"310 },311 "rolling_sumsq@10x390000": {312 "cpu1_ms": 6.913874763995409,313 "cpuMT_ms": 1.7658751457929611,314 "metal_ms": 2.544207964092493,315 "speedup": 0.6940765734230536,316 "verdict": "CPU"317 },318 "rolling_sumsq@100x39000": {319 "cpu1_ms": 7.338124793022871,320 "cpuMT_ms": 1.0874588042497635,321 "metal_ms": 2.226833254098892,322 "speedup": 0.4883431672524638,323 "verdict": "CPU"324 },325 "rolling_sumsq@1000x3900": {326 "cpu1_ms": 6.95441709831357,327 "cpuMT_ms": 1.0273326188325882,328 "metal_ms": 2.144791651517153,329 "speedup": 0.47898947112456725,330 "verdict": "CPU"331 },332 "rolling_sumsq@10000x390": {333 "cpu1_ms": 7.047916762530804,334 "cpuMT_ms": 1.07216602191329,335 "metal_ms": 2.1627498790621758,336 "speedup": 0.49574203299838304,337 "verdict": "CPU"338 },339 "rolling_sumsq@100x390000": {340 "cpu1_ms": 69.62170917540789,341 "cpuMT_ms": 9.413291700184345,342 "metal_ms": 14.852333813905716,343 "speedup": 0.6337920907333103,344 "verdict": "CPU"345 },346 "rolling_sumsq@1000x39000": {347 "cpu1_ms": 70.26320835575461,348 "cpuMT_ms": 8.31229193136096,349 "metal_ms": 14.728832989931107,350 "speedup": 0.5643550943271196,351 "verdict": "CPU"352 },353 "rolling_sumsq@10000x3900": {354 "cpu1_ms": 69.22604190185666,355 "cpuMT_ms": 6.54304213821888,356 "metal_ms": 14.753291849046946,357 "speedup": 0.4434970991671636,358 "verdict": "CPU"359 },360 "garch_nll_P1@1x390": {361 "cpu1_ms": 0.0017909333109855652,362 "cpuMT_ms": 0.0017499551177024841,363 "metal_ms": 0.9180000051856041,364 "speedup": 0.0019062691806288963,365 "verdict": "CPU"366 },367 "garch_nll_P1@1x3900": {368 "cpu1_ms": 0.016250181943178177,369 "cpuMT_ms": 0.01695798709988594,370 "metal_ms": 1.348957885056734,371 "speedup": 0.012571176081729732,372 "verdict": "CPU"373 },374 "garch_nll_P1@10x390": {375 "cpu1_ms": 0.021916814148426056,376 "cpuMT_ms": 0.02929195761680603,377 "metal_ms": 0.3432091325521469,378 "speedup": 0.08534725576498299,379 "verdict": "CPU"380 },381 "garch_nll_P1@10x3900": {382 "cpu1_ms": 0.2155420370399952,383 "cpuMT_ms": 0.06916606798768044,384 "metal_ms": 1.4300826005637646,385 "speedup": 0.04836508601699924,386 "verdict": "CPU"387 },388 "garch_nll_P1@100x390": {389 "cpu1_ms": 0.1916671171784401,390 "cpuMT_ms": 0.16116676852107048,391 "metal_ms": 0.6238752976059914,392 "speedup": 0.2583317036906555,393 "verdict": "CPU"394 },395 "garch_nll_P1@100x3900": {396 "cpu1_ms": 1.6154590994119644,397 "cpuMT_ms": 0.20695803686976433,398 "metal_ms": 1.6493331640958786,399 "speedup": 0.12547982504384633,400 "verdict": "CPU"401 },402 "garch_nll_P1@1000x390": {403 "cpu1_ms": 1.6390001401305199,404 "cpuMT_ms": 0.2765827812254429,405 "metal_ms": 1.1531668715178967,406 "speedup": 0.23984627728802252,407 "verdict": "CPU"408 },409 "garch_nll_P1@1000x3900": {410 "cpu1_ms": 18.310166895389557,411 "cpuMT_ms": 1.4978330582380295,412 "metal_ms": 7.2068748995661736,413 "speedup": 0.20783391957146272,414 "verdict": "CPU"415 },416 "garch_nll_P1@10000x390": {417 "cpu1_ms": 17.741417046636343,418 "cpuMT_ms": 2.2433330304920673,419 "metal_ms": 6.75466563552618,420 "speedup": 0.33211607376881125,421 "verdict": "CPU"422 },423 "garch_nll_P1@10000x3900": {424 "cpu1_ms": 162.26391727104783,425 "cpuMT_ms": 13.83341709151864,426 "metal_ms": 61.06641702353954,427 "speedup": 0.22653068193252948,428 "verdict": "CPU"429 },430 "garch_nll_P64@1x390": {431 "cpu1_ms": 0.08287513628602028,432 "cpuMT_ms": 0.17224997282028198,433 "metal_ms": 0.5012080073356628,434 "speedup": 0.3436696347608925,435 "verdict": "CPU"436 },437 "garch_nll_P64@1x3900": {438 "cpu1_ms": 0.8078329265117645,439 "cpuMT_ms": 0.14187488704919815,440 "metal_ms": 1.4235423877835274,441 "speedup": 0.09966326838366861,442 "verdict": "CPU"443 },444 "garch_nll_P64@10x390": {445 "cpu1_ms": 0.8257082663476467,446 "cpuMT_ms": 0.2438751980662346,447 "metal_ms": 1.0179998353123665,448 "speedup": 0.23956310168891443,449 "verdict": "CPU"450 },451 "garch_nll_P64@10x3900": {452 "cpu1_ms": 8.083874825388193,453 "cpuMT_ms": 0.775500200688839,454 "metal_ms": 1.3822498731315136,455 "speedup": 0.5610419763916696,456 "verdict": "CPU"457 },458 "garch_nll_P64@100x390": {459 "cpu1_ms": 8.346542250365019,460 "cpuMT_ms": 1.005750149488449,461 "metal_ms": 0.5332920700311661,462 "speedup": 1.8859274420294159,463 "verdict": "Metal"464 },465 "garch_nll_P64@100x3900": {466 "cpu1_ms": 80.1338329911232,467 "cpuMT_ms": 6.173874717205763,468 "metal_ms": 2.1704169921576977,469 "speedup": 2.84455693975565,470 "verdict": "Metal"471 },472 "garch_nll_P64@1000x390": {473 "cpu1_ms": 96.79854195564985,474 "cpuMT_ms": 8.48708301782608,475 "metal_ms": 2.336665987968445,476 "speedup": 3.632133587567199,477 "verdict": "Metal"478 },479 "garch_nll_P64@1000x3900": {480 "cpu1_ms": 856.1791670508683,481 "cpuMT_ms": 81.50566695258021,482 "metal_ms": 10.272707790136337,483 "speedup": 7.934195016316967,484 "verdict": "Metal"485 }486 },487 "breakeven": {488 "realized_fused": {489 "smallest_metal_win": 39000,490 "largest_cpu_win": 39000,491 "max_speedup": 3.4364769430726474,492 "min_speedup": 0.006398401293585508493 },494 "regression_stats": {495 "smallest_metal_win": 390000,496 "largest_cpu_win": 390000,497 "max_speedup": 3.851129874745179,498 "min_speedup": 0.003588669989219929499 },500 "rolling_sumsq": {501 "smallest_metal_win": null,502 "largest_cpu_win": 39000000,503 "max_speedup": 0.909589128259996,504 "min_speedup": 0.0027898646399008046505 },506 "garch_nll_P1": {507 "smallest_metal_win": null,508 "largest_cpu_win": 39000000,509 "max_speedup": 0.33211607376881125,510 "min_speedup": 0.0019062691806288963511 },512 "garch_nll_P64": {513 "smallest_metal_win": 39000,514 "largest_cpu_win": 39000,515 "max_speedup": 7.934195016316967,516 "min_speedup": 0.09966326838366861517 }518 },519 "E1": {520 "real_S1_day": {521 "elements": 88350,522 "cpu1_ms": 0.7735420949757099,523 "cpuMT_ms": 0.9354581125080585,524 "metal_ms": 0.9417501278221607,525 "metal_unfused_ms": 2.271167002618313,526 "speedup_MT": 0.993318805988747,527 "fusion_gain": 2.4116450165719523,528 "max_rel_err": 3.216772293576152e-08,529 "metal_wins": false,530 "cpu_wins": false531 },532 "real_S1_week": {533 "elements": 87732,534 "cpu1_ms": 0.8084997534751892,535 "cpuMT_ms": 0.9053335525095463,536 "metal_ms": 0.7747076451778412,537 "metal_unfused_ms": 1.9873343408107758,538 "speedup_MT": 1.1686131641333148,539 "fusion_gain": 2.5652700772748473,540 "max_rel_err": 1.5355137638729577e-08,541 "metal_wins": true,542 "cpu_wins": false543 },544 "real_S1_month": {545 "elements": 85202,546 "cpu1_ms": 0.5944999866187572,547 "cpuMT_ms": 0.263875350356102,548 "metal_ms": 0.32645929604768753,549 "metal_unfused_ms": 1.0339580476284027,550 "speedup_MT": 0.8082947967809022,551 "fusion_gain": 3.167188253317091,552 "max_rel_err": 5.502644725750323e-09,553 "metal_wins": false,554 "cpu_wins": true555 },556 "real_S1_year": {557 "elements": 88350,558 "cpu1_ms": 0.8845417760312557,559 "cpuMT_ms": 0.7403329946100712,560 "metal_ms": 0.5079996772110462,561 "metal_unfused_ms": 1.289083156734705,562 "speedup_MT": 1.4573493406030318,563 "fusion_gain": 2.537566881561543,564 "max_rel_err": 1.1553520565395228e-09,565 "metal_wins": true,566 "cpu_wins": false567 },568 "real_S10_day": {569 "elements": 660818,570 "cpu1_ms": 4.591624718159437,571 "cpuMT_ms": 1.333874650299549,572 "metal_ms": 1.396208070218563,573 "metal_unfused_ms": 1.9492078572511673,574 "speedup_MT": 0.9553552072584308,575 "fusion_gain": 1.3960726189944148,576 "max_rel_err": 1.1707127776091667e-07,577 "metal_wins": false,578 "cpu_wins": false579 },580 "real_S10_week": {581 "elements": 655478,582 "cpu1_ms": 4.3206666596233845,583 "cpuMT_ms": 1.0201670229434967,584 "metal_ms": 0.8149999193847179,585 "metal_unfused_ms": 1.9696662202477455,586 "speedup_MT": 1.2517388022733416,587 "fusion_gain": 2.416768607455495,588 "max_rel_err": 4.3164647273400464e-08,589 "metal_wins": false,590 "cpu_wins": false591 },592 "real_S10_month": {593 "elements": 634608,594 "cpu1_ms": 4.162374883890152,595 "cpuMT_ms": 0.9038751013576984,596 "metal_ms": 1.0571670718491077,597 "metal_unfused_ms": 1.4940421096980572,598 "speedup_MT": 0.8549974033685291,599 "fusion_gain": 1.413250705098868,600 "max_rel_err": 1.5374929954074983e-08,601 "metal_wins": false,602 "cpu_wins": false603 },604 "real_S10_year": {605 "elements": 660818,606 "cpu1_ms": 4.490583203732967,607 "cpuMT_ms": 1.3055838644504547,608 "metal_ms": 1.4134589582681656,609 "metal_unfused_ms": 2.377707976847887,610 "speedup_MT": 0.9236800664167254,611 "fusion_gain": 1.6821910271531078,612 "max_rel_err": 3.180737515032068e-09,613 "metal_wins": false,614 "cpu_wins": false615 },616 "real_S100_day": {617 "elements": 4857139,618 "cpu1_ms": 29.412207659333944,619 "cpuMT_ms": 3.8021672517061234,620 "metal_ms": 4.112166818231344,621 "metal_unfused_ms": 7.726917043328285,622 "speedup_MT": 0.9246140586634681,623 "fusion_gain": 1.8790378369551788,624 "max_rel_err": 1.463952514147405e-07,625 "metal_wins": false,626 "cpu_wins": false627 },628 "real_S100_week": {629 "elements": 4814500,630 "cpu1_ms": 28.37820863351226,631 "cpuMT_ms": 3.745041787624359,632 "metal_ms": 3.630833700299263,633 "metal_unfused_ms": 6.0623749159276485,634 "speedup_MT": 1.031455058741931,635 "fusion_gain": 1.6696922570229453,636 "max_rel_err": 1.3949921298073233e-07,637 "metal_wins": false,638 "cpu_wins": false639 },640 "real_S100_month": {641 "elements": 4656568,642 "cpu1_ms": 27.86025032401085,643 "cpuMT_ms": 3.613583743572235,644 "metal_ms": 3.4282919950783253,645 "metal_unfused_ms": 5.321166943758726,646 "speedup_MT": 1.054047831619919,647 "fusion_gain": 1.552133526373431,648 "max_rel_err": 6.515494931810648e-08,649 "metal_wins": true,650 "cpu_wins": false651 },652 "real_S100_year": {653 "elements": 4817403,654 "cpu1_ms": 29.63858423754573,655 "cpuMT_ms": 3.890958148986101,656 "metal_ms": 3.2545411959290504,657 "metal_unfused_ms": 5.527874920517206,658 "speedup_MT": 1.1955473643575671,659 "fusion_gain": 1.6985112763150025,660 "max_rel_err": 1.220912079679724e-08,661 "metal_wins": true,662 "cpu_wins": false663 },664 "real_S926_day": {665 "elements": 40408948,666 "cpu1_ms": 240.89466594159603,667 "cpuMT_ms": 29.765665996819735,668 "metal_ms": 27.769084088504314,669 "metal_unfused_ms": 51.85075011104345,670 "speedup_MT": 1.0718994512729338,671 "fusion_gain": 1.8672113904004608,672 "max_rel_err": 1.6198392060671777e-07,673 "metal_wins": false,674 "cpu_wins": false675 },676 "real_S926_week": {677 "elements": 40062893,678 "cpu1_ms": 235.06820807233453,679 "cpuMT_ms": 29.190624598413706,680 "metal_ms": 24.931750260293484,681 "metal_unfused_ms": 44.04070833697915,682 "speedup_MT": 1.1708213139332997,683 "fusion_gain": 1.7664507255681425,684 "max_rel_err": 1.3949921298073233e-07,685 "metal_wins": true,686 "cpu_wins": false687 },688 "real_S926_month": {689 "elements": 38769255,690 "cpu1_ms": 231.19533294811845,691 "cpuMT_ms": 28.66779128089547,692 "metal_ms": 20.429750438779593,693 "metal_unfused_ms": 38.208582904189825,694 "speedup_MT": 1.4032374681620434,695 "fusion_gain": 1.8702422733301036,696 "max_rel_err": 6.515494931810648e-08,697 "metal_wins": true,698 "cpu_wins": false699 },700 "real_S926_year": {701 "elements": 39917613,702 "cpu1_ms": 241.63200007751584,703 "cpuMT_ms": 28.705624863505363,704 "metal_ms": 20.413792226463556,705 "metal_unfused_ms": 39.6507503464818,706 "speedup_MT": 1.406187764872645,707 "fusion_gain": 1.9423510294711575,708 "max_rel_err": 1.4314531656643865e-08,709 "metal_wins": true,710 "cpu_wins": false711 },712 "synthetic_S10000_day": {713 "elements": 3900000,714 "cpu1_ms": 21.742417011409998,715 "cpuMT_ms": 2.6805000379681587,716 "metal_ms": 3.3537917770445347,717 "metal_unfused_ms": null,718 "speedup_MT": 0.7992446210629983,719 "fusion_gain": null,720 "max_rel_err": 4.9499305589440414e-08,721 "metal_wins": false,722 "cpu_wins": true723 },724 "synthetic_S10000_week": {725 "elements": 19500000,726 "cpu1_ms": 106.63599986582994,727 "cpuMT_ms": 12.074083089828491,728 "metal_ms": 9.116541128605604,729 "metal_unfused_ms": null,730 "speedup_MT": 1.3244149200339592,731 "fusion_gain": null,732 "max_rel_err": 3.356929504238224e-08,733 "metal_wins": true,734 "cpu_wins": false735 },736 "synthetic_S10000_month": {737 "elements": 85800000,738 "cpu1_ms": 483.16720919683576,739 "cpuMT_ms": 54.07591676339507,740 "metal_ms": 35.40699975565076,741 "metal_unfused_ms": null,742 "speedup_MT": 1.5272662788878308,743 "fusion_gain": null,744 "max_rel_err": 2.7721528772327113e-08,745 "metal_wins": true,746 "cpu_wins": false747 }748 },749 "E2": {750 "accuracy": {751 "h1": {752 "n": 100,753 "har": 0.19596646955954006,754 "loghar": 0.20549043426692812,755 "harq": 0.20287854864925106,756 "rw": 0.2509836820568328,757 "har_beats_rw_pct": 84.0,758 "fits_per_symbol": 132.0759 },760 "h5": {761 "n": 100,762 "har": 0.14599330475845337,763 "loghar": 0.13780663128811915,764 "harq": 0.15032513333481387,765 "rw": 0.2392329633290453,766 "har_beats_rw_pct": 86.0,767 "fits_per_symbol": 128.0768 },769 "h22": {770 "n": 100,771 "har": 0.13380122970874658,772 "loghar": 0.11202433356845258,773 "harq": 0.1317067007400809,774 "rw": 0.30092923731362164,775 "har_beats_rw_pct": 78.0,776 "fits_per_symbol": 111.0777 }778 },779 "runtime": {780 "10": {781 "per_series_cpu1": 0.07679173722863197,782 "per_series_cpuMT": 0.053416937589645386,783 "batched_cpu": 0.10233419016003609,784 "batched_metal": 0.3199586644768715,785 "T": 252786 },787 "100": {788 "per_series_cpu1": 0.7653338834643364,789 "per_series_cpuMT": 0.14466699212789536,790 "batched_cpu": 0.6509590893983841,791 "batched_metal": 0.7528341375291348,792 "T": 252793 },794 "781": {795 "per_series_cpu1": 6.033665966242552,796 "per_series_cpuMT": 0.6839591078460217,797 "batched_cpu": 3.8614580407738686,798 "batched_metal": 4.703125450760126,799 "T": 251800 }801 }802 },803 "E3": {804 "symbols": 888,805 "daily_history": 845,806 "garch.n": {807 "n": 888,808 "converged_pct": 100.0,809 "median_iter": 14.0,810 "median_ms": 2.8645414859056473,811 "median_persistence": 0.962240963021934,812 "qlike": 0.4032196350815048,813 "qlike_rw": 0.27550123596742626,814 "n_train": 2458.5,815 "n_eval": 888816 },817 "gjr.n": {818 "n": 888,819 "converged_pct": 98.42342342342343,820 "median_iter": 18.0,821 "median_ms": 3.9954171516001225,822 "median_persistence": 0.9710634836054904,823 "qlike": 0.39931764172261175,824 "qlike_rw": 0.2734243088287934,825 "n_train": 2458.5,826 "n_eval": 874827 },828 "egarch.n": {829 "n": 888,830 "converged_pct": 92.7927927927928,831 "median_iter": 17.0,832 "median_ms": 18.152124946936965,833 "median_persistence": 0.9561998303082433,834 "qlike": 0.39635306701502293,835 "qlike_rw": 0.27241123059255185,836 "n_train": 2458.5,837 "n_eval": 824838 },839 "garch.t": {840 "n": 888,841 "converged_pct": 100.0,842 "median_iter": 18.0,843 "median_ms": 6.74610398709774,844 "median_persistence": 0.9727760170446753,845 "qlike": 0.3908846216118549,846 "qlike_rw": 0.27550123596742626,847 "n_train": 2458.5,848 "n_eval": 888849 },850 "grid": {851 "S": 888,852 "P": 256,853 "cpuMT_ms": 117.02079232782125,854 "metal_ms": 22.934832610189915,855 "max_rel_err_nll": 0.001696265571243037,856 "argmin_agreement": 888,857 "argmin_total": 888858 }859 },860 "E4": {861 "10": {862 "days_ok": 182,863 "days_skipped": 70,864 "cond_median": 80.51310121584409,865 "cond_max": 1114.4148164242238,866 "lw": 0.15825066990879552,867 "dy_windows": 133,868 "dy_total": 37.15801851010236,869 "dy_ms": 0.5304999649524689,870 "dy_failures": 0871 },872 "30": {873 "days_ok": 129,874 "days_skipped": 123,875 "cond_median": 421.7546397917854,876 "cond_max": 1982.0116043100866,877 "lw": 0.26298332837244776,878 "dy_windows": 133,879 "dy_total": 69.67433187119195,880 "dy_ms": 2.2807088680565357,881 "dy_failures": 0882 },883 "60": {884 "days_ok": 95,885 "days_skipped": 157,886 "cond_median": 5918.2160036330415,887 "cond_max": 4.004356648938842e+297,888 "lw": 0.3264154734521777,889 "dy_windows": 133,890 "dy_total": 87.50466794156553,891 "dy_ms": 8.867499884217978,892 "dy_failures": 0893 },894 "100": {895 "days_ok": 88,896 "days_skipped": 164,897 "cond_median": 1.3073204915206876e+298,898 "cond_max": 4.628848885035562e+298,899 "lw": 0.3323406895220246,900 "dy_windows": 133,901 "dy_total": 97.24027926801519,902 "dy_ms": 28.755417093634605,903 "dy_failures": 0904 }905 },906 "E5": {907 "garch_n500": {908 "mu": {909 "bias": -0.00048301580401779385,910 "coverage95": 0.95,911 "rmse": 0.03830937699585465912 },913 "omega": {914 "bias": 0.020140386483790382,915 "coverage95": 0.954,916 "rmse": 0.04874063710909834917 },918 "alpha": {919 "bias": 0.0021013443234158386,920 "coverage95": 0.896,921 "rmse": 0.030365422987920495922 },923 "beta": {924 "bias": -0.025611816484074457,925 "coverage95": 0.916,926 "rmse": 0.07085785700063447927 },928 "converged": 1000,929 "R": 1000930 },931 "garch_n2000": {932 "mu": {933 "bias": 0.0001115840803594372,934 "coverage95": 0.961,935 "rmse": 0.018994072598395778936 },937 "omega": {938 "bias": 0.0034273370897326973,939 "coverage95": 0.972,940 "rmse": 0.009288147787445019941 },942 "alpha": {943 "bias": 0.0007353540065208454,944 "coverage95": 0.932,945 "rmse": 0.013671869751518313946 },947 "beta": {948 "bias": -0.004814929382042228,949 "coverage95": 0.936,950 "rmse": 0.019568746480840227951 },952 "converged": 1000,953 "R": 1000954 },955 "har_h1": [956 0.945,957 0.939,958 0.946,959 0.941960 ],961 "har_h5": [962 0.909,963 0.936,964 0.931,965 0.9966 ],967 "repro_bootstrap": {968 "bitwise_identical_across_threads": true,969 "replicas": 2000,970 "threads": [971 1,972 4,973 18974 ]975 },976 "repro_realized": {977 "cpu_threads_vs_1_identical": true,978 "metal_backend_used": "metal",979 "metal_runs_identical": true,980 "metal_vs_cpu_max_rel_rv": 3.6599268443269906e-08981 }982 },983 "E6": {984 "bars_per_file": 2367760.5,985 "read_s": 0.06473202048800886,986 "prep_s": 0.02098981267772615,987 "est_cpu_s": 0.03066229191608727,988 "est_metal_s": 0.03653329168446362,989 "RAID cpu": {990 "median_s": 0.1182449993211776,991 "ci": [992 0.09712429158389568,993 0.12820672919042408994 ],995 "bars_per_s": 20024191.412684422996 },997 "RAID metal": {998 "median_s": 0.12477712496183813,999 "ci": [1000 0.10097172926180065,1001 0.1343048328999431002 ],1003 "bars_per_s": 18975918.0677079741004 },1005 "polars": {1006 "median_s": 0.16476131248055026,1007 "ci": [1008 0.14585839601932094,1009 0.172257666999939831010 ],1011 "bars_per_s": 14370852.382471012 },1013 "duckdb": {1014 "median_s": 0.1637031040736474,1015 "ci": [1016 0.15818560402840376,1017 0.165373312484007331018 ],1019 "bars_per_s": 14463748.3412335441020 },1021 "pandas": {1022 "median_s": 2.5584507705061696,1023 "ci": [1024 2.355445542023517,1025 2.63371756247943271026 ],1027 "bars_per_s": 925466.50781619571028 }1029 },1030 "E7": {1031 "m2m8a": {1032 "chip": "Apple M2",1033 "gpu_cores": 10,1034 "cpu_threads": "8",1035 "mem_gb": 8,1036 "macos": "26.5.1",1037 "cold_compile_s": 0.109846416,1038 "warm_compile_s": 0.000537584,1039 "realized_fused@1000x3900_speedup_MT": 3.990399191000979,1040 "regression_stats@1000x3900_speedup_MT": 1.6134322509601442,1041 "garch_nll_P64@1000x390_speedup_MT": 6.670422238065105,1042 "rolling_sumsq@1000x3900_speedup_MT": 0.6518314749487951,1043 "realized_fused@1000x3900_cpuMT_ms": 5.524458014406264,1044 "realized_fused@1000x3900_metal_ms": 1.3844374334439635,1045 "tests": "pass / pass"1046 },1047 "M2M32c": {1048 "chip": "Apple M2 Max",1049 "gpu_cores": 30,1050 "cpu_threads": "12",1051 "mem_gb": 32,1052 "macos": "26.5.1",1053 "cold_compile_s": 0.048325125,1054 "warm_compile_s": 0.000524916,1055 "realized_fused@1000x3900_speedup_MT": 3.6053646941003636,1056 "regression_stats@1000x3900_speedup_MT": 1.35476806903387,1057 "garch_nll_P64@1000x390_speedup_MT": 7.836957668549106,1058 "rolling_sumsq@1000x3900_speedup_MT": 0.5173055981132895,1059 "realized_fused@1000x3900_cpuMT_ms": 3.611000021919608,1060 "realized_fused@1000x3900_metal_ms": 1.0015630396082997,1061 "tests": "pass / pass"1062 },1063 "M2U64": {1064 "chip": "Apple M2 Ultra",1065 "gpu_cores": 60,1066 "cpu_threads": "24",1067 "mem_gb": 64,1068 "macos": "26.5",1069 "cold_compile_s": 0.049152792,1070 "warm_compile_s": 0.000613,1071 "realized_fused@1000x3900_speedup_MT": 2.1845461259882226,1072 "regression_stats@1000x3900_speedup_MT": 1.0830287027429175,1073 "garch_nll_P64@1000x390_speedup_MT": 4.924931422444954,1074 "rolling_sumsq@1000x3900_speedup_MT": 0.32161785435813445,1075 "realized_fused@1000x3900_cpuMT_ms": 2.279437379911542,1076 "realized_fused@1000x3900_metal_ms": 1.0434375144541264,1077 "tests": "pass / pass"1078 },1079 "M3BA24": {1080 "chip": "Apple M3",1081 "gpu_cores": 10,1082 "cpu_threads": "8",1083 "mem_gb": 24,1084 "macos": "26.5.1",1085 "cold_compile_s": 0.043905667,1086 "warm_compile_s": 0.000421292,1087 "realized_fused@1000x3900_speedup_MT": 2.687471016852494,1088 "regression_stats@1000x3900_speedup_MT": 1.6792771365359433,1089 "garch_nll_P64@1000x390_speedup_MT": 6.207505979251421,1090 "rolling_sumsq@1000x3900_speedup_MT": 0.3554353915980856,1091 "realized_fused@1000x3900_cpuMT_ms": 4.603916313499212,1092 "realized_fused@1000x3900_metal_ms": 1.7131036147475243,1093 "tests": "pass / pass"1094 },1095 "M3U96b": {1096 "chip": "Apple M3 Ultra",1097 "gpu_cores": 60,1098 "cpu_threads": "28",1099 "mem_gb": 96,1100 "macos": "26.4",1101 "cold_compile_s": 0.047089167,1102 "warm_compile_s": 0.000531084,1103 "realized_fused@1000x3900_speedup_MT": 1.6817560971796317,1104 "regression_stats@1000x3900_speedup_MT": 0.7767583073146588,1105 "garch_nll_P64@1000x390_speedup_MT": 3.179140922934574,1106 "rolling_sumsq@1000x3900_speedup_MT": 0.24312350847240793,1107 "realized_fused@1000x3900_cpuMT_ms": 2.304041408933699,1108 "realized_fused@1000x3900_metal_ms": 1.370021142065525,1109 "tests": "pass / pass"1110 },1111 "m4md": {1112 "chip": "Apple M4",1113 "gpu_cores": 10,1114 "cpu_threads": "10",1115 "mem_gb": 16,1116 "macos": "26.6.2",1117 "cold_compile_s": 0.042053541,1118 "warm_compile_s": 0.000386541,1119 "realized_fused@1000x3900_speedup_MT": 2.548863991558486,1120 "regression_stats@1000x3900_speedup_MT": 1.338401514661036,1121 "garch_nll_P64@1000x390_speedup_MT": 4.206244849053445,1122 "rolling_sumsq@1000x3900_speedup_MT": 0.37666800739402895,1123 "realized_fused@1000x3900_cpuMT_ms": 3.558958414942026,1124 "realized_fused@1000x3900_metal_ms": 1.3962920056656003,1125 "tests": "pass / pass"1126 },1127 "m4mm": {1128 "chip": "Apple M4 Pro",1129 "gpu_cores": 16,1130 "cpu_threads": "12",1131 "mem_gb": 48,1132 "macos": "26.5.1",1133 "cold_compile_s": 0.038549083,1134 "warm_compile_s": 0.000449708,1135 "realized_fused@1000x3900_speedup_MT": 1.6260083182113196,1136 "regression_stats@1000x3900_speedup_MT": 0.91166043986465,1137 "garch_nll_P64@1000x390_speedup_MT": 2.1391683174192333,1138 "rolling_sumsq@1000x3900_speedup_MT": 0.23880014056164212,1139 "realized_fused@1000x3900_cpuMT_ms": 2.68670788500458,1140 "realized_fused@1000x3900_metal_ms": 1.6523334197700024,1141 "tests": "pass / pass"1142 },1143 "M4M64c": {1144 "chip": "Apple M4 Max",1145 "gpu_cores": 40,1146 "cpu_threads": "16",1147 "mem_gb": 64,1148 "macos": "26.4",1149 "cold_compile_s": 0.040168875,1150 "warm_compile_s": 0.0004675,1151 "realized_fused@1000x3900_speedup_MT": 2.79582771769825,1152 "regression_stats@1000x3900_speedup_MT": 1.1902389066688093,1153 "garch_nll_P64@1000x390_speedup_MT": 4.8188331984067,1154 "rolling_sumsq@1000x3900_speedup_MT": 0.4781437102048132,1155 "realized_fused@1000x3900_cpuMT_ms": 2.066000597551465,1156 "realized_fused@1000x3900_metal_ms": 0.7389584789052606,1157 "tests": "pass / pass"1158 },1159 "m5ma": {1160 "chip": "Apple M5 Pro",1161 "gpu_cores": 16,1162 "cpu_threads": "15",1163 "mem_gb": 24,1164 "macos": "27.0",1165 "cold_compile_s": 0.043711542,1166 "warm_compile_s": 0.000386292,1167 "realized_fused@1000x3900_speedup_MT": 1.1284910996519257,1168 "regression_stats@1000x3900_speedup_MT": 0.5487957656812417,1169 "garch_nll_P64@1000x390_speedup_MT": 1.8287923928070076,1170 "rolling_sumsq@1000x3900_speedup_MT": 0.19530880040350074,1171 "realized_fused@1000x3900_cpuMT_ms": 2.040499937720597,1172 "realized_fused@1000x3900_metal_ms": 1.8081666203215718,1173 "tests": "pass / pass"1174 },1175 "M5M36": {1176 "chip": "Apple M5 Max",1177 "gpu_cores": 32,1178 "cpu_threads": "18",1179 "mem_gb": 36,1180 "macos": "27.0",1181 "cold_compile_s": 0.037059042,1182 "warm_compile_s": 0.000456708,1183 "realized_fused@1000x3900_speedup_MT": 1.1217974525711423,1184 "regression_stats@1000x3900_speedup_MT": 0.6015969625826116,1185 "garch_nll_P64@1000x390_speedup_MT": 2.1447918847693943,1186 "rolling_sumsq@1000x3900_speedup_MT": 0.22944356711535452,1187 "realized_fused@1000x3900_cpuMT_ms": 1.6108546406030655,1188 "realized_fused@1000x3900_metal_ms": 1.4359585475176573,1189 "tests": "pass / pass"1190 },1191 "m6ma": {1192 "chip": "Apple M6",1193 "gpu_cores": 12,1194 "cpu_threads": "12",1195 "mem_gb": 24,1196 "macos": "27.0",1197 "cold_compile_s": 0.039953334,1198 "warm_compile_s": 0.000306458,1199 "realized_fused@1000x3900_speedup_MT": 1.6330551240965197,1200 "regression_stats@1000x3900_speedup_MT": 0.7851066834472289,1201 "garch_nll_P64@1000x390_speedup_MT": 3.7206830701585027,1202 "rolling_sumsq@1000x3900_speedup_MT": 0.34461349554716936,1203 "realized_fused@1000x3900_cpuMT_ms": 2.4681249633431435,1204 "realized_fused@1000x3900_metal_ms": 1.5113543486222625,1205 "tests": "pass / pass"1206 }1207 },1208 "laptop": {1209 "chip": "Apple M5 Max",1210 "os": "27.0",1211 "xcode": "Xcode 27.2 Build version 27B52",1212 "clang": "Apple clang version 21.0.0 (clang-2100.4.1.1)",1213 "cmake": "cmake version 4.3.2",1214 "metal_toolchain": "Apple metal version 32023.922 (metalfe-32023.922.4)",1215 "brew": {1216 "eigen": "eigen 5.0.1",1217 "apache-arrow": "apache-arrow 26.0.0_3",1218 "catch2": "catch2 3.16.1",1219 "nlohmann-json": "nlohmann-json 3.12.0",1220 "openblas": "openblas 0.3.33",1221 "libomp": "libomp 22.1.8"1222 },1223 "load_avg": "{ 3,67 3,00 2,56 }",1224 "thermal": "Note: No thermal warning level has been recorded;Note: No performance warning level has been recorded;Note: No CPU power status has been recorded;",1225 "ncpu": "18",1226 "perf_cores": "6",1227 "eff_cores": "12"1228 },1229 "generated_at": "2026-11-02T21:05:20.158901+00:00"1230}