-
Notifications
You must be signed in to change notification settings - Fork 25
Extend Rotate recognition #1856
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
+572
−1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
EnzymeJAX Benchmarks
Details
| Benchmark suite | Current: 55fa9b8 | Previous: 008dac3 | Ratio |
|---|---|---|---|
actmtch / JaXPipe / cpu / Primal |
0.000007219600011012517 s |
0.000006760500036762096 s |
1.07 |
actmtch / Jax / cpu / Primal |
0.000006937700009075343 s |
0.000006411220001609764 s |
1.08 |
actmtch / HLOOpt / cpu / Primal |
0.000008001980004337384 s |
0.000008145720021275339 s |
0.98 |
actmtch / PartOpt / cpu / Primal |
0.000006918760018379544 s |
0.000006577820022357627 s |
1.05 |
actmtch / IPartOpt / cpu / Primal |
0.000007273139972312492 s |
0.000006845999960205517 s |
1.06 |
actmtch / DefOpt / cpu / Primal |
0.000008002299991858309 s |
0.000007159520037021139 s |
1.12 |
actmtch / IDefOpt / cpu / Primal |
0.000007745939992673811 s |
0.000007819799966455321 s |
0.99 |
actmtch / JaXPipe / cpu / Forward |
0.000011593719964366756 s |
0.00001100208001844294 s |
1.05 |
actmtch / Jax / cpu / Forward |
0.000010134320027646027 s |
0.00001000555997052288 s |
1.01 |
actmtch / HLOOpt / cpu / Forward |
0.000012213939999128343 s |
0.000011567560004550616 s |
1.06 |
actmtch / PartOpt / cpu / Forward |
0.000012317599994275952 s |
0.000010661280030035412 s |
1.16 |
actmtch / IPartOpt / cpu / Forward |
0.000011965199983023922 s |
0.000011272220053797356 s |
1.06 |
actmtch / DefOpt / cpu / Forward |
0.00001164608001090528 s |
0.000010422680006740849 s |
1.12 |
actmtch / IDefOpt / cpu / Forward |
0.000011969359975410044 s |
0.000010585179988993332 s |
1.13 |
actmtch / JaXPipe / cpu / PreRev |
0.000011538819981069535 s |
0.00001065782000296167 s |
1.08 |
actmtch / JaXPipe / cpu / PostRev |
0.000011596199947234709 s |
0.000009895780012811885 s |
1.17 |
actmtch / JaXPipe / cpu / BothRev |
0.000013018939980611322 s |
0.000011262480038567446 s |
1.16 |
actmtch / Jax / cpu / BothRev |
0.000010528179991524669 s |
0.00001015358000586275 s |
1.04 |
actmtch / HLOOpt / cpu / PreRev |
0.000012500800030466051 s |
0.000010812100017574266 s |
1.16 |
actmtch / HLOOpt / cpu / PostRev |
0.000013378120002016658 s |
0.000012807180000891094 s |
1.04 |
actmtch / HLOOpt / cpu / BothRev |
0.00001181432000521454 s |
0.00001181797997560352 s |
1.00 |
actmtch / PartOpt / cpu / PreRev |
0.00001183654000669776 s |
0.000010439159987072345 s |
1.13 |
actmtch / PartOpt / cpu / PostRev |
0.000011016879971066374 s |
0.000010471360028532217 s |
1.05 |
actmtch / PartOpt / cpu / BothRev |
0.000012776619996657246 s |
0.000011898939937964317 s |
1.07 |
actmtch / IPartOpt / cpu / PreRev |
0.000011382860038793295 s |
0.000010801919979712692 s |
1.05 |
actmtch / IPartOpt / cpu / PostRev |
0.000010706939992815025 s |
0.000009592260012141196 s |
1.12 |
actmtch / IPartOpt / cpu / BothRev |
0.000012827480013584136 s |
0.000011451419995864853 s |
1.12 |
actmtch / DefOpt / cpu / PreRev |
0.000011133059997519012 s |
0.000010753459991974524 s |
1.04 |
actmtch / DefOpt / cpu / PostRev |
0.000011579539959711838 s |
0.00001099387999602186 s |
1.05 |
actmtch / DefOpt / cpu / BothRev |
0.000012121499994464102 s |
0.000011193439931957982 s |
1.08 |
actmtch / IDefOpt / cpu / PreRev |
0.00001178591996904288 s |
0.000011068260055253632 s |
1.06 |
actmtch / IDefOpt / cpu / PostRev |
0.00001255560002391576 s |
0.000011407880001570448 s |
1.10 |
actmtch / IDefOpt / cpu / BothRev |
0.000012186220010335091 s |
0.000011293160023342352 s |
1.08 |
actmtch / JaXPipe / cuda / Primal |
0.000002368 s |
0.000002015 s |
1.18 |
actmtch / Jax / cuda / Primal |
0.0000024 s |
0.000002016 s |
1.19 |
actmtch / HLOOpt / cuda / Primal |
0.000002368 s |
0.000002016 s |
1.17 |
actmtch / PartOpt / cuda / Primal |
0.000002399 s |
0.000002016 s |
1.19 |
actmtch / IPartOpt / cuda / Primal |
0.000002368 s |
0.000002015 s |
1.18 |
actmtch / DefOpt / cuda / Primal |
0.0000023670000000000004 s |
0.000002016 s |
1.17 |
actmtch / IDefOpt / cuda / Primal |
0.000002368 s |
0.000002016 s |
1.17 |
actmtch / JaXPipe / cuda / Forward |
0.000010656 s |
0.000009664 s |
1.10 |
actmtch / Jax / cuda / Forward |
0.000010272 s |
0.000009888 s |
1.04 |
actmtch / HLOOpt / cuda / Forward |
0.000010528 s |
0.000009952 s |
1.06 |
actmtch / PartOpt / cuda / Forward |
0.000010432 s |
0.000009728 s |
1.07 |
actmtch / IPartOpt / cuda / Forward |
0.0000104 s |
0.000009888 s |
1.05 |
actmtch / DefOpt / cuda / Forward |
0.000010432 s |
0.000010016 s |
1.04 |
actmtch / IDefOpt / cuda / Forward |
0.00001056 s |
0.000010144 s |
1.04 |
actmtch / JaXPipe / cuda / PreRev |
0.000010784 s |
0.000009569 s |
1.13 |
actmtch / JaXPipe / cuda / PostRev |
0.000011520000000000002 s |
0.00000976 s |
1.18 |
actmtch / JaXPipe / cuda / BothRev |
0.000010624 s |
0.000009728 s |
1.09 |
actmtch / Jax / cuda / BothRev |
0.000011648 s |
0.000010271 s |
1.13 |
actmtch / HLOOpt / cuda / PreRev |
0.00001056 s |
0.000010144 s |
1.04 |
actmtch / HLOOpt / cuda / PostRev |
0.000010688 s |
0.000009888 s |
1.08 |
actmtch / HLOOpt / cuda / BothRev |
0.000010816 s |
0.000009985 s |
1.08 |
actmtch / PartOpt / cuda / PreRev |
0.000010719 s |
0.000010176 s |
1.05 |
actmtch / PartOpt / cuda / PostRev |
0.000010496 s |
0.000009825 s |
1.07 |
actmtch / PartOpt / cuda / BothRev |
0.000010592 s |
0.000009408 s |
1.13 |
actmtch / IPartOpt / cuda / PreRev |
0.000010944 s |
0.000010016 s |
1.09 |
actmtch / IPartOpt / cuda / PostRev |
0.000010816 s |
0.000009888 s |
1.09 |
actmtch / IPartOpt / cuda / BothRev |
0.000010753 s |
0.000009696 s |
1.11 |
actmtch / DefOpt / cuda / PreRev |
0.000010912 s |
0.000010048 s |
1.09 |
actmtch / DefOpt / cuda / PostRev |
0.000010815 s |
0.000009824 s |
1.10 |
actmtch / DefOpt / cuda / BothRev |
0.000010719 s |
0.00001024 s |
1.05 |
actmtch / IDefOpt / cuda / PreRev |
0.00001056 s |
0.000010304 s |
1.02 |
actmtch / IDefOpt / cuda / PostRev |
0.000010528 s |
0.000009729 s |
1.08 |
actmtch / IDefOpt / cuda / BothRev |
0.000010368 s |
0.000010111 s |
1.03 |
actmtch / JaXPipe / tpu / Primal |
5.63275e-7 s |
5.63425e-7 s |
1.00 |
actmtch / Jax / tpu / Primal |
5.96975e-7 s |
5.966250000000001e-7 s |
1.00 |
actmtch / HLOOpt / tpu / Primal |
0.00000209415 s |
0.0000021007 s |
1.00 |
actmtch / PartOpt / tpu / Primal |
5.964250000000001e-7 s |
5.967e-7 s |
1.00 |
actmtch / IPartOpt / tpu / Primal |
5.528999999999999e-7 s |
5.5285e-7 s |
1.00 |
actmtch / DefOpt / tpu / Primal |
0.000002154975 s |
0.00000216535 s |
1.00 |
actmtch / IDefOpt / tpu / Primal |
0.0000021036 s |
0.000002095925 s |
1.00 |
actmtch / JaXPipe / tpu / Forward |
0.000003828075000000001 s |
0.000003833699999999999 s |
1.00 |
actmtch / Jax / tpu / Forward |
0.00000121105 s |
0.0000012137 s |
1.00 |
actmtch / HLOOpt / tpu / Forward |
0.000003940775 s |
0.000003934825 s |
1.00 |
actmtch / PartOpt / tpu / Forward |
0.00000391235 s |
0.000003914125 s |
1.00 |
actmtch / IPartOpt / tpu / Forward |
0.000003945825 s |
0.0000039562 s |
1.00 |
actmtch / DefOpt / tpu / Forward |
0.000003918575000000001 s |
0.0000039197 s |
1.00 |
actmtch / IDefOpt / tpu / Forward |
0.0000039444 s |
0.000003948875 s |
1.00 |
actmtch / JaXPipe / tpu / PreRev |
0.000003477675 s |
0.000003474775 s |
1.00 |
actmtch / JaXPipe / tpu / PostRev |
0.0000016404750000000002 s |
0.000001638225 s |
1.00 |
actmtch / JaXPipe / tpu / BothRev |
0.000003493275 s |
0.0000034755000000000004 s |
1.01 |
actmtch / Jax / tpu / BothRev |
0.000001636525 s |
0.0000016347999999999998 s |
1.00 |
actmtch / HLOOpt / tpu / PreRev |
0.00000347935 s |
0.0000034835 s |
1.00 |
actmtch / HLOOpt / tpu / PostRev |
0.000003423075 s |
0.0000034127000000000004 s |
1.00 |
actmtch / HLOOpt / tpu / BothRev |
0.000003487 s |
0.00000346445 s |
1.01 |
actmtch / PartOpt / tpu / PreRev |
0.00000341505 s |
0.0000034168 s |
1.00 |
actmtch / PartOpt / tpu / PostRev |
0.000001585025 s |
0.000001595925 s |
0.99 |
actmtch / PartOpt / tpu / BothRev |
0.00000341325 s |
0.00000340855 s |
1.00 |
actmtch / IPartOpt / tpu / PreRev |
0.0000034763500000000006 s |
0.000003468525 s |
1.00 |
actmtch / IPartOpt / tpu / PostRev |
0.000001633675 s |
0.000001630525 s |
1.00 |
actmtch / IPartOpt / tpu / BothRev |
0.000003478425 s |
0.00000348495 s |
1.00 |
actmtch / DefOpt / tpu / PreRev |
0.0000034184999999999995 s |
0.000003405575 s |
1.00 |
actmtch / DefOpt / tpu / PostRev |
0.0000034131250000000005 s |
0.000003419525 s |
1.00 |
actmtch / DefOpt / tpu / BothRev |
0.0000034026 s |
0.00000341945 s |
1.00 |
actmtch / IDefOpt / tpu / PreRev |
0.000003491375 s |
0.000003468625 s |
1.01 |
actmtch / IDefOpt / tpu / PostRev |
0.0000034063500000000004 s |
0.0000034068500000000003 s |
1.00 |
actmtch / IDefOpt / tpu / BothRev |
0.000003481775 s |
0.000003474975 s |
1.00 |
actmtch / JaXPipe / cpu / Primal |
0.000016955000000000003 s |
0.000006760500036762096 s |
2.51 |
actmtch / Jax / cpu / Primal |
0.000017037 s |
0.000006411220001609764 s |
2.66 |
actmtch / HLOOpt / cpu / Primal |
0.00001744 s |
0.000008145720021275339 s |
2.14 |
actmtch / PartOpt / cpu / Primal |
0.000016834 s |
0.000006577820022357627 s |
2.56 |
actmtch / IPartOpt / cpu / Primal |
0.000016868999999999997 s |
0.000006845999960205517 s |
2.46 |
actmtch / DefOpt / cpu / Primal |
0.000017491 s |
0.000007159520037021139 s |
2.44 |
actmtch / IDefOpt / cpu / Primal |
0.000017797 s |
0.000007819799966455321 s |
2.28 |
actmtch / JaXPipe / cpu / Forward |
0.000023931 s |
0.00001100208001844294 s |
2.18 |
actmtch / Jax / cpu / Forward |
0.000022711 s |
0.00001000555997052288 s |
2.27 |
actmtch / HLOOpt / cpu / Forward |
0.000024147 s |
0.000011567560004550616 s |
2.09 |
actmtch / PartOpt / cpu / Forward |
0.000024114 s |
0.000010661280030035412 s |
2.26 |
actmtch / IPartOpt / cpu / Forward |
0.000023981 s |
0.000011272220053797356 s |
2.13 |
actmtch / DefOpt / cpu / Forward |
0.000023467 s |
0.000010422680006740849 s |
2.25 |
actmtch / IDefOpt / cpu / Forward |
0.000023612 s |
0.000010585179988993332 s |
2.23 |
actmtch / JaXPipe / cpu / PreRev |
0.000024495 s |
0.00001065782000296167 s |
2.30 |
actmtch / JaXPipe / cpu / PostRev |
0.000022046 s |
0.000009895780012811885 s |
2.23 |
actmtch / JaXPipe / cpu / BothRev |
0.000024167 s |
0.000011262480038567446 s |
2.15 |
actmtch / Jax / cpu / BothRev |
0.000022147 s |
0.00001015358000586275 s |
2.18 |
actmtch / HLOOpt / cpu / PreRev |
0.000024502 s |
0.000010812100017574266 s |
2.27 |
actmtch / HLOOpt / cpu / PostRev |
0.000024333 s |
0.000012807180000891094 s |
1.90 |
actmtch / HLOOpt / cpu / BothRev |
0.000024398 s |
0.00001181797997560352 s |
2.06 |
actmtch / PartOpt / cpu / PreRev |
0.000024112 s |
0.000010439159987072345 s |
2.31 |
actmtch / PartOpt / cpu / PostRev |
0.000022053 s |
0.000010471360028532217 s |
2.11 |
actmtch / PartOpt / cpu / BothRev |
0.000024206 s |
0.000011898939937964317 s |
2.03 |
actmtch / IPartOpt / cpu / PreRev |
0.000024315 s |
0.000010801919979712692 s |
2.25 |
actmtch / IPartOpt / cpu / PostRev |
0.0000215 s |
0.000009592260012141196 s |
2.24 |
actmtch / IPartOpt / cpu / BothRev |
0.000024032 s |
0.000011451419995864853 s |
2.10 |
actmtch / DefOpt / cpu / PreRev |
0.00002439 s |
0.000010753459991974524 s |
2.27 |
actmtch / DefOpt / cpu / PostRev |
0.000024632 s |
0.00001099387999602186 s |
2.24 |
actmtch / DefOpt / cpu / BothRev |
0.000024346 s |
0.000011193439931957982 s |
2.18 |
actmtch / IDefOpt / cpu / PreRev |
0.000024297 s |
0.000011068260055253632 s |
2.20 |
actmtch / IDefOpt / cpu / PostRev |
0.000024202 s |
0.000011407880001570448 s |
2.12 |
actmtch / IDefOpt / cpu / BothRev |
0.000024456 s |
0.000011293160023342352 s |
2.17 |
add_one / JaXPipe / cpu / Primal |
0.000006766400019841967 s |
0.000007061899959808216 s |
0.96 |
add_one / Jax / cpu / Primal |
0.00000701046000358474 s |
0.000007725300010861246 s |
0.91 |
add_one / HLOOpt / cpu / Primal |
0.0000067159000354877205 s |
0.000007127159988158383 s |
0.94 |
add_one / PartOpt / cpu / Primal |
0.000006456360015363316 s |
0.0000064727400240371934 s |
1.00 |
add_one / IPartOpt / cpu / Primal |
0.000007295920004253276 s |
0.000006855559977338999 s |
1.06 |
add_one / DefOpt / cpu / Primal |
0.000006764760000805836 s |
0.000006799359998694854 s |
0.99 |
add_one / IDefOpt / cpu / Primal |
0.000006472800005212776 s |
0.000006532919996971032 s |
0.99 |
add_one / JaXPipe / cpu / Forward |
0.000010426539975014748 s |
0.000010692179985198891 s |
0.98 |
add_one / Jax / cpu / Forward |
0.000010362539997004206 s |
0.000009852040057012344 s |
1.05 |
add_one / HLOOpt / cpu / Forward |
0.000010711020013332018 s |
0.00001061569998455525 s |
1.01 |
add_one / PartOpt / cpu / Forward |
0.000010018179991675423 s |
0.000010313280026821304 s |
0.97 |
add_one / IPartOpt / cpu / Forward |
0.000010749960010798533 s |
0.000010236940006507212 s |
1.05 |
add_one / DefOpt / cpu / Forward |
0.000010087039981954147 s |
0.00001021022000713856 s |
0.99 |
add_one / IDefOpt / cpu / Forward |
0.000010709299986046971 s |
0.00000989591997495154 s |
1.08 |
add_one / JaXPipe / cpu / PreRev |
0.000012811520000468593 s |
0.000011687020005410889 s |
1.10 |
add_one / JaXPipe / cpu / PostRev |
0.00001250757997695473 s |
0.000011235759975534164 s |
1.11 |
add_one / JaXPipe / cpu / BothRev |
0.000012652120012717204 s |
0.000012070920010955888 s |
1.05 |
add_one / Jax / cpu / BothRev |
0.000012484280023272732 s |
0.00001110520000111137 s |
1.12 |
add_one / HLOOpt / cpu / PreRev |
0.000012529659989013453 s |
0.0000117855600456096 s |
1.06 |
add_one / HLOOpt / cpu / PostRev |
0.0000147597399973165 s |
0.0000174333799895976 s |
0.85 |
add_one / HLOOpt / cpu / BothRev |
0.000012448559991753428 s |
0.000011470099998405203 s |
1.09 |
add_one / PartOpt / cpu / PreRev |
0.000012288619982427918 s |
0.000011000640006386676 s |
1.12 |
add_one / PartOpt / cpu / PostRev |
0.000013095279991830466 s |
0.000011238540000704234 s |
1.17 |
add_one / PartOpt / cpu / BothRev |
0.000013286659968798632 s |
0.000011834960005217 s |
1.12 |
add_one / IPartOpt / cpu / PreRev |
0.000011644140013231665 s |
0.000011671399961414864 s |
1.00 |
add_one / IPartOpt / cpu / PostRev |
0.000012916999985463915 s |
0.000012116419975427562 s |
1.07 |
add_one / IPartOpt / cpu / BothRev |
0.00001268416000129946 s |
0.000011671220026983064 s |
1.09 |
add_one / DefOpt / cpu / PreRev |
0.00001207088002047385 s |
0.000011632380019364063 s |
1.04 |
add_one / DefOpt / cpu / PostRev |
0.00001316150001002825 s |
0.000011632059986368405 s |
1.13 |
add_one / DefOpt / cpu / BothRev |
0.000013018680010645767 s |
0.00001143328000580368 s |
1.14 |
add_one / IDefOpt / cpu / PreRev |
0.000012351220002528862 s |
0.00001101984002161771 s |
1.12 |
add_one / IDefOpt / cpu / PostRev |
0.000012618619975910406 s |
0.000011647559977063794 s |
1.08 |
add_one / IDefOpt / cpu / BothRev |
0.00001241630000549776 s |
0.00001107572001274093 s |
1.12 |
add_one / JaXPipe / cuda / Primal |
0.000002303 s |
0.0000019200000000000003 s |
1.20 |
add_one / Jax / cuda / Primal |
0.000002303 s |
0.0000019200000000000003 s |
1.20 |
add_one / HLOOpt / cuda / Primal |
0.000002303 s |
0.0000019200000000000003 s |
1.20 |
add_one / PartOpt / cuda / Primal |
0.000002303 s |
0.0000019200000000000003 s |
1.20 |
add_one / IPartOpt / cuda / Primal |
0.000002303 s |
0.0000019200000000000003 s |
1.20 |
add_one / DefOpt / cuda / Primal |
0.000002303 s |
0.0000019200000000000003 s |
1.20 |
add_one / IDefOpt / cuda / Primal |
0.000002303 s |
0.0000019200000000000003 s |
1.20 |
add_one / JaXPipe / cuda / Forward |
0.0000104 s |
0.000010144 s |
1.03 |
add_one / Jax / cuda / Forward |
0.000010112 s |
0.000010112 s |
1 |
add_one / HLOOpt / cuda / Forward |
0.000010433 s |
0.000011391 s |
0.92 |
add_one / PartOpt / cuda / Forward |
0.000010464 s |
0.000009824 s |
1.07 |
add_one / IPartOpt / cuda / Forward |
0.000010656 s |
0.000011392 s |
0.94 |
add_one / DefOpt / cuda / Forward |
0.000010496 s |
0.000011328 s |
0.93 |
add_one / IDefOpt / cuda / Forward |
0.000010271 s |
0.000009953 s |
1.03 |
add_one / JaXPipe / cuda / PreRev |
0.000025984 s |
0.000029536 s |
0.88 |
add_one / JaXPipe / cuda / PostRev |
0.000024736 s |
0.000029408 s |
0.84 |
add_one / JaXPipe / cuda / BothRev |
0.000026304 s |
0.000024704 s |
1.06 |
add_one / Jax / cuda / BothRev |
0.0000256 s |
0.000023936 s |
1.07 |
add_one / HLOOpt / cuda / PreRev |
0.000026271 s |
0.000029056 s |
0.90 |
add_one / HLOOpt / cuda / PostRev |
0.000025024 s |
0.000024895 s |
1.01 |
add_one / HLOOpt / cuda / BothRev |
0.00002528 s |
0.000028992 s |
0.87 |
add_one / PartOpt / cuda / PreRev |
0.000025152 s |
0.000024801 s |
1.01 |
add_one / PartOpt / cuda / PostRev |
0.000025696 s |
0.00002464 s |
1.04 |
add_one / PartOpt / cuda / BothRev |
0.000025632 s |
0.000024736 s |
1.04 |
add_one / IPartOpt / cuda / PreRev |
0.000025631 s |
0.00002496 s |
1.03 |
add_one / IPartOpt / cuda / PostRev |
0.000025664 s |
0.000024607 s |
1.04 |
add_one / IPartOpt / cuda / BothRev |
0.000025472000000000003 s |
0.000024544 s |
1.04 |
add_one / DefOpt / cuda / PreRev |
0.00002496 s |
0.000024896 s |
1.00 |
add_one / DefOpt / cuda / PostRev |
0.000025632 s |
0.00002464 s |
1.04 |
add_one / DefOpt / cuda / BothRev |
0.000025504 s |
0.00002528 s |
1.01 |
add_one / IDefOpt / cuda / PreRev |
0.000025824 s |
0.000024736 s |
1.04 |
add_one / IDefOpt / cuda / PostRev |
0.000025952 s |
0.000024896 s |
1.04 |
add_one / IDefOpt / cuda / BothRev |
0.000025376 s |
0.000024544 s |
1.03 |
add_one / JaXPipe / tpu / Primal |
0.000001427175 s |
0.000001425475 s |
1.00 |
add_one / Jax / tpu / Primal |
0.0000014035 s |
0.000001400975 s |
1.00 |
add_one / HLOOpt / tpu / Primal |
0.0000014274 s |
0.00000143205 s |
1.00 |
add_one / PartOpt / tpu / Primal |
0.0000014040749999999998 s |
0.0000014018749999999998 s |
1.00 |
add_one / IPartOpt / tpu / Primal |
0.00000142675 s |
0.00000142615 s |
1.00 |
add_one / DefOpt / tpu / Primal |
0.0000014067750000000002 s |
0.0000014055 s |
1.00 |
add_one / IDefOpt / tpu / Primal |
0.00000142765 s |
0.000001431325 s |
1.00 |
add_one / JaXPipe / tpu / Forward |
0.0000018545 s |
0.0000018029 s |
1.03 |
add_one / Jax / tpu / Forward |
0.000001844525 s |
0.00000184345 s |
1.00 |
add_one / HLOOpt / tpu / Forward |
0.0000018445 s |
0.000001803225 s |
1.02 |
add_one / PartOpt / tpu / Forward |
0.00000183855 s |
0.000001844125 s |
1.00 |
add_one / IPartOpt / tpu / Forward |
0.0000018445 s |
0.000001798375 s |
1.03 |
add_one / DefOpt / tpu / Forward |
0.00000184355 s |
0.00000183825 s |
1.00 |
add_one / IDefOpt / tpu / Forward |
0.000001852225 s |
0.0000018087 s |
1.02 |
add_one / JaXPipe / tpu / PreRev |
0.000002239075 s |
0.0000022364 s |
1.00 |
add_one / JaXPipe / tpu / PostRev |
0.000002232975 s |
0.000002194825 s |
1.02 |
add_one / JaXPipe / tpu / BothRev |
0.000002230075 s |
0.000002238375 s |
1.00 |
add_one / Jax / tpu / BothRev |
0.0000022493 s |
0.00000217835 s |
1.03 |
add_one / HLOOpt / tpu / PreRev |
0.00000223905 s |
0.000002233875 s |
1.00 |
add_one / HLOOpt / tpu / PostRev |
0.00000223535 s |
0.0000021854000000000003 s |
1.02 |
add_one / HLOOpt / tpu / BothRev |
0.00000224435 s |
0.0000022366 s |
1.00 |
add_one / PartOpt / tpu / PreRev |
0.0000022434 s |
0.0000021858250000000004 s |
1.03 |
add_one / PartOpt / tpu / PostRev |
0.000002232775 s |
0.00000223615 s |
1.00 |
add_one / PartOpt / tpu / BothRev |
0.00000224575 s |
0.0000021889500000000004 s |
1.03 |
add_one / IPartOpt / tpu / PreRev |
0.000002230875 s |
0.000002251875 s |
0.99 |
add_one / IPartOpt / tpu / PostRev |
0.000002239375 s |
0.0000021842 s |
1.03 |
add_one / IPartOpt / tpu / BothRev |
0.00000223475 s |
0.00000223985 s |
1.00 |
add_one / DefOpt / tpu / PreRev |
0.000002246575 s |
0.000002184575 s |
1.03 |
add_one / DefOpt / tpu / PostRev |
0.000002232275 s |
0.000002233075 s |
1.00 |
add_one / DefOpt / tpu / BothRev |
0.0000022449 s |
0.0000021877 s |
1.03 |
add_one / IDefOpt / tpu / PreRev |
0.0000022411 s |
0.000002241625 s |
1.00 |
add_one / IDefOpt / tpu / PostRev |
0.000002244575 s |
0.0000021856000000000003 s |
1.03 |
add_one / IDefOpt / tpu / BothRev |
0.000002235925 s |
0.000002233375 s |
1.00 |
add_one / JaXPipe / cpu / Primal |
0.000016287 s |
0.000007061899959808216 s |
2.31 |
add_one / Jax / cpu / Primal |
0.000016311 s |
0.000007725300010861246 s |
2.11 |
add_one / HLOOpt / cpu / Primal |
0.00001648 s |
0.000007127159988158383 s |
2.31 |
add_one / PartOpt / cpu / Primal |
0.000016492 s |
0.0000064727400240371934 s |
2.55 |
add_one / IPartOpt / cpu / Primal |
0.000016366 s |
0.000006855559977338999 s |
2.39 |
add_one / DefOpt / cpu / Primal |
0.000016330999999999997 s |
0.000006799359998694854 s |
2.40 |
add_one / IDefOpt / cpu / Primal |
0.000016204 s |
0.000006532919996971032 s |
2.48 |
add_one / JaXPipe / cpu / Forward |
0.000022432 s |
0.000010692179985198891 s |
2.10 |
add_one / Jax / cpu / Forward |
0.000022011 s |
0.000009852040057012344 s |
2.23 |
add_one / HLOOpt / cpu / Forward |
0.000022103 s |
0.00001061569998455525 s |
2.08 |
add_one / PartOpt / cpu / Forward |
0.000021894 s |
0.000010313280026821304 s |
2.12 |
add_one / IPartOpt / cpu / Forward |
0.000022175 s |
0.000010236940006507212 s |
2.17 |
add_one / DefOpt / cpu / Forward |
0.000022219 s |
0.00001021022000713856 s |
2.18 |
add_one / IDefOpt / cpu / Forward |
0.000021966 s |
0.00000989591997495154 s |
2.22 |
add_one / JaXPipe / cpu / PreRev |
0.000024711 s |
0.000011687020005410889 s |
2.11 |
add_one / JaXPipe / cpu / PostRev |
0.000024140000000000003 s |
0.000011235759975534164 s |
2.15 |
add_one / JaXPipe / cpu / BothRev |
0.000024108 s |
0.000012070920010955888 s |
2.00 |
add_one / Jax / cpu / BothRev |
0.000024243 s |
0.00001110520000111137 s |
2.18 |
add_one / HLOOpt / cpu / PreRev |
0.000024312 s |
0.0000117855600456096 s |
2.06 |
add_one / HLOOpt / cpu / PostRev |
0.00002469 s |
0.0000174333799895976 s |
1.42 |
add_one / HLOOpt / cpu / BothRev |
0.000024286 s |
0.000011470099998405203 s |
2.12 |
add_one / PartOpt / cpu / PreRev |
0.000024633 s |
0.000011000640006386676 s |
2.24 |
add_one / PartOpt / cpu / PostRev |
0.000024643 s |
0.000011238540000704234 s |
2.19 |
add_one / PartOpt / cpu / BothRev |
0.000024298 s |
0.000011834960005217 s |
2.05 |
add_one / IPartOpt / cpu / PreRev |
0.000024282 s |
0.000011671399961414864 s |
2.08 |
add_one / IPartOpt / cpu / PostRev |
0.00002473 s |
0.000012116419975427562 s |
2.04 |
add_one / IPartOpt / cpu / BothRev |
0.000024642 s |
0.000011671220026983064 s |
2.11 |
add_one / DefOpt / cpu / PreRev |
0.000024803 s |
0.000011632380019364063 s |
2.13 |
add_one / DefOpt / cpu / PostRev |
0.000024186 s |
0.000011632059986368405 s |
2.08 |
add_one / DefOpt / cpu / BothRev |
0.000024643 s |
0.00001143328000580368 s |
2.16 |
add_one / IDefOpt / cpu / PreRev |
0.000025039 s |
0.00001101984002161771 s |
2.27 |
add_one / IDefOpt / cpu / PostRev |
0.000024626 s |
0.000011647559977063794 s |
2.11 |
add_one / IDefOpt / cpu / BothRev |
0.000024622 s |
0.00001107572001274093 s |
2.22 |
add_two / JaXPipe / cpu / Primal |
0.000007352780012297444 s |
0.000006867799966130406 s |
1.07 |
add_two / Jax / cpu / Primal |
0.000007023840007605031 s |
0.000006908039995323634 s |
1.02 |
add_two / HLOOpt / cpu / Primal |
0.000007302940011868486 s |
0.000007006639998508036 s |
1.04 |
add_two / PartOpt / cpu / Primal |
0.000007367939979303628 s |
0.000007027579995337874 s |
1.05 |
add_two / IPartOpt / cpu / Primal |
0.00000707068001247535 s |
0.000007588979979118449 s |
0.93 |
add_two / DefOpt / cpu / Primal |
0.000006897260036566877 s |
0.0000068686600297951375 s |
1.00 |
add_two / IDefOpt / cpu / Primal |
0.000007111559971235692 s |
0.000006989980029175058 s |
1.02 |
add_two / JaXPipe / cpu / Forward |
0.000010896840058194357 s |
0.000010030479979832308 s |
1.09 |
add_two / Jax / cpu / Forward |
0.000010803940012920066 s |
0.000009928719991876278 s |
1.09 |
add_two / HLOOpt / cpu / Forward |
0.00001132066002355714 s |
0.00001017656001749856 s |
1.11 |
add_two / PartOpt / cpu / Forward |
0.000010628779973558268 s |
0.000010274779997416772 s |
1.03 |
add_two / IPartOpt / cpu / Forward |
0.000010467019992574933 s |
0.000010454699986439663 s |
1.00 |
add_two / DefOpt / cpu / Forward |
0.00001064430001861183 s |
0.000010264359962093295 s |
1.04 |
add_two / IDefOpt / cpu / Forward |
0.0000106617399615061 s |
0.00001037967996126099 s |
1.03 |
add_two / JaXPipe / cpu / PreRev |
0.000015257120030582883 s |
0.000013865560013073265 s |
1.10 |
add_two / JaXPipe / cpu / PostRev |
0.000014976320026107714 s |
0.000014588599997296116 s |
1.03 |
add_two / JaXPipe / cpu / BothRev |
0.000014595680013371748 s |
0.000014942600009817398 s |
0.98 |
add_two / Jax / cpu / BothRev |
0.00001503940003203752 s |
0.000013541219987018849 s |
1.11 |
add_two / HLOOpt / cpu / PreRev |
0.000015224779999698513 s |
0.000014437700037888137 s |
1.05 |
add_two / HLOOpt / cpu / PostRev |
0.000017304300035903 s |
0.00001636072001019784 s |
1.06 |
add_two / HLOOpt / cpu / BothRev |
0.0000158201599970198 s |
0.000014554019971910747 s |
1.09 |
add_two / PartOpt / cpu / PreRev |
0.00001535404000605922 s |
0.0000141802000325697 s |
1.08 |
add_two / PartOpt / cpu / PostRev |
0.00001492956002948631 s |
0.0000140553999972326 s |
1.06 |
add_two / PartOpt / cpu / BothRev |
0.000014828399971520411 s |
0.000014440060003835245 s |
1.03 |
add_two / IPartOpt / cpu / PreRev |
0.000015484920049857463 s |
0.000014146200001050602 s |
1.09 |
add_two / IPartOpt / cpu / PostRev |
0.000014987399963501957 s |
0.00001453995997508173 s |
1.03 |
add_two / IPartOpt / cpu / BothRev |
0.000015284160026567408 s |
0.000014311239992821356 s |
1.07 |
add_two / DefOpt / cpu / PreRev |
0.00001545057999464916 s |
0.000013563660022555269 s |
1.14 |
add_two / DefOpt / cpu / PostRev |
0.000014861840045341525 s |
0.00001501925997217768 s |
0.99 |
add_two / DefOpt / cpu / BothRev |
0.000014815800004726044 s |
0.00001491654000346898 s |
0.99 |
add_two / IDefOpt / cpu / PreRev |
0.00001569946002746292 s |
0.00001355600003080326 s |
1.16 |
add_two / IDefOpt / cpu / PostRev |
0.000014131400057522114 s |
0.000014451440019911388 s |
0.98 |
add_two / IDefOpt / cpu / BothRev |
0.000014751260041521163 s |
0.000014129720002529213 s |
1.04 |
add_two / JaXPipe / cuda / Primal |
0.0000024 s |
0.0000019200000000000003 s |
1.25 |
add_two / Jax / cuda / Primal |
0.0000024 s |
0.0000019200000000000003 s |
1.25 |
add_two / HLOOpt / cuda / Primal |
0.0000024 s |
0.0000019200000000000003 s |
1.25 |
add_two / PartOpt / cuda / Primal |
0.0000024 s |
0.000001919 s |
1.25 |
add_two / IPartOpt / cuda / Primal |
0.0000024 s |
0.0000019200000000000003 s |
1.25 |
add_two / DefOpt / cuda / Primal |
0.0000024 s |
0.0000019200000000000003 s |
1.25 |
add_two / IDefOpt / cuda / Primal |
0.0000024 s |
0.0000019200000000000003 s |
1.25 |
add_two / JaXPipe / cuda / Forward |
0.000010752 s |
0.000009664 s |
1.11 |
add_two / Jax / cuda / Forward |
0.0000104 s |
0.000009376 s |
1.11 |
add_two / HLOOpt / cuda / Forward |
0.00001008 s |
0.000009856 s |
1.02 |
add_two / PartOpt / cuda / Forward |
0.000010336 s |
0.000009888 s |
1.05 |
add_two / IPartOpt / cuda / Forward |
0.000010464 s |
0.000009696 s |
1.08 |
add_two / DefOpt / cuda / Forward |
0.000010528 s |
0.000009792 s |
1.08 |
add_two / IDefOpt / cuda / Forward |
0.0000104 s |
0.00000976 s |
1.07 |
add_two / JaXPipe / cuda / PreRev |
0.000032672 s |
0.000032608 s |
1.00 |
add_two / JaXPipe / cuda / PostRev |
0.000032896000000000005 s |
0.000032352 s |
1.02 |
add_two / JaXPipe / cuda / BothRev |
0.000031744 s |
0.00003264 s |
0.97 |
add_two / Jax / cuda / BothRev |
0.000032736 s |
0.000032513 s |
1.01 |
add_two / HLOOpt / cuda / PreRev |
0.000033024 s |
0.00003264 s |
1.01 |
add_two / HLOOpt / cuda / PostRev |
0.000032672 s |
0.000031616 s |
1.03 |
add_two / HLOOpt / cuda / BothRev |
0.000032416 s |
0.000032896000000000005 s |
0.99 |
add_two / PartOpt / cuda / PreRev |
0.000032064 s |
0.000032767999999999995 s |
0.98 |
add_two / PartOpt / cuda / PostRev |
0.000032127999999999995 s |
0.000032064 s |
1.00 |
add_two / PartOpt / cuda / BothRev |
0.000032 s |
0.000032576 s |
0.98 |
add_two / IPartOpt / cuda / PreRev |
0.000032767 s |
0.000032928 s |
1.00 |
add_two / IPartOpt / cuda / PostRev |
0.000032671 s |
0.00003168 s |
1.03 |
add_two / IPartOpt / cuda / BothRev |
0.000032 s |
0.000032576 s |
0.98 |
add_two / DefOpt / cuda / PreRev |
0.000032288 s |
0.000032671 s |
0.99 |
add_two / DefOpt / cuda / PostRev |
0.00003184 s |
0.00003168 s |
1.01 |
add_two / DefOpt / cuda / BothRev |
0.00003232 s |
0.000031647000000000004 s |
1.02 |
add_two / IDefOpt / cuda / PreRev |
0.000033759999999999995 s |
0.000032064 s |
1.05 |
add_two / IDefOpt / cuda / PostRev |
0.000032448 s |
0.000032096 s |
1.01 |
add_two / IDefOpt / cuda / BothRev |
0.000034624 s |
0.000031937 s |
1.08 |
add_two / JaXPipe / tpu / Primal |
0.0000014315249999999998 s |
0.0000014319 s |
1.00 |
add_two / Jax / tpu / Primal |
0.000001472625 s |
0.000001423975 s |
1.03 |
add_two / HLOOpt / tpu / Primal |
0.0000014293 s |
0.0000014321 s |
1.00 |
add_two / PartOpt / tpu / Primal |
0.00000147075 s |
0.000001420075 s |
1.04 |
add_two / IPartOpt / tpu / Primal |
0.0000014236750000000002 s |
0.00000142885 s |
1.00 |
add_two / DefOpt / tpu / Primal |
0.0000014884 s |
0.000001434525 s |
1.04 |
add_two / IDefOpt / tpu / Primal |
0.000001426675 s |
0.000001431175 s |
1.00 |
add_two / JaXPipe / tpu / Forward |
0.000001832375 s |
0.0000018271 s |
1.00 |
add_two / Jax / tpu / Forward |
0.000001835525 s |
0.000001827825 s |
1.00 |
add_two / HLOOpt / tpu / Forward |
0.000001826125 s |
0.00000183625 s |
0.99 |
add_two / PartOpt / tpu / Forward |
0.0000018389 s |
0.00000182075 s |
1.01 |
add_two / IPartOpt / tpu / Forward |
0.0000018237 s |
0.000001831175 s |
1.00 |
add_two / DefOpt / tpu / Forward |
0.000001827525 s |
0.000001834675 s |
1.00 |
add_two / IDefOpt / tpu / Forward |
0.000001829475 s |
0.000001831225 s |
1.00 |
add_two / JaXPipe / tpu / PreRev |
0.0000028336499999999995 s |
0.000002835075 s |
1.00 |
add_two / JaXPipe / tpu / PostRev |
0.000002746725 s |
0.000002755875 s |
1.00 |
add_two / JaXPipe / tpu / BothRev |
0.000002844775 s |
0.0000028421000000000003 s |
1.00 |
add_two / Jax / tpu / BothRev |
0.000002751675 s |
0.000002751975 s |
1.00 |
add_two / HLOOpt / tpu / PreRev |
0.00000283765 s |
0.0000028349 s |
1.00 |
add_two / HLOOpt / tpu / PostRev |
0.000002763925 s |
0.0000027513250000000003 s |
1.00 |
add_two / HLOOpt / tpu / BothRev |
0.0000028384500000000003 s |
0.000002831625 s |
1.00 |
add_two / PartOpt / tpu / PreRev |
0.0000027563749999999995 s |
0.000002742475 s |
1.01 |
add_two / PartOpt / tpu / PostRev |
0.000002841225 s |
0.00000283765 s |
1.00 |
add_two / PartOpt / tpu / BothRev |
0.000002754725 s |
0.000002765825 s |
1.00 |
add_two / IPartOpt / tpu / PreRev |
0.000002845525 s |
0.000002844575 s |
1.00 |
add_two / IPartOpt / tpu / PostRev |
0.000002757075 s |
0.000002751 s |
1.00 |
add_two / IPartOpt / tpu / BothRev |
0.000002845125 s |
0.00000283395 s |
1.00 |
add_two / DefOpt / tpu / PreRev |
0.0000027537 s |
0.000002757975 s |
1.00 |
add_two / DefOpt / tpu / PostRev |
0.0000028369 s |
0.0000028295749999999995 s |
1.00 |
add_two / DefOpt / tpu / BothRev |
0.000002757175 s |
0.00000274965 s |
1.00 |
add_two / IDefOpt / tpu / PreRev |
0.0000028262749999999995 s |
0.00000283355 s |
1.00 |
add_two / IDefOpt / tpu / PostRev |
0.0000027492 s |
0.0000027563749999999995 s |
1.00 |
add_two / IDefOpt / tpu / BothRev |
0.000002836075 s |
0.000002845875 s |
1.00 |
add_two / JaXPipe / cpu / Primal |
0.000016893 s |
0.000006867799966130406 s |
2.46 |
add_two / Jax / cpu / Primal |
0.000016822 s |
0.000006908039995323634 s |
2.44 |
add_two / HLOOpt / cpu / Primal |
0.000016814 s |
0.000007006639998508036 s |
2.40 |
add_two / PartOpt / cpu / Primal |
0.000016916000000000002 s |
0.000007027579995337874 s |
2.41 |
add_two / IPartOpt / cpu / Primal |
0.000016712000000000002 s |
0.000007588979979118449 s |
2.20 |
add_two / DefOpt / cpu / Primal |
0.000016862 s |
0.0000068686600297951375 s |
2.45 |
add_two / IDefOpt / cpu / Primal |
0.000016424 s |
0.000006989980029175058 s |
2.35 |
add_two / JaXPipe / cpu / Forward |
0.000022859 s |
0.000010030479979832308 s |
2.28 |
add_two / Jax / cpu / Forward |
0.000022533000000000003 s |
0.000009928719991876278 s |
2.27 |
add_two / HLOOpt / cpu / Forward |
0.00002204 s |
0.00001017656001749856 s |
2.17 |
add_two / PartOpt / cpu / Forward |
0.000022677 s |
0.000010274779997416772 s |
2.21 |
add_two / IPartOpt / cpu / Forward |
0.00002264 s |
0.000010454699986439663 s |
2.17 |
add_two / DefOpt / cpu / Forward |
0.000022732 s |
0.000010264359962093295 s |
2.21 |
add_two / IDefOpt / cpu / Forward |
0.000022696 s |
0.00001037967996126099 s |
2.19 |
add_two / JaXPipe / cpu / PreRev |
0.000029123 s |
0.000013865560013073265 s |
2.10 |
add_two / JaXPipe / cpu / PostRev |
0.000028398 s |
0.000014588599997296116 s |
1.95 |
add_two / JaXPipe / cpu / BothRev |
0.000028664 s |
0.000014942600009817398 s |
1.92 |
add_two / Jax / cpu / BothRev |
0.000027973 s |
0.000013541219987018849 s |
2.07 |
add_two / HLOOpt / cpu / PreRev |
0.000028032 s |
0.000014437700037888137 s |
1.94 |
add_two / HLOOpt / cpu / PostRev |
0.000028681 s |
0.00001636072001019784 s |
1.75 |
add_two / HLOOpt / cpu / BothRev |
0.000028315 s |
0.000014554019971910747 s |
1.95 |
add_two / PartOpt / cpu / PreRev |
0.000028194 s |
0.0000141802000325697 s |
1.99 |
add_two / PartOpt / cpu / PostRev |
0.000028483 s |
0.0000140553999972326 s |
2.03 |
add_two / PartOpt / cpu / BothRev |
0.000028486 s |
0.000014440060003835245 s |
1.97 |
add_two / IPartOpt / cpu / PreRev |
0.000028273 s |
0.000014146200001050602 s |
2.00 |
add_two / IPartOpt / cpu / PostRev |
0.000028293 s |
0.00001453995997508173 s |
1.95 |
add_two / IPartOpt / cpu / BothRev |
0.000028342 s |
0.000014311239992821356 s |
1.98 |
add_two / DefOpt / cpu / PreRev |
0.000028173 s |
0.000013563660022555269 s |
2.08 |
add_two / DefOpt / cpu / PostRev |
0.000028743 s |
0.00001501925997217768 s |
1.91 |
add_two / DefOpt / cpu / BothRev |
0.000028375 s |
0.00001491654000346898 s |
1.90 |
add_two / IDefOpt / cpu / PreRev |
0.000028259 s |
0.00001355600003080326 s |
2.08 |
add_two / IDefOpt / cpu / PostRev |
0.000029261 s |
0.000014451440019911388 s |
2.02 |
add_two / IDefOpt / cpu / BothRev |
0.000028729 s |
0.000014129720002529213 s |
2.03 |
cache / JaXPipe / cpu / Primal |
0.00000703515999703086 s |
0.000006572259999302332 s |
1.07 |
cache / Jax / cpu / Primal |
0.000006481280006482848 s |
0.000006501319994640653 s |
1.00 |
cache / HLOOpt / cpu / Primal |
0.000006892579958730493 s |
0.00000615048002146068 s |
1.12 |
cache / PartOpt / cpu / Primal |
0.000006388960018739454 s |
0.000006232679988897871 s |
1.03 |
cache / IPartOpt / cpu / Primal |
0.000006422680016839877 s |
0.000006268780007303576 s |
1.02 |
cache / DefOpt / cpu / Primal |
0.000006636940015596337 s |
0.000006588100022781873 s |
1.01 |
cache / IDefOpt / cpu / Primal |
0.0000067897400640504205 s |
0.000006464800007961458 s |
1.05 |
cache / JaXPipe / cpu / Forward |
0.000015402900016852074 s |
0.000014711600006194204 s |
1.05 |
cache / Jax / cpu / Forward |
0.00001615365999896312 s |
0.00001440755996554799 s |
1.12 |
cache / HLOOpt / cpu / Forward |
0.00001568711998515937 s |
0.00001561347999086138 s |
1.00 |
cache / PartOpt / cpu / Forward |
0.000015765419993840625 s |
0.000014749180008948317 s |
1.07 |
cache / IPartOpt / cpu / Forward |
0.000015741440029160005 s |
0.000016127100006997353 s |
0.98 |
cache / DefOpt / cpu / Forward |
0.00001535362001050089 s |
0.000015200499992715775 s |
1.01 |
cache / IDefOpt / cpu / Forward |
0.000016016859999581355 s |
0.000015227600015350615 s |
1.05 |
cache / JaXPipe / cpu / PreRev |
0.00001720934001241403 s |
0.000016161640023710787 s |
1.06 |
cache / JaXPipe / cpu / PostRev |
0.00002033172002484207 s |
0.000021423939997475828 s |
0.95 |
cache / JaXPipe / cpu / BothRev |
0.000017232439959116163 s |
0.00001640085999497387 s |
1.05 |
cache / Jax / cpu / BothRev |
0.00002290846001415048 s |
0.000021007039958931272 s |
1.09 |
cache / HLOOpt / cpu / PreRev |
0.00001822302002437937 s |
0.000016289080003843993 s |
1.12 |
cache / HLOOpt / cpu / PostRev |
0.000018971819981743467 s |
0.000019273419984529027 s |
0.98 |
cache / HLOOpt / cpu / BothRev |
0.000016825060038172522 s |
0.000017125759968621422 s |
0.98 |
cache / PartOpt / cpu / PreRev |
0.000016901340004551457 s |
0.000016171379975276068 s |
1.05 |
cache / PartOpt / cpu / PostRev |
0.00002087683998979628 s |
0.000019693940039360317 s |
1.06 |
cache / PartOpt / cpu / BothRev |
0.000016831579987410805 s |
0.000016042779989220435 s |
1.05 |
cache / IPartOpt / cpu / PreRev |
0.00001679199996033276 s |
0.000015654539993192884 s |
1.07 |
cache / IPartOpt / cpu / PostRev |
0.00002178967999498127 s |
0.00001996903996769106 s |
1.09 |
cache / IPartOpt / cpu / BothRev |
0.000016785419966254267 s |
0.000015126959997360244 s |
1.11 |
cache / DefOpt / cpu / PreRev |
0.000016394440026488156 s |
0.000015228679976644345 s |
1.08 |
cache / DefOpt / cpu / PostRev |
0.000017087640017052764 s |
0.000015360740017058562 s |
1.11 |
cache / DefOpt / cpu / BothRev |
0.00001771725996150053 s |
0.000015114279985937172 s |
1.17 |
cache / IDefOpt / cpu / PreRev |
0.000017714879959385144 s |
0.000015915160092845325 s |
1.11 |
cache / IDefOpt / cpu / PostRev |
0.00001806345996556047 s |
0.000016638339993733097 s |
1.09 |
cache / IDefOpt / cpu / BothRev |
0.00001745837993439636 s |
0.000016164739990927045 s |
1.08 |
cache / JaXPipe / cuda / Primal |
0.000002304 s |
0.000002303 s |
1.00 |
cache / Jax / cuda / Primal |
0.000002335 s |
0.000002304 s |
1.01 |
cache / HLOOpt / cuda / Primal |
0.000002304 s |
0.00000224 s |
1.03 |
cache / PartOpt / cuda / Primal |
0.000002304 s |
0.00000224 s |
1.03 |
cache / IPartOpt / cuda / Primal |
0.000002303 s |
0.000002303 s |
1 |
cache / DefOpt / cuda / Primal |
0.000002336 s |
0.00000224 s |
1.04 |
cache / IDefOpt / cuda / Primal |
0.000002304 s |
0.000002208 s |
1.04 |
cache / JaXPipe / cuda / Forward |
0.000002336 s |
0.000002335 s |
1.00 |
cache / Jax / cuda / Forward |
0.000002336 s |
0.000002304 s |
1.01 |
cache / HLOOpt / cuda / Forward |
0.000002336 s |
0.000002335 s |
1.00 |
cache / PartOpt / cuda / Forward |
0.000002336 s |
0.000002335 s |
1.00 |
cache / IPartOpt / cuda / Forward |
0.000002336 s |
0.000002335 s |
1.00 |
cache / DefOpt / cuda / Forward |
0.000002335 s |
0.000002272 s |
1.03 |
cache / IDefOpt / cuda / Forward |
0.000002336 s |
0.000002335 s |
1.00 |
cache / JaXPipe / cuda / PreRev |
0.000011104 s |
0.000009984 s |
1.11 |
cache / JaXPipe / cuda / PostRev |
0.00001056 s |
0.000010528 s |
1.00 |
cache / JaXPipe / cuda / BothRev |
0.000010816 s |
0.0000104 s |
1.04 |
cache / Jax / cuda / BothRev |
0.000010656 s |
0.000010656 s |
1 |
cache / HLOOpt / cuda / PreRev |
0.000013568 s |
0.000013504 s |
1.00 |
cache / HLOOpt / cuda / PostRev |
0.000013536 s |
0.000013536 s |
1 |
cache / HLOOpt / cuda / BothRev |
0.000013568 s |
0.000013536 s |
1.00 |
cache / PartOpt / cuda / PreRev |
0.00001072 s |
0.000011745 s |
0.91 |
cache / PartOpt / cuda / PostRev |
0.000010976 s |
0.000011520000000000002 s |
0.95 |
cache / PartOpt / cuda / BothRev |
0.000010496 s |
0.000010463 s |
1.00 |
cache / IPartOpt / cuda / PreRev |
0.00001056 s |
0.000010624 s |
0.99 |
cache / IPartOpt / cuda / PostRev |
0.000010656 s |
0.000010432 s |
1.02 |
cache / IPartOpt / cuda / BothRev |
0.000010912 s |
0.0000104 s |
1.05 |
cache / DefOpt / cuda / PreRev |
0.00001104 s |
0.00001072 s |
1.03 |
cache / DefOpt / cuda / PostRev |
0.000010816 s |
0.000010336 s |
1.05 |
cache / DefOpt / cuda / BothRev |
0.00001072 s |
0.000010752 s |
1.00 |
cache / IDefOpt / cuda / PreRev |
0.000010784 s |
0.000010591 s |
1.02 |
cache / IDefOpt / cuda / PostRev |
0.000010528 s |
0.000010304 s |
1.02 |
cache / IDefOpt / cuda / BothRev |
0.000010944 s |
0.000010464 s |
1.05 |
cache / JaXPipe / tpu / Primal |
0.000002458025 s |
0.0000024717 s |
0.99 |
cache / Jax / tpu / Primal |
0.000002463875 s |
0.000002463125 s |
1.00 |
cache / HLOOpt / tpu / Primal |
0.00000246395 s |
0.000002479075 s |
0.99 |
cache / PartOpt / tpu / Primal |
0.0000024572 s |
0.00000247065 s |
0.99 |
cache / IPartOpt / tpu / Primal |
0.000002463925 s |
0.0000024608 s |
1.00 |
cache / DefOpt / tpu / Primal |
0.0000024608250000000003 s |
0.0000024597 s |
1.00 |
cache / IDefOpt / tpu / Primal |
0.000002470675 s |
0.000002462275 s |
1.00 |
cache / JaXPipe / tpu / Forward |
0.0000035389 s |
0.000003541175 s |
1.00 |
cache / Jax / tpu / Forward |
0.00000352655 s |
0.000003548125 s |
0.99 |
cache / HLOOpt / tpu / Forward |
0.000003550425 s |
0.000003560675 s |
1.00 |
cache / PartOpt / tpu / Forward |
0.0000035305 s |
0.000003532225 s |
1.00 |
cache / IPartOpt / tpu / Forward |
0.0000035556 s |
0.00000355105 s |
1.00 |
cache / DefOpt / tpu / Forward |
0.0000035295500000000004 s |
0.0000035362 s |
1.00 |
cache / IDefOpt / tpu / Forward |
0.0000035523250000000003 s |
0.000003544875 s |
1.00 |
cache / JaXPipe / tpu / PreRev |
0.000004939325 s |
0.00000495055 s |
1.00 |
cache / JaXPipe / tpu / PostRev |
0.0000049496 s |
0.00000496035 s |
1.00 |
cache / JaXPipe / tpu / BothRev |
0.000004973425 s |
0.000004976425 s |
1.00 |
cache / Jax / tpu / BothRev |
0.0000049778 s |
0.000004994475 s |
1.00 |
cache / HLOOpt / tpu / PreRev |
0.00000393935 s |
0.0000039297 s |
1.00 |
cache / HLOOpt / tpu / PostRev |
0.000004140825 s |
0.000004137525000000001 s |
1.00 |
cache / HLOOpt / tpu / BothRev |
0.00000396615 s |
0.0000039311 s |
1.01 |
cache / PartOpt / tpu / PreRev |
0.000004972625 s |
0.0000049712 s |
1.00 |
cache / PartOpt / tpu / PostRev |
0.000004962525 s |
0.000004976825 s |
1.00 |
cache / PartOpt / tpu / BothRev |
0.000004987400000000001 s |
0.00000496935 s |
1.00 |
cache / IPartOpt / tpu / PreRev |
0.0000049838500000000006 s |
0.000004975975 s |
1.00 |
cache / IPartOpt / tpu / PostRev |
0.00000497355 s |
0.0000049639 s |
1.00 |
cache / IPartOpt / tpu / BothRev |
0.00000498515 s |
0.0000049710750000000005 s |
1.00 |
cache / DefOpt / tpu / PreRev |
0.000004974025 s |
0.000004988775 s |
1.00 |
cache / DefOpt / tpu / PostRev |
0.00000497755 s |
0.00000495615 s |
1.00 |
cache / DefOpt / tpu / BothRev |
0.000004964624999999999 s |
0.00000498125 s |
1.00 |
cache / IDefOpt / tpu / PreRev |
0.000004966125 s |
0.000004979 s |
1.00 |
cache / IDefOpt / tpu / PostRev |
0.0000049804 s |
0.000004971375 s |
1.00 |
cache / IDefOpt / tpu / BothRev |
0.000004963425000000001 s |
0.000004941475 s |
1.00 |
cache / JaXPipe / cpu / Primal |
0.000018746 s |
0.000006572259999302332 s |
2.85 |
cache / Jax / cpu / Primal |
0.000018664 s |
0.000006501319994640653 s |
2.87 |
cache / HLOOpt / cpu / Primal |
0.000018886 s |
0.00000615048002146068 s |
3.07 |
cache / PartOpt / cpu / Primal |
0.0000188 s |
0.000006232679988897871 s |
3.02 |
cache / IPartOpt / cpu / Primal |
0.000019005 s |
0.000006268780007303576 s |
3.03 |
cache / DefOpt / cpu / Primal |
0.000018801 s |
0.000006588100022781873 s |
2.85 |
cache / IDefOpt / cpu / Primal |
0.000018793 s |
0.000006464800007961458 s |
2.91 |
cache / JaXPipe / cpu / Forward |
0.000021407 s |
0.000014711600006194204 s |
1.46 |
cache / Jax / cpu / Forward |
0.000021713 s |
0.00001440755996554799 s |
1.51 |
cache / HLOOpt / cpu / Forward |
0.000021407 s |
0.00001561347999086138 s |
1.37 |
cache / PartOpt / cpu / Forward |
0.000021528 s |
0.000014749180008948317 s |
1.46 |
cache / IPartOpt / cpu / Forward |
0.000021912 s |
0.000016127100006997353 s |
1.36 |
cache / DefOpt / cpu / Forward |
0.000021429 s |
0.000015200499992715775 s |
1.41 |
cache / IDefOpt / cpu / Forward |
0.000021381 s |
0.000015227600015350615 s |
1.40 |
cache / JaXPipe / cpu / PreRev |
0.000022426 s |
0.000016161640023710787 s |
1.39 |
cache / JaXPipe / cpu / PostRev |
0.000024815 s |
0.000021423939997475828 s |
1.16 |
cache / JaXPipe / cpu / BothRev |
0.000022093 s |
0.00001640085999497387 s |
1.35 |
cache / Jax / cpu / BothRev |
0.000027524 s |
0.000021007039958931272 s |
1.31 |
cache / HLOOpt / cpu / PreRev |
0.00002281 s |
0.000016289080003843993 s |
1.40 |
cache / HLOOpt / cpu / PostRev |
0.000021713 s |
0.000019273419984529027 s |
1.13 |
cache / HLOOpt / cpu / BothRev |
0.000022537 s |
0.000017125759968621422 s |
1.32 |
cache / PartOpt / cpu / PreRev |
0.000021972 s |
0.000016171379975276068 s |
1.36 |
cache / PartOpt / cpu / PostRev |
0.00002734 s |
0.000019693940039360317 s |
1.39 |
cache / PartOpt / cpu / BothRev |
0.000021219 s |
0.000016042779989220435 s |
1.32 |
cache / IPartOpt / cpu / PreRev |
0.000022573 s |
0.000015654539993192884 s |
1.44 |
cache / IPartOpt / cpu / PostRev |
0.00002402 s |
0.00001996903996769106 s |
1.20 |
cache / IPartOpt / cpu / BothRev |
0.000022776 s |
0.000015126959997360244 s |
1.51 |
cache / DefOpt / cpu / PreRev |
0.000022344 s |
0.000015228679976644345 s |
1.47 |
cache / DefOpt / cpu / PostRev |
0.000022585 s |
0.000015360740017058562 s |
1.47 |
cache / DefOpt / cpu / BothRev |
0.000022190000000000003 s |
0.000015114279985937172 s |
1.47 |
cache / IDefOpt / cpu / PreRev |
0.000023259 s |
0.000015915160092845325 s |
1.46 |
cache / IDefOpt / cpu / PostRev |
0.000022371 s |
0.000016638339993733097 s |
1.34 |
cache / IDefOpt / cpu / BothRev |
0.000022109 s |
0.000016164739990927045 s |
1.37 |
Concat / JaXPipe / cpu / Primal |
0.0000072837200059439054 s |
0.000007459219978045439 s |
0.98 |
Concat / Jax / cpu / Primal |
0.000006921380017956835 s |
0.0000072401800116495 s |
0.96 |
Concat / HLOOpt / cpu / Primal |
0.000006893979998494615 s |
0.0000072882999938883585 s |
0.95 |
Concat / PartOpt / cpu / Primal |
0.00000673363994792453 s |
0.000007322039991777274 s |
0.92 |
Concat / IPartOpt / cpu / Primal |
0.000006922380016476382 s |
0.000006696399968859623 s |
1.03 |
Concat / DefOpt / cpu / Primal |
0.00000726314001440187 s |
0.000006468439987656894 s |
1.12 |
Concat / IDefOpt / cpu / Primal |
0.000006981500018810039 s |
0.000006598119989575935 s |
1.06 |
Concat / JaXPipe / cpu / Forward |
0.000010243020024063298 s |
0.000009809859993765712 s |
1.04 |
Concat / Jax / cpu / Forward |
0.000010658020028131431 s |
0.000010438159988552795 s |
1.02 |
Concat / HLOOpt / cpu / Forward |
0.000010832239986484638 s |
0.000010427059996800382 s |
1.04 |
Concat / PartOpt / cpu / Forward |
0.000011084539964940632 s |
0.00001027719998091925 s |
1.08 |
Concat / IPartOpt / cpu / Forward |
0.000010677139971448924 s |
0.000010685560009733309 s |
1.00 |
Concat / DefOpt / cpu / Forward |
0.000010531460011407036 s |
0.000010202059975199518 s |
1.03 |
Concat / IDefOpt / cpu / Forward |
0.00001071437995051383 s |
0.00000999803997729032 s |
1.07 |
Concat / JaXPipe / cpu / PreRev |
0.000012318640046942165 s |
0.000012138919973949667 s |
1.01 |
Concat / JaXPipe / cpu / PostRev |
0.000012623739976334035 s |
0.00001107852001041465 s |
1.14 |
Concat / JaXPipe / cpu / BothRev |
0.000011935380007344063 s |
0.000010961260022668284 s |
1.09 |
Concat / Jax / cpu / BothRev |
0.000011716140006683418 s |
0.00001153500001237262 s |
1.02 |
Concat / HLOOpt / cpu / PreRev |
0.000012878919987997504 s |
0.000012123960059398087 s |
1.06 |
Concat / HLOOpt / cpu / PostRev |
0.000014366100031111272 s |
0.00001364110003123642 s |
1.05 |
Concat / HLOOpt / cpu / BothRev |
0.000012416499985192784 s |
0.000010911959998338716 s |
1.14 |
Concat / PartOpt / cpu / PreRev |
0.000012328079947110382 s |
0.00001119947999541182 s |
1.10 |
Concat / PartOpt / cpu / PostRev |
0.000012449759960873052 s |
0.000011387060012566508 s |
1.09 |
Concat / PartOpt / cpu / BothRev |
0.000012604939993252628 s |
0.000012363559999357677 s |
1.02 |
Concat / IPartOpt / cpu / PreRev |
0.000012384740030029206 s |
0.000012330119961916352 s |
1.00 |
Concat / IPartOpt / cpu / PostRev |
0.00001236557999618526 s |
0.000011503100004119916 s |
1.07 |
Concat / IPartOpt / cpu / BothRev |
0.00001235948001522047 s |
0.000011435539990998222 s |
1.08 |
Concat / DefOpt / cpu / PreRev |
0.000012153559955550009 s |
0.000011610259998633407 s |
1.05 |
Concat / DefOpt / cpu / PostRev |
0.0000125023399687052 s |
0.000011580839955058763 s |
1.08 |
Concat / DefOpt / cpu / BothRev |
0.000012181199945189292 s |
0.000011326979984005448 s |
1.08 |
Concat / IDefOpt / cpu / PreRev |
0.00001198115998704452 s |
0.000011609920002229044 s |
1.03 |
Concat / IDefOpt / cpu / PostRev |
0.000012231559985593776 s |
0.000011728899999070565 s |
1.04 |
Concat / IDefOpt / cpu / BothRev |
0.000012601960006577427 s |
0.0000115970599836146 s |
1.09 |
Concat / JaXPipe / cuda / Primal |
0.0000024 s |
0.000001888 s |
1.27 |
Concat / Jax / cuda / Primal |
0.0000024 s |
0.0000019200000000000003 s |
1.25 |
Concat / HLOOpt / cuda / Primal |
0.0000024 s |
0.0000019200000000000003 s |
1.25 |
Concat / PartOpt / cuda / Primal |
0.000002431 s |
0.0000019200000000000003 s |
1.27 |
Concat / IPartOpt / cuda / Primal |
0.0000024 s |
0.0000019200000000000003 s |
1.25 |
Concat / DefOpt / cuda / Primal |
0.0000024 s |
0.0000019200000000000003 s |
1.25 |
Concat / IDefOpt / cuda / Primal |
0.0000024 s |
0.0000019200000000000003 s |
1.25 |
Concat / JaXPipe / cuda / Forward |
0.000010816 s |
0.000009887 s |
1.09 |
Concat / Jax / cuda / Forward |
0.000010656 s |
0.000010176 s |
1.05 |
Concat / HLOOpt / cuda / Forward |
0.00001056 s |
0.000009824 s |
1.07 |
Concat / PartOpt / cuda / Forward |
0.000010432 s |
0.000009631 s |
1.08 |
Concat / IPartOpt / cuda / Forward |
0.000010528 s |
0.000010304 s |
1.02 |
Concat / DefOpt / cuda / Forward |
0.00001056 s |
0.000010048 s |
1.05 |
Concat / IDefOpt / cuda / Forward |
0.000010433 s |
0.00000944 s |
1.11 |
Concat / JaXPipe / cuda / PreRev |
0.000017184 s |
0.000016545 s |
1.04 |
Concat / JaXPipe / cuda / PostRev |
0.00001696 s |
0.00001584 s |
1.07 |
Concat / JaXPipe / cuda / BothRev |
0.000016672 s |
0.00001632 s |
1.02 |
Concat / Jax / cuda / BothRev |
0.00001696 s |
0.000016032 s |
1.06 |
Concat / HLOOpt / cuda / PreRev |
0.000016927999999999998 s |
0.000015968 s |
1.06 |
Concat / HLOOpt / cuda / PostRev |
0.000016704 s |
0.00001584 s |
1.05 |
Concat / HLOOpt / cuda / BothRev |
0.000017152 s |
0.000016576000000000002 s |
1.03 |
Concat / PartOpt / cuda / PreRev |
0.000016607 s |
0.000016 s |
1.04 |
Concat / PartOpt / cuda / PostRev |
0.000016896000000000002 s |
0.000016063999999999997 s |
1.05 |
Concat / PartOpt / cuda / BothRev |
0.000016608 s |
0.000016288 s |
1.02 |
Concat / IPartOpt / cuda / PreRev |
0.000016864 s |
0.000016416 s |
1.03 |
Concat / IPartOpt / cuda / PostRev |
0.000017088 s |
0.00001584 s |
1.08 |
Concat / IPartOpt / cuda / BothRev |
0.000016672 s |
0.000016 s |
1.04 |
Concat / DefOpt / cuda / PreRev |
0.000016672 s |
0.000016192 s |
1.03 |
Concat / DefOpt / cuda / PostRev |
0.000016544 s |
0.000016511 s |
1.00 |
Concat / DefOpt / cuda / BothRev |
0.000017056 s |
0.00001584 s |
1.08 |
Concat / IDefOpt / cuda / PreRev |
0.000016576000000000002 s |
0.00001616 s |
1.03 |
Concat / IDefOpt / cuda / PostRev |
0.000016863 s |
0.000015712 s |
1.07 |
Concat / IDefOpt / cuda / BothRev |
0.00001664 s |
0.000016608 s |
1.00 |
Concat / JaXPipe / tpu / Primal |
0.000001531875 s |
0.0000014826 s |
1.03 |
Concat / Jax / tpu / Primal |
0.0000015232499999999998 s |
0.0000014854999999999998 s |
1.03 |
Concat / HLOOpt / tpu / Primal |
0.000001526225 s |
0.0000014761 s |
1.03 |
Concat / PartOpt / tpu / Primal |
0.00000152175 s |
0.0000014868 s |
1.02 |
Concat / IPartOpt / tpu / Primal |
0.000001530375 s |
0.000001476675 s |
1.04 |
Concat / DefOpt / tpu / Primal |
0.000001529075 s |
0.0000014921 s |
1.02 |
Concat / IDefOpt / tpu / Primal |
0.0000015343 s |
0.0000014804 s |
1.04 |
Concat / JaXPipe / tpu / Forward |
0.000001567825 s |
0.0000015552 s |
1.01 |
Concat / Jax / tpu / Forward |
0.0000015580250000000002 s |
0.000001504375 s |
1.04 |
Concat / HLOOpt / tpu / Forward |
0.000001583725 s |
0.00000154035 s |
1.03 |
Concat / PartOpt / tpu / Forward |
0.00000156155 s |
0.00000151385 s |
1.03 |
Concat / IPartOpt / tpu / Forward |
0.0000015799 s |
0.000001547175 s |
1.02 |
Concat / DefOpt / tpu / Forward |
0.0000015544250000000002 s |
0.000001514675 s |
1.03 |
Concat / IDefOpt / tpu / Forward |
0.000001575825 s |
0.000001551225 s |
1.02 |
Concat / JaXPipe / tpu / PreRev |
0.000002000525 s |
0.0000019532250000000003 s |
1.02 |
Concat / JaXPipe / tpu / PostRev |
0.000002093125 s |
0.000002041625 s |
1.03 |
Concat / JaXPipe / tpu / BothRev |
0.0000020023750000000005 s |
0.0000019443750000000003 s |
1.03 |
Concat / Jax / tpu / BothRev |
0.000002086275 s |
0.000002032475 s |
1.03 |
Concat / HLOOpt / tpu / PreRev |
0.000002006625 s |
0.0000019443750000000003 s |
1.03 |
Concat / HLOOpt / tpu / PostRev |
0.00000207315 s |
0.000002035425 s |
1.02 |
Concat / HLOOpt / tpu / BothRev |
0.000002004675 s |
0.00000195195 s |
1.03 |
Concat / PartOpt / tpu / PreRev |
0.000002073075 s |
0.000002037175 s |
1.02 |
Concat / PartOpt / tpu / PostRev |
0.000002008475 s |
0.000001951725 s |
1.03 |
Concat / PartOpt / tpu / BothRev |
0.00000208055 s |
0.0000020347 s |
1.02 |
Concat / IPartOpt / tpu / PreRev |
0.0000020052 s |
0.00000195195 s |
1.03 |
Concat / IPartOpt / tpu / PostRev |
0.000002071875 s |
0.0000020362 s |
1.02 |
Concat / IPartOpt / tpu / BothRev |
0.000002009775 s |
0.00000194775 s |
1.03 |
Concat / DefOpt / tpu / PreRev |
0.00000206905 s |
0.0000020317 s |
1.02 |
Concat / DefOpt / tpu / PostRev |
0.00000200295 s |
0.000001952 s |
1.03 |
Concat / DefOpt / tpu / BothRev |
0.0000020736 s |
0.000002034425 s |
1.02 |
Concat / IDefOpt / tpu / PreRev |
0.000002004825 s |
0.00000194375 s |
1.03 |
Concat / IDefOpt / tpu / PostRev |
0.000002073175 s |
0.00000203705 s |
1.02 |
Concat / IDefOpt / tpu / BothRev |
0.000002019025 s |
0.000001943275 s |
1.04 |
Concat / JaXPipe / cpu / Primal |
0.000016271 s |
0.000007459219978045439 s |
2.18 |
Concat / Jax / cpu / Primal |
0.000016385 s |
0.0000072401800116495 s |
2.26 |
Concat / HLOOpt / cpu / Primal |
0.000016308 s |
0.0000072882999938883585 s |
2.24 |
Concat / PartOpt / cpu / Primal |
0.000016233999999999997 s |
0.000007322039991777274 s |
2.22 |
Concat / IPartOpt / cpu / Primal |
0.000016502 s |
0.000006696399968859623 s |
2.46 |
Concat / DefOpt / cpu / Primal |
0.000016357 s |
0.000006468439987656894 s |
2.53 |
Concat / IDefOpt / cpu / Primal |
0.000016388 s |
0.000006598119989575935 s |
2.48 |
Concat / JaXPipe / cpu / Forward |
0.000022094 s |
0.000009809859993765712 s |
2.25 |
Concat / Jax / cpu / Forward |
0.000021833000000000003 s |
0.000010438159988552795 s |
2.09 |
Concat / HLOOpt / cpu / Forward |
0.000021861 s |
0.000010427059996800382 s |
2.10 |
Concat / PartOpt / cpu / Forward |
0.000021752 s |
0.00001027719998091925 s |
2.12 |
Concat / IPartOpt / cpu / Forward |
0.000021993 s |
0.000010685560009733309 s |
2.06 |
Concat / DefOpt / cpu / Forward |
0.000021576 s |
0.000010202059975199518 s |
2.11 |
Concat / IDefOpt / cpu / Forward |
0.000021602 s |
0.00000999803997729032 s |
2.16 |
Concat / JaXPipe / cpu / PreRev |
0.000024894 s |
0.000012138919973949667 s |
2.05 |
Concat / JaXPipe / cpu / PostRev |
0.000024047 s |
0.00001107852001041465 s |
2.17 |
Concat / JaXPipe / cpu / BothRev |
0.00002412 s |
0.000010961260022668284 s |
2.20 |
Concat / Jax / cpu / BothRev |
0.000025439 s |
0.00001153500001237262 s |
2.21 |
Concat / HLOOpt / cpu / PreRev |
0.000024853 s |
0.000012123960059398087 s |
2.05 |
Concat / HLOOpt / cpu / PostRev |
0.000024595 s |
0.00001364110003123642 s |
1.80 |
Concat / HLOOpt / cpu / BothRev |
0.000023725 s |
0.000010911959998338716 s |
2.17 |
Concat / PartOpt / cpu / PreRev |
0.00002466 s |
0.00001119947999541182 s |
2.20 |
Concat / PartOpt / cpu / PostRev |
0.000024136 s |
0.000011387060012566508 s |
2.12 |
Concat / PartOpt / cpu / BothRev |
0.000024135 s |
0.000012363559999357677 s |
1.95 |
Concat / IPartOpt / cpu / PreRev |
0.000024518 s |
0.000012330119961916352 s |
1.99 |
Concat / IPartOpt / cpu / PostRev |
0.000024315 s |
0.000011503100004119916 s |
2.11 |
Concat / IPartOpt / cpu / BothRev |
0.000024385 s |
0.000011435539990998222 s |
2.13 |
Concat / DefOpt / cpu / PreRev |
0.000024394 s |
0.000011610259998633407 s |
2.10 |
Concat / DefOpt / cpu / PostRev |
0.000024824 s |
0.000011580839955058763 s |
2.14 |
Concat / DefOpt / cpu / BothRev |
0.000024718 s |
0.000011326979984005448 s |
2.18 |
Concat / IDefOpt / cpu / PreRev |
0.000025113 s |
0.000011609920002229044 s |
2.16 |
Concat / IDefOpt / cpu / PostRev |
0.000024463 s |
0.000011728899999070565 s |
2.09 |
Concat / IDefOpt / cpu / BothRev |
0.000024249 s |
0.0000115970599836146 s |
2.09 |
const_scatter / JaXPipe / cpu / Primal |
0.000006942440004422678 s |
0.000006414199997379911 s |
1.08 |
const_scatter / Jax / cpu / Primal |
0.000006782720001865527 s |
0.000006381759994837921 s |
1.06 |
const_scatter / HLOOpt / cpu / Primal |
0.000007485039996026898 s |
0.000007092419973560027 s |
1.06 |
const_scatter / PartOpt / cpu / Primal |
0.000006834959976913524 s |
0.000006388200008586864 s |
1.07 |
const_scatter / IPartOpt / cpu / Primal |
0.000006775319989174023 s |
0.000007287040007213363 s |
0.93 |
const_scatter / DefOpt / cpu / Primal |
0.00000752270002521982 s |
0.000006763159999536583 s |
1.11 |
const_scatter / IDefOpt / cpu / Primal |
0.000007737359965176438 s |
0.000007052119999571005 s |
1.10 |
const_scatter / JaXPipe / cpu / Forward |
0.0000114659000064421 s |
0.000010790360001919908 s |
1.06 |
const_scatter / Jax / cpu / Forward |
0.000010237739979856995 s |
0.000009555260021443246 s |
1.07 |
const_scatter / HLOOpt / cpu / Forward |
0.000011819380006272697 s |
0.000011073819969169565 s |
1.07 |
const_scatter / PartOpt / cpu / Forward |
0.00001176101997771184 s |
0.000010634000009304144 s |
1.11 |
const_scatter / IPartOpt / cpu / Forward |
0.000011280500029897666 s |
0.000010531140032981057 s |
1.07 |
const_scatter / DefOpt / cpu / Forward |
0.000011436239983595442 s |
0.000010720419995777774 s |
1.07 |
const_scatter / IDefOpt / cpu / Forward |
0.00001176203997601988 s |
0.000010679459992388729 s |
1.10 |
const_scatter / JaXPipe / cpu / PreRev |
0.0002922202800436 s |
0.0002888223200261 s |
1.01 |
const_scatter / JaXPipe / cpu / PostRev |
0.0002837334600189 s |
0.0002839717799724 s |
1.00 |
const_scatter / JaXPipe / cpu / BothRev |
0.0002878149000389 s |
0.0002854160999595 s |
1.01 |
const_scatter / Jax / cpu / BothRev |
0.0002857083800063 s |
0.0002842025400059 s |
1.01 |
const_scatter / HLOOpt / cpu / PreRev |
0.0002875807999771 s |
0.0002855643800376 s |
1.01 |
const_scatter / HLOOpt / cpu / PostRev |
0.0002913887399972 s |
0.0002889120800318 s |
1.01 |
const_scatter / HLOOpt / cpu / BothRev |
0.0002873395399456 s |
0.0002857153400054 s |
1.01 |
const_scatter / PartOpt / cpu / PreRev |
0.0002878320199943 s |
0.000283256499988 s |
1.02 |
const_scatter / PartOpt / cpu / PostRev |
0.0002853346000392 s |
0.0002831990800314 s |
1.01 |
const_scatter / PartOpt / cpu / BothRev |
0.0002866487000574 s |
0.0002844155800357 s |
1.01 |
const_scatter / IPartOpt / cpu / PreRev |
0.0002906409999559 s |
0.0002835344200138 s |
1.03 |
const_scatter / IPartOpt / cpu / PostRev |
0.0002858707000177 s |
0.0002824978799799 s |
1.01 |
const_scatter / IPartOpt / cpu / BothRev |
0.0002870949999851 s |
0.0002845528399939 s |
1.01 |
const_scatter / DefOpt / cpu / PreRev |
0.0002860695399976 s |
0.0002848829400136 s |
1.00 |
const_scatter / DefOpt / cpu / PostRev |
0.0002878341799987 s |
0.0002848792600161 s |
1.01 |
const_scatter / DefOpt / cpu / BothRev |
0.0002880138000091 s |
0.0002847787200244 s |
1.01 |
const_scatter / IDefOpt / cpu / PreRev |
0.0002853387000504 s |
0.0002828045599926 s |
1.01 |
const_scatter / IDefOpt / cpu / PostRev |
0.0002877711400014 s |
0.0002841483999873 s |
1.01 |
const_scatter / IDefOpt / cpu / BothRev |
0.0002866851399448 s |
0.0002834731599705 s |
1.01 |
const_scatter / JaXPipe / cuda / Primal |
0.0000024 s |
0.000001887 s |
1.27 |
const_scatter / Jax / cuda / Primal |
0.0000024 s |
0.000001887 s |
1.27 |
const_scatter / HLOOpt / cuda / Primal |
0.0000024 s |
0.000001887 s |
1.27 |
const_scatter / PartOpt / cuda / Primal |
0.0000024 s |
0.000001888 s |
1.27 |
const_scatter / IPartOpt / cuda / Primal |
0.000002431 s |
0.000001887 s |
1.29 |
const_scatter / DefOpt / cuda / Primal |
0.0000024 s |
0.000001887 s |
1.27 |
const_scatter / IDefOpt / cuda / Primal |
0.0000024 s |
0.000001887 s |
1.27 |
const_scatter / JaXPipe / cuda / Forward |
0.000010624 s |
0.000009632 s |
1.10 |
const_scatter / Jax / cuda / Forward |
0.000010528 s |
0.00001008 s |
1.04 |
const_scatter / HLOOpt / cuda / Forward |
0.000010848 s |
0.000010016 s |
1.08 |
const_scatter / PartOpt / cuda / Forward |
0.000010752 s |
0.000009568 s |
1.12 |
const_scatter / IPartOpt / cuda / Forward |
0.000010752 s |
0.000010081 s |
1.07 |
const_scatter / DefOpt / cuda / Forward |
0.000010592 s |
0.000010048 s |
1.05 |
const_scatter / IDefOpt / cuda / Forward |
0.000010592 s |
0.000010144 s |
1.04 |
const_scatter / JaXPipe / cuda / PreRev |
0.000016672 s |
0.000016576000000000002 s |
1.01 |
const_scatter / JaXPipe / cuda / PostRev |
0.000016672 s |
0.000016096 s |
1.04 |
const_scatter / JaXPipe / cuda / BothRev |
0.00001648 s |
0.000015935999999999998 s |
1.03 |
const_scatter / Jax / cuda / BothRev |
0.000016608 s |
0.000016576000000000002 s |
1.00 |
const_scatter / HLOOpt / cuda / PreRev |
0.000016768000000000003 s |
0.000016416 s |
1.02 |
const_scatter / HLOOpt / cuda / PostRev |
0.000016672 s |
0.000016383999999999998 s |
1.02 |
const_scatter / HLOOpt / cuda / BothRev |
0.00001664 s |
0.00001616 s |
1.03 |
const_scatter / PartOpt / cuda / PreRev |
0.000016927999999999998 s |
0.000015744 s |
1.08 |
const_scatter / PartOpt / cuda / PostRev |
0.000016864 s |
0.00001616 s |
1.04 |
const_scatter / PartOpt / cuda / BothRev |
0.000016351 s |
0.000016031 s |
1.02 |
const_scatter / IPartOpt / cuda / PreRev |
0.000016416 s |
0.000016063999999999997 s |
1.02 |
const_scatter / IPartOpt / cuda / PostRev |
0.00001648 s |
0.00001664 s |
0.99 |
const_scatter / IPartOpt / cuda / BothRev |
0.000016544 s |
0.000016255999999999998 s |
1.02 |
const_scatter / DefOpt / cuda / PreRev |
0.000017056 s |
0.000016288 s |
1.05 |
const_scatter / DefOpt / cuda / PostRev |
0.000016768000000000003 s |
0.000015935999999999998 s |
1.05 |
const_scatter / DefOpt / cuda / BothRev |
0.000016704 s |
0.000015904000000000002 s |
1.05 |
const_scatter / IDefOpt / cuda / PreRev |
0.000016704 s |
0.000015808 s |
1.06 |
const_scatter / IDefOpt / cuda / PostRev |
0.000016896000000000002 s |
0.00001712 s |
0.99 |
const_scatter / IDefOpt / cuda / BothRev |
0.000016672 s |
0.000015935999999999998 s |
1.05 |
const_scatter / JaXPipe / tpu / Primal |
0.00000380255 s |
0.000003813725 s |
1.00 |
const_scatter / Jax / tpu / Primal |
0.00000380495 s |
0.000003810925 s |
1.00 |
const_scatter / HLOOpt / tpu / Primal |
0.00000380265 s |
0.000003826475 s |
0.99 |
const_scatter / PartOpt / tpu / Primal |
0.0000038142 s |
0.000003823775 s |
1.00 |
const_scatter / IPartOpt / tpu / Primal |
0.000003787525 s |
0.000003800625 s |
1.00 |
const_scatter / DefOpt / tpu / Primal |
0.000003814275 s |
0.0000038115 s |
1.00 |
const_scatter / IDefOpt / tpu / Primal |
0.00000380185 s |
0.000003787725 s |
1.00 |
const_scatter / JaXPipe / tpu / Forward |
0.00000645125 s |
0.000006466275 s |
1.00 |
const_scatter / Jax / tpu / Forward |
0.00000648315 s |
0.0000065071 s |
1.00 |
const_scatter / HLOOpt / tpu / Forward |
0.0000064634 s |
0.000006460749999999999 s |
1.00 |
const_scatter / PartOpt / tpu / Forward |
0.00000648155 s |
0.000006514025 s |
1.00 |
const_scatter / IPartOpt / tpu / Forward |
0.0000064754 s |
0.00000643815 s |
1.01 |
const_scatter / DefOpt / tpu / Forward |
0.000006464299999999999 s |
0.00000649575 s |
1.00 |
const_scatter / IDefOpt / tpu / Forward |
0.00000645075 s |
0.000006461475 s |
1.00 |
const_scatter / JaXPipe / tpu / PreRev |
0.0000066127 s |
0.00000667555 s |
0.99 |
const_scatter / JaXPipe / tpu / PostRev |
0.000006620374999999999 s |
0.000006664774999999999 s |
0.99 |
const_scatter / JaXPipe / tpu / BothRev |
0.00000659845 s |
0.0000066576250000000005 s |
0.99 |
const_scatter / Jax / tpu / BothRev |
0.000006601825 s |
0.0000066598 s |
0.99 |
const_scatter / HLOOpt / tpu / PreRev |
0.0000066093 s |
0.0000066682 s |
0.99 |
const_scatter / HLOOpt / tpu / PostRev |
0.00000660655 s |
0.000006652350000000001 s |
0.99 |
const_scatter / HLOOpt / tpu / BothRev |
0.0000066264 s |
0.000006684425000000001 s |
0.99 |
const_scatter / PartOpt / tpu / PreRev |
0.000006608074999999999 s |
0.000006659425 s |
0.99 |
const_scatter / PartOpt / tpu / PostRev |
0.000006594449999999999 s |
0.0000066629 s |
0.99 |
const_scatter / PartOpt / tpu / BothRev |
0.00000662995 s |
0.000006664474999999999 s |
0.99 |
const_scatter / IPartOpt / tpu / PreRev |
0.000006589424999999999 s |
0.000006663175 s |
0.99 |
const_scatter / IPartOpt / tpu / PostRev |
0.000006604125 s |
0.000006668525 s |
0.99 |
const_scatter / IPartOpt / tpu / BothRev |
0.0000065919500000000005 s |
0.00000667465 s |
0.99 |
const_scatter / DefOpt / tpu / PreRev |
0.00000662365 s |
0.000006678150000000001 s |
0.99 |
const_scatter / DefOpt / tpu / PostRev |
0.0000066049 s |
0.0000066493 s |
0.99 |
const_scatter / DefOpt / tpu / BothRev |
0.0000066047 s |
0.000006677975 s |
0.99 |
const_scatter / IDefOpt / tpu / PreRev |
0.000006596575 s |
0.000006650975 s |
0.99 |
const_scatter / IDefOpt / tpu / PostRev |
0.000006620825 s |
0.000006669874999999999 s |
0.99 |
const_scatter / IDefOpt / tpu / BothRev |
0.000006612 s |
0.00000665875 s |
0.99 |
const_scatter / JaXPipe / cpu / Primal |
0.000016258000000000003 s |
0.000006414199997379911 s |
2.53 |
const_scatter / Jax / cpu / Primal |
0.000015996 s |
0.000006381759994837921 s |
2.51 |
const_scatter / HLOOpt / cpu / Primal |
0.000016801 s |
0.000007092419973560027 s |
2.37 |
const_scatter / PartOpt / cpu / Primal |
0.00001609 s |
0.000006388200008586864 s |
2.52 |
const_scatter / IPartOpt / cpu / Primal |
0.00001604 s |
0.000007287040007213363 s |
2.20 |
const_scatter / DefOpt / cpu / Primal |
0.000017035999999999997 s |
0.000006763159999536583 s |
2.52 |
const_scatter / IDefOpt / cpu / Primal |
0.000017076 s |
0.000007052119999571005 s |
2.42 |
const_scatter / JaXPipe / cpu / Forward |
0.000022700000000000003 s |
0.000010790360001919908 s |
2.10 |
const_scatter / Jax / cpu / Forward |
0.00002104 s |
0.000009555260021443246 s |
2.20 |
const_scatter / HLOOpt / cpu / Forward |
0.000022671 s |
0.000011073819969169565 s |
2.05 |
const_scatter / PartOpt / cpu / Forward |
0.000022578 s |
0.000010634000009304144 s |
2.12 |
const_scatter / IPartOpt / cpu / Forward |
0.000022519 s |
0.000010531140032981057 s |
2.14 |
const_scatter / DefOpt / cpu / Forward |
0.000022517 s |
0.000010720419995777774 s |
2.10 |
const_scatter / IDefOpt / cpu / Forward |
0.000022841 s |
0.000010679459992388729 s |
2.14 |
const_scatter / JaXPipe / cpu / PreRev |
0.0005289009999999 s |
0.0002888223200261 s |
1.83 |
const_scatter / JaXPipe / cpu / PostRev |
0.000528158 s |
0.0002839717799724 s |
1.86 |
const_scatter / JaXPipe / cpu / BothRev |
0.000534416 s |
0.0002854160999595 s |
1.87 |
const_scatter / Jax / cpu / BothRev |
0.000535907 s |
0.0002842025400059 s |
1.89 |
const_scatter / HLOOpt / cpu / PreRev |
0.000547216 s |
0.0002855643800376 s |
1.92 |
const_scatter / HLOOpt / cpu / PostRev |
0.000531717 s |
0.0002889120800318 s |
1.84 |
const_scatter / HLOOpt / cpu / BothRev |
0.000538897 s |
0.0002857153400054 s |
1.89 |
const_scatter / PartOpt / cpu / PreRev |
0.000546002 s |
0.000283256499988 s |
1.93 |
const_scatter / PartOpt / cpu / PostRev |
0.000538957 s |
0.0002831990800314 s |
1.90 |
const_scatter / PartOpt / cpu / BothRev |
0.00055507 s |
0.0002844155800357 s |
1.95 |
const_scatter / IPartOpt / cpu / PreRev |
0.000530415 s |
0.0002835344200138 s |
1.87 |
const_scatter / IPartOpt / cpu / PostRev |
0.0005393409999999 s |
0.0002824978799799 s |
1.91 |
const_scatter / IPartOpt / cpu / BothRev |
0.00053379 s |
0.0002845528399939 s |
1.88 |
const_scatter / DefOpt / cpu / PreRev |
0.000542865 s |
0.0002848829400136 s |
1.91 |
const_scatter / DefOpt / cpu / PostRev |
0.000531501 s |
0.0002848792600161 s |
1.87 |
const_scatter / DefOpt / cpu / BothRev |
0.000533267 s |
0.0002847787200244 s |
1.87 |
const_scatter / IDefOpt / cpu / PreRev |
0.000526363 s |
0.0002828045599926 s |
1.86 |
const_scatter / IDefOpt / cpu / PostRev |
0.000543177 s |
0.0002841483999873 s |
1.91 |
const_scatter / IDefOpt / cpu / BothRev |
0.00053693 s |
0.0002834731599705 s |
1.89 |
GenDot / JaXPipe / cpu / Primal |
0.00000785711996286409 s |
0.000007298380041902419 s |
1.08 |
GenDot / Jax / cpu / Primal |
0.000007979060001161997 s |
0.000007048700008454034 s |
1.13 |
GenDot / HLOOpt / cpu / Primal |
0.000008108880037980271 s |
0.00000794292001046415 s |
1.02 |
GenDot / PartOpt / cpu / Primal |
0.000007248740021168487 s |
0.000006769920055376133 s |
1.07 |
GenDot / IPartOpt / cpu / Primal |
0.000007814359969415819 s |
0.000007515740007875138 s |
1.04 |
GenDot / DefOpt / cpu / Primal |
0.00000745851998544822 s |
0.000007409619984173332 s |
1.01 |
GenDot / IDefOpt / cpu / Primal |
0.000007287919979717117 s |
0.000007622040011483477 s |
0.96 |
GenDot / JaXPipe / cpu / Forward |
0.000011590379999688594 s |
0.000011569240014068782 s |
1.00 |
GenDot / Jax / cpu / Forward |
0.000010831540021172258 s |
0.000009718079991216654 s |
1.11 |
GenDot / HLOOpt / cpu / Forward |
0.000011714159973053028 s |
0.000011745740011974704 s |
1.00 |
GenDot / PartOpt / cpu / Forward |
0.00001143725995461864 s |
0.000011508360021252884 s |
0.99 |
GenDot / IPartOpt / cpu / Forward |
0.00001174454007013992 s |
0.000011128580026706914 s |
1.06 |
GenDot / DefOpt / cpu / Forward |
0.000011835579980470355 s |
0.000010798399998748209 s |
1.10 |
GenDot / IDefOpt / cpu / Forward |
0.00001138744002673775 s |
0.00001077956000699487 s |
1.06 |
GenDot / JaXPipe / cpu / PreRev |
0.00001151437999396876 s |
0.000010790999995151652 s |
1.07 |
GenDot / JaXPipe / cpu / PostRev |
0.000010849239997696711 s |
0.000010381940037405 s |
1.05 |
GenDot / JaXPipe / cpu / BothRev |
0.000011640240018095938 s |
0.000011352839983373995 s |
1.03 |
GenDot / Jax / cpu / BothRev |
0.00001215170002069499 s |
0.000011042040014217492 s |
1.10 |
GenDot / HLOOpt / cpu / PreRev |
0.000011743560035029076 s |
0.000011735859989130403 s |
1.00 |
GenDot / HLOOpt / cpu / PostRev |
0.00001364941998872382 s |
0.000013340659997993496 s |
1.02 |
GenDot / HLOOpt / cpu / BothRev |
0.000012027779966956586 s |
0.000010679819979486638 s |
1.13 |
GenDot / PartOpt / cpu / PreRev |
0.000011477460011519725 s |
0.000010874159997911192 s |
1.06 |
GenDot / PartOpt / cpu / PostRev |
0.00001051305997862073 s |
0.000011166739977852555 s |
0.94 |
GenDot / PartOpt / cpu / BothRev |
0.000012005600037809929 s |
0.000011426359942561248 s |
1.05 |
GenDot / IPartOpt / cpu / PreRev |
0.000011795319987868423 s |
0.000010923079989879626 s |
1.08 |
GenDot / IPartOpt / cpu / PostRev |
0.000010875979996853858 s |
0.000010891519996221178 s |
1.00 |
GenDot / IPartOpt / cpu / BothRev |
0.000011626440045802157 s |
0.000011160020021634409 s |
1.04 |
GenDot / DefOpt / cpu / PreRev |
0.00001203732000249147 s |
0.000011140939977849483 s |
1.08 |
GenDot / DefOpt / cpu / PostRev |
0.000011123419972136616 s |
0.000011533419992701966 s |
0.96 |
GenDot / DefOpt / cpu / BothRev |
0.000011107980044471332 s |
0.000010761060020740842 s |
1.03 |
GenDot / IDefOpt / cpu / PreRev |
0.000011620680006672044 s |
0.000010950339974442614 s |
1.06 |
GenDot / IDefOpt / cpu / PostRev |
0.00001194121996377362 s |
0.00001149753998106462 s |
1.04 |
GenDot / IDefOpt / cpu / BothRev |
0.000011630720027824282 s |
0.000010877040003833827 s |
1.07 |
GenDot / JaXPipe / cuda / Primal |
0.000002496 s |
0.000002016 s |
1.24 |
GenDot / Jax / cuda / Primal |
0.000002496 s |
0.000002015 s |
1.24 |
GenDot / HLOOpt / cuda / Primal |
0.000002495 s |
0.000001984 s |
1.26 |
GenDot / PartOpt / cuda / Primal |
0.000002496 s |
0.000002016 s |
1.24 |
GenDot / IPartOpt / cuda / Primal |
0.000002527 s |
0.000002016 s |
1.25 |
GenDot / DefOpt / cuda / Primal |
0.000002495 s |
0.000002015 s |
1.24 |
GenDot / IDefOpt / cuda / Primal |
0.000002495 s |
0.000002015 s |
1.24 |
GenDot / JaXPipe / cuda / Forward |
0.000010496 s |
0.000009409 s |
1.12 |
GenDot / Jax / cuda / Forward |
0.000010624 s |
0.000009728 s |
1.09 |
GenDot / HLOOpt / cuda / Forward |
0.000010624 s |
0.000009696 s |
1.10 |
GenDot / PartOpt / cuda / Forward |
0.000010528 s |
0.000009792 s |
1.08 |
GenDot / IPartOpt / cuda / Forward |
0.000010624 s |
0.000009024 s |
1.18 |
GenDot / DefOpt / cuda / Forward |
0.00001056 s |
0.000009984 s |
1.06 |
GenDot / IDefOpt / cuda / Forward |
0.000010336 s |
0.000009855 s |
1.05 |
GenDot / JaXPipe / cuda / PreRev |
0.00001056 s |
0.000008703000000000001 s |
1.21 |
GenDot / JaXPipe / cuda / PostRev |
0.000010464 s |
0.000009856 s |
1.06 |
GenDot / JaXPipe / cuda / BothRev |
0.000010656 s |
0.000009536 s |
1.12 |
GenDot / Jax / cuda / BothRev |
0.000010656 s |
0.000009312000000000002 s |
1.14 |
GenDot / HLOOpt / cuda / PreRev |
0.000010752 s |
0.000009504 s |
1.13 |
GenDot / HLOOpt / cuda / PostRev |
0.000010528 s |
0.000014752 s |
0.71 |
GenDot / HLOOpt / cuda / BothRev |
0.000010816 s |
0.00001104 s |
0.98 |
GenDot / PartOpt / cuda / PreRev |
0.00001088 s |
0.000010912 s |
1.00 |
GenDot / PartOpt / cuda / PostRev |
0.000010592 s |
0.000011104 s |
0.95 |
GenDot / PartOpt / cuda / BothRev |
0.000010464 s |
0.000011104 s |
0.94 |
GenDot / IPartOpt / cuda / PreRev |
0.000010336 s |
0.000010784 s |
0.96 |
GenDot / IPartOpt / cuda / PostRev |
0.000010592 s |
0.000011072 s |
0.96 |
GenDot / IPartOpt / cuda / BothRev |
0.000010624 s |
0.00000992 s |
1.07 |
GenDot / DefOpt / cuda / PreRev |
0.000010688 s |
0.000009856 s |
1.08 |
GenDot / DefOpt / cuda / PostRev |
0.000010687 s |
0.000009568 s |
1.12 |
GenDot / DefOpt / cuda / BothRev |
0.000010592 s |
0.000009856 s |
1.07 |
GenDot / IDefOpt / cuda / PreRev |
0.000010496 s |
0.000009856 s |
1.06 |
GenDot / IDefOpt / cuda / PostRev |
0.000010624 s |
0.000009536 s |
1.11 |
GenDot / IDefOpt / cuda / BothRev |
0.00001056 s |
0.000009632 s |
1.10 |
GenDot / JaXPipe / tpu / Primal |
9.30175e-7 s |
9.29875e-7 s |
1.00 |
GenDot / Jax / tpu / Primal |
9.2525e-7 s |
9.2665e-7 s |
1.00 |
GenDot / HLOOpt / tpu / Primal |
0.000001571525 s |
0.00000158335 s |
0.99 |
GenDot / PartOpt / tpu / Primal |
9.261e-7 s |
9.2605e-7 s |
1.00 |
GenDot / IPartOpt / tpu / Primal |
9.30125e-7 s |
9.30725e-7 s |
1.00 |
GenDot / DefOpt / tpu / Primal |
0.0000014832999999999998 s |
0.0000015009749999999998 s |
0.99 |
GenDot / IDefOpt / tpu / Primal |
0.0000015776499999999998 s |
0.000001590625 s |
0.99 |
GenDot / JaXPipe / tpu / Forward |
0.00000316455 s |
0.00000317515 s |
1.00 |
GenDot / Jax / tpu / Forward |
0.00000232115 s |
0.00000233035 s |
1.00 |
GenDot / HLOOpt / tpu / Forward |
0.00000310585 s |
0.0000031335 s |
0.99 |
GenDot / PartOpt / tpu / Forward |
0.0000032151000000000004 s |
0.000003231625 s |
0.99 |
GenDot / IPartOpt / tpu / Forward |
0.0000031104500000000004 s |
0.0000031330000000000003 s |
0.99 |
GenDot / DefOpt / tpu / Forward |
0.00000321245 s |
0.0000032337 s |
0.99 |
GenDot / IDefOpt / tpu / Forward |
0.000003118575 s |
0.0000031358 s |
0.99 |
GenDot / JaXPipe / tpu / PreRev |
0.000002957375 s |
0.000002985475 s |
0.99 |
GenDot / JaXPipe / tpu / PostRev |
0.000002415725 s |
0.000002399875 s |
1.01 |
GenDot / JaXPipe / tpu / BothRev |
0.00000294695 s |
0.000002993825 s |
0.98 |
GenDot / Jax / tpu / BothRev |
0.000002412525 s |
0.00000239935 s |
1.01 |
GenDot / HLOOpt / tpu / PreRev |
0.00000295365 s |
0.0000029822 s |
0.99 |
GenDot / HLOOpt / tpu / PostRev |
0.0000029358250000000004 s |
0.0000029412 s |
1.00 |
GenDot / HLOOpt / tpu / BothRev |
0.0000029637750000000003 s |
0.000003004175 s |
0.99 |
GenDot / PartOpt / tpu / PreRev |
0.0000029361 s |
0.000002957425 s |
0.99 |
GenDot / PartOpt / tpu / PostRev |
0.0000023942 s |
0.000002396275 s |
1.00 |
GenDot / PartOpt / tpu / BothRev |
0.0000029226500000000003 s |
0.000002944225 s |
0.99 |
GenDot / IPartOpt / tpu / PreRev |
0.00000295645 s |
0.000002986025 s |
0.99 |
GenDot / IPartOpt / tpu / PostRev |
0.000002407825 s |
0.000002399275 s |
1.00 |
GenDot / IPartOpt / tpu / BothRev |
0.0000029629 s |
0.0000029928 s |
0.99 |
GenDot / DefOpt / tpu / PreRev |
0.000002928875 s |
0.00000293195 s |
1.00 |
GenDot / DefOpt / tpu / PostRev |
0.0000029557 s |
0.000002990275 s |
0.99 |
GenDot / DefOpt / tpu / BothRev |
0.000002927825 s |
0.00000293015 s |
1.00 |
GenDot / IDefOpt / tpu / PreRev |
0.0000029506 s |
0.000002993225 s |
0.99 |
GenDot / IDefOpt / tpu / PostRev |
0.0000029288 s |
0.000002935 s |
1.00 |
GenDot / IDefOpt / tpu / BothRev |
0.000002955075 s |
0.0000029784500000000003 s |
0.99 |
GenDot / JaXPipe / cpu / Primal |
0.000018780000000000003 s |
0.000007298380041902419 s |
2.57 |
GenDot / Jax / cpu / Primal |
0.000018568 s |
0.000007048700008454034 s |
2.63 |
GenDot / HLOOpt / cpu / Primal |
0.000017395999999999997 s |
0.00000794292001046415 s |
2.19 |
GenDot / PartOpt / cpu / Primal |
0.000018348 s |
0.000006769920055376133 s |
2.71 |
GenDot / IPartOpt / cpu / Primal |
0.00001866 s |
0.000007515740007875138 s |
2.48 |
GenDot / DefOpt / cpu / Primal |
0.000017811 s |
0.000007409619984173332 s |
2.40 |
GenDot / IDefOpt / cpu / Primal |
0.000017219000000000002 s |
0.000007622040011483477 s |
2.26 |
GenDot / JaXPipe / cpu / Forward |
0.000024197 s |
0.000011569240014068782 s |
2.09 |
GenDot / Jax / cpu / Forward |
0.00002535 s |
0.000009718079991216654 s |
2.61 |
GenDot / HLOOpt / cpu / Forward |
0.000023621 s |
0.000011745740011974704 s |
2.01 |
GenDot / PartOpt / cpu / Forward |
0.000023907 s |
0.000011508360021252884 s |
2.08 |
GenDot / IPartOpt / cpu / Forward |
0.000023977 s |
0.000011128580026706914 s |
2.15 |
GenDot / DefOpt / cpu / Forward |
0.000023875 s |
0.000010798399998748209 s |
2.21 |
GenDot / IDefOpt / cpu / Forward |
0.000024121 s |
0.00001077956000699487 s |
2.24 |
GenDot / JaXPipe / cpu / PreRev |
0.000024632 s |
0.000010790999995151652 s |
2.28 |
GenDot / JaXPipe / cpu / PostRev |
0.000025074 s |
0.000010381940037405 s |
2.42 |
GenDot / JaXPipe / cpu / BothRev |
0.000023867 s |
0.000011352839983373995 s |
2.10 |
GenDot / Jax / cpu / BothRev |
0.000025014 s |
0.000011042040014217492 s |
2.27 |
GenDot / HLOOpt / cpu / PreRev |
0.00002406 s |
0.000011735859989130403 s |
2.05 |
GenDot / HLOOpt / cpu / PostRev |
0.000025006 s |
0.000013340659997993496 s |
1.87 |
GenDot / HLOOpt / cpu / BothRev |
0.00002395 s |
0.000010679819979486638 s |
2.24 |
GenDot / PartOpt / cpu / PreRev |
0.000024535 s |
0.000010874159997911192 s |
2.26 |
GenDot / PartOpt / cpu / PostRev |
0.00002498 s |
0.000011166739977852555 s |
2.24 |
GenDot / PartOpt / cpu / BothRev |
0.000024243 s |
0.000011426359942561248 s |
2.12 |
GenDot / IPartOpt / cpu / PreRev |
0.000024087 s |
0.000010923079989879626 s |
2.21 |
GenDot / IPartOpt / cpu / PostRev |
0.00002538 s |
0.000010891519996221178 s |
2.33 |
GenDot / IPartOpt / cpu / BothRev |
0.000024242 s |
0.000011160020021634409 s |
2.17 |
GenDot / DefOpt / cpu / PreRev |
0.000024062 s |
0.000011140939977849483 s |
2.16 |
GenDot / DefOpt / cpu / PostRev |
0.000024387 s |
0.000011533419992701966 s |
2.11 |
GenDot / DefOpt / cpu / BothRev |
0.000024593 s |
0.000010761060020740842 s |
2.29 |
GenDot / IDefOpt / cpu / PreRev |
0.00002408 s |
0.000010950339974442614 s |
2.20 |
GenDot / IDefOpt / cpu / PostRev |
0.000024644 s |
0.00001149753998106462 s |
2.14 |
GenDot / IDefOpt / cpu / BothRev |
0.000024445 s |
0.000010877040003833827 s |
2.25 |
hlo_ffi / JaXPipe / cpu / Primal |
0.000010300519998054367 s |
0.000010284639974997845 s |
1.00 |
hlo_ffi / Jax / cpu / Primal |
0.000010605800007397192 s |
0.000009667560016168864 s |
1.10 |
hlo_ffi / HLOOpt / cpu / Primal |
0.000010277780011165306 s |
0.000010284979998687047 s |
1.00 |
hlo_ffi / PartOpt / cpu / Primal |
0.0000097367600119469 s |
0.00000951727997744456 s |
1.02 |
hlo_ffi / IPartOpt / cpu / Primal |
0.000010110559978784296 s |
0.000010334960024920293 s |
0.98 |
hlo_ffi / DefOpt / cpu / Primal |
0.000010027260004790151 s |
0.000010058319985546404 s |
1.00 |
hlo_ffi / IDefOpt / cpu / Primal |
0.000009868300021480535 s |
0.000009962120047930512 s |
0.99 |
hlo_ffi / JaXPipe / cpu / Forward |
0.000014289099981397158 s |
0.000014187380020302954 s |
1.01 |
hlo_ffi / Jax / cpu / Forward |
0.000014404420026039589 s |
0.000013873439984308789 s |
1.04 |
hlo_ffi / HLOOpt / cpu / Forward |
0.00001463523998609162 s |
0.00001400121997903625 s |
1.05 |
hlo_ffi / PartOpt / cpu / Forward |
0.000014507260029859026 s |
0.00001432539997040294 s |
1.01 |
hlo_ffi / IPartOpt / cpu / Forward |
0.000014647200068793608 s |
0.000014166840010148008 s |
1.03 |
hlo_ffi / DefOpt / cpu / Forward |
0.000014413099961529952 s |
0.000014209059972927207 s |
1.01 |
hlo_ffi / IDefOpt / cpu / Forward |
0.000014777579990550291 s |
0.000014338580022013049 s |
1.03 |
hlo_ffi / JaXPipe / cpu / PreRev |
0.00001507004002633039 s |
0.000014636240020990954 s |
1.03 |
hlo_ffi / JaXPipe / cpu / PostRev |
0.000014439260021390507 s |
0.000014110460006122592 s |
1.02 |
hlo_ffi / JaXPipe / cpu / BothRev |
0.000014131999996607192 s |
0.00001390391998029372 s |
1.02 |
hlo_ffi / Jax / cpu / BothRev |
0.00001473306000661978 s |
0.000014062179998290958 s |
1.05 |
hlo_ffi / HLOOpt / cpu / PreRev |
0.00001478114003475639 s |
0.000014028819978193496 s |
1.05 |
hlo_ffi / HLOOpt / cpu / PostRev |
0.000016831040011311415 s |
0.00001594318003299122 s |
1.06 |
hlo_ffi / HLOOpt / cpu / BothRev |
0.000014247620019887107 s |
0.000014413599992622038 s |
0.99 |
hlo_ffi / PartOpt / cpu / PreRev |
0.000014889680014675833 s |
0.00001416582001183997 s |
1.05 |
hlo_ffi / PartOpt / cpu / PostRev |
0.000014285999986896058 s |
0.00001393637999171915 s |
1.03 |
hlo_ffi / PartOpt / cpu / BothRev |
0.00001478552000662603 s |
0.0000143006199868978 s |
1.03 |
hlo_ffi / IPartOpt / cpu / PreRev |
0.00001464822000343702 s |
0.000013980779976918712 s |
1.05 |
hlo_ffi / IPartOpt / cpu / PostRev |
0.000014256760023272363 s |
0.000014213119957275922 s |
1.00 |
hlo_ffi / IPartOpt / cpu / BothRev |
0.000014587660007236992 s |
0.000014170980020935531 s |
1.03 |
hlo_ffi / DefOpt / cpu / PreRev |
0.000015153680014918792 s |
0.000014085239999985788 s |
1.08 |
hlo_ffi / DefOpt / cpu / PostRev |
0.000014386819957508124 s |
0.000014310660035334876 s |
1.01 |
hlo_ffi / DefOpt / cpu / BothRev |
0.00001439107999431144 s |
0.000013982019991090056 s |
1.03 |
hlo_ffi / IDefOpt / cpu / PreRev |
0.0000153047399908246 s |
0.000014316020051410303 s |
1.07 |
hlo_ffi / IDefOpt / cpu / PostRev |
0.000014281279982242268 s |
0.000014057119979042908 s |
1.02 |
hlo_ffi / IDefOpt / cpu / BothRev |
0.000014564420007445732 s |
0.000014209260025381808 s |
1.02 |
hlo_ffi / JaXPipe / cuda / Primal |
0.000002336 s |
0.000001983 s |
1.18 |
hlo_ffi / Jax / cuda / Primal |
0.000002336 s |
0.000001983 s |
1.18 |
hlo_ffi / HLOOpt / cuda / Primal |
0.000002335 s |
0.000001984 s |
1.18 |
hlo_ffi / PartOpt / cuda / Primal |
0.000002336 s |
0.000001983 s |
1.18 |
hlo_ffi / IPartOpt / cuda / Primal |
0.000002336 s |
0.000001984 s |
1.18 |
hlo_ffi / DefOpt / cuda / Primal |
0.000002336 s |
0.000001983 s |
1.18 |
hlo_ffi / IDefOpt / cuda / Primal |
0.000002336 s |
0.000001983 s |
1.18 |
hlo_ffi / JaXPipe / cuda / Forward |
0.000002431 s |
0.000002049 s |
1.19 |
hlo_ffi / Jax / cuda / Forward |
0.000002431 s |
0.00000208 s |
1.17 |
hlo_ffi / HLOOpt / cuda / Forward |
0.000002431 s |
0.00000208 s |
1.17 |
hlo_ffi / PartOpt / cuda / Forward |
0.000002432 s |
0.000002048 s |
1.19 |
hlo_ffi / IPartOpt / cuda / Forward |
0.000002431 s |
0.00000208 s |
1.17 |
hlo_ffi / DefOpt / cuda / Forward |
0.000002431 s |
0.00000208 s |
1.17 |
hlo_ffi / IDefOpt / cuda / Forward |
0.000002431 s |
0.000002048 s |
1.19 |
hlo_ffi / JaXPipe / cuda / PreRev |
0.0000024 s |
0.000002047 s |
1.17 |
hlo_ffi / JaXPipe / cuda / PostRev |
0.000002431 s |
0.000002048 s |
1.19 |
hlo_ffi / JaXPipe / cuda / BothRev |
0.000002431 s |
0.000002048 s |
1.19 |
hlo_ffi / Jax / cuda / BothRev |
0.0000024 s |
0.000002048 s |
1.17 |
hlo_ffi / HLOOpt / cuda / PreRev |
0.0000024 s |
0.000002048 s |
1.17 |
hlo_ffi / HLOOpt / cuda / PostRev |
0.000002431 s |
0.000002048 s |
1.19 |
hlo_ffi / HLOOpt / cuda / BothRev |
0.0000024 s |
0.000002047 s |
1.17 |
hlo_ffi / PartOpt / cuda / PreRev |
0.0000024 s |
0.000002048 s |
1.17 |
hlo_ffi / PartOpt / cuda / PostRev |
0.0000024 s |
0.000002048 s |
1.17 |
hlo_ffi / PartOpt / cuda / BothRev |
0.000002431 s |
0.000002047 s |
1.19 |
hlo_ffi / IPartOpt / cuda / PreRev |
0.000002431 s |
0.000002047 s |
1.19 |
hlo_ffi / IPartOpt / cuda / PostRev |
0.0000024 s |
0.000002048 s |
1.17 |
hlo_ffi / IPartOpt / cuda / BothRev |
0.000002431 s |
0.000002047 s |
1.19 |
hlo_ffi / DefOpt / cuda / PreRev |
0.0000024 s |
0.000002047 s |
1.17 |
hlo_ffi / DefOpt / cuda / PostRev |
0.000002399 s |
0.000002048 s |
1.17 |
hlo_ffi / DefOpt / cuda / BothRev |
0.000002431 s |
0.000002047 s |
1.19 |
hlo_ffi / IDefOpt / cuda / PreRev |
0.0000024 s |
0.000002048 s |
1.17 |
hlo_ffi / IDefOpt / cuda / PostRev |
0.0000024 s |
0.000002048 s |
1.17 |
hlo_ffi / IDefOpt / cuda / BothRev |
0.0000024 s |
0.000002047 s |
1.17 |
hlo_ffi / JaXPipe / tpu / Primal |
9.27275e-7 s |
9.186e-7 s |
1.01 |
hlo_ffi / Jax / tpu / Primal |
9.519e-7 s |
9.53225e-7 s |
1.00 |
hlo_ffi / HLOOpt / tpu / Primal |
9.074e-7 s |
8.98e-7 s |
1.01 |
hlo_ffi / PartOpt / tpu / Primal |
9.55275e-7 s |
9.543e-7 s |
1.00 |
hlo_ffi / IPartOpt / tpu / Primal |
9.19475e-7 s |
8.99475e-7 s |
1.02 |
hlo_ffi / DefOpt / tpu / Primal |
9.5195e-7 s |
9.518e-7 s |
1.00 |
hlo_ffi / IDefOpt / tpu / Primal |
9.0965e-7 s |
8.9985e-7 s |
1.01 |
hlo_ffi / JaXPipe / tpu / Forward |
9.49775e-7 s |
9.4875e-7 s |
1.00 |
hlo_ffi / Jax / tpu / Forward |
9.81225e-7 s |
9.810750000000002e-7 s |
1.00 |
hlo_ffi / HLOOpt / tpu / Forward |
9.74325e-7 s |
9.737250000000002e-7 s |
1.00 |
hlo_ffi / PartOpt / tpu / Forward |
9.3465e-7 s |
9.3345e-7 s |
1.00 |
hlo_ffi / IPartOpt / tpu / Forward |
9.74925e-7 s |
9.7375e-7 s |
1.00 |
hlo_ffi / DefOpt / tpu / Forward |
9.34775e-7 s |
9.33125e-7 s |
1.00 |
hlo_ffi / IDefOpt / tpu / Forward |
9.75e-7 s |
9.739e-7 s |
1.00 |
hlo_ffi / JaXPipe / tpu / PreRev |
9.38325e-7 s |
9.315e-7 s |
1.01 |
hlo_ffi / JaXPipe / tpu / PostRev |
9.65875e-7 s |
9.64925e-7 s |
1.00 |
hlo_ffi / JaXPipe / tpu / BothRev |
9.6265e-7 s |
9.62e-7 s |
1.00 |
hlo_ffi / Jax / tpu / BothRev |
9.654e-7 s |
9.64325e-7 s |
1.00 |
hlo_ffi / HLOOpt / tpu / PreRev |
9.626e-7 s |
9.62075e-7 s |
1.00 |
hlo_ffi / HLOOpt / tpu / PostRev |
9.65125e-7 s |
9.6465e-7 s |
1.00 |
hlo_ffi / HLOOpt / tpu / BothRev |
9.63225e-7 s |
9.6245e-7 s |
1.00 |
hlo_ffi / PartOpt / tpu / PreRev |
9.65575e-7 s |
9.64725e-7 s |
1.00 |
hlo_ffi / PartOpt / tpu / PostRev |
9.628499999999998e-7 s |
9.616e-7 s |
1.00 |
hlo_ffi / PartOpt / tpu / BothRev |
9.65275e-7 s |
9.6475e-7 s |
1.00 |
hlo_ffi / IPartOpt / tpu / PreRev |
9.62775e-7 s |
9.62225e-7 s |
1.00 |
hlo_ffi / IPartOpt / tpu / PostRev |
9.6545e-7 s |
9.649e-7 s |
1.00 |
hlo_ffi / IPartOpt / tpu / BothRev |
9.62425e-7 s |
9.6195e-7 s |
1.00 |
hlo_ffi / DefOpt / tpu / PreRev |
9.652e-7 s |
9.648e-7 s |
1.00 |
hlo_ffi / DefOpt / tpu / PostRev |
9.628499999999998e-7 s |
9.618500000000002e-7 s |
1.00 |
hlo_ffi / DefOpt / tpu / BothRev |
9.655e-7 s |
9.644e-7 s |
1.00 |
hlo_ffi / IDefOpt / tpu / PreRev |
9.625749999999998e-7 s |
9.617e-7 s |
1.00 |
hlo_ffi / IDefOpt / tpu / PostRev |
9.65575e-7 s |
9.64525e-7 s |
1.00 |
hlo_ffi / IDefOpt / tpu / BothRev |
9.62e-7 s |
9.61725e-7 s |
1.00 |
hlo_ffi / JaXPipe / cpu / Primal |
0.000021912 s |
0.000010284639974997845 s |
2.13 |
hlo_ffi / Jax / cpu / Primal |
0.000021297 s |
0.000009667560016168864 s |
2.20 |
hlo_ffi / HLOOpt / cpu / Primal |
0.000021895 s |
0.000010284979998687047 s |
2.13 |
hlo_ffi / PartOpt / cpu / Primal |
0.000021773 s |
0.00000951727997744456 s |
2.29 |
hlo_ffi / IPartOpt / cpu / Primal |
0.000021533 s |
0.000010334960024920293 s |
2.08 |
hlo_ffi / DefOpt / cpu / Primal |
0.000021824 s |
0.000010058319985546404 s |
2.17 |
hlo_ffi / IDefOpt / cpu / Primal |
0.00002156 s |
0.000009962120047930512 s |
2.16 |
hlo_ffi / JaXPipe / cpu / Forward |
0.000029767 s |
0.000014187380020302954 s |
2.10 |
hlo_ffi / Jax / cpu / Forward |
0.000028821 s |
0.000013873439984308789 s |
2.08 |
hlo_ffi / HLOOpt / cpu / Forward |
0.000029477 s |
0.00001400121997903625 s |
2.11 |
hlo_ffi / PartOpt / cpu / Forward |
0.000029477 s |
0.00001432539997040294 s |
2.06 |
hlo_ffi / IPartOpt / cpu / Forward |
0.000051235 s |
0.000014166840010148008 s |
3.62 |
hlo_ffi / DefOpt / cpu / Forward |
0.000029381 s |
0.000014209059972927207 s |
2.07 |
hlo_ffi / IDefOpt / cpu / Forward |
0.000029461 s |
0.000014338580022013049 s |
2.05 |
hlo_ffi / JaXPipe / cpu / PreRev |
0.000029691 s |
0.000014636240020990954 s |
2.03 |
hlo_ffi / JaXPipe / cpu / PostRev |
0.000029516 s |
0.000014110460006122592 s |
2.09 |
hlo_ffi / JaXPipe / cpu / BothRev |
0.000029423000000000003 s |
0.00001390391998029372 s |
2.12 |
hlo_ffi / Jax / cpu / BothRev |
0.000029443 s |
0.000014062179998290958 s |
2.09 |
hlo_ffi / HLOOpt / cpu / PreRev |
0.000029658 s |
0.000014028819978193496 s |
2.11 |
hlo_ffi / HLOOpt / cpu / PostRev |
0.000029211 s |
0.00001594318003299122 s |
1.83 |
hlo_ffi / HLOOpt / cpu / BothRev |
0.000029152 s |
0.000014413599992622038 s |
2.02 |
hlo_ffi / PartOpt / cpu / PreRev |
0.000030429 s |
0.00001416582001183997 s |
2.15 |
hlo_ffi / PartOpt / cpu / PostRev |
0.000029354 s |
0.00001393637999171915 s |
2.11 |
hlo_ffi / PartOpt / cpu / BothRev |
0.000029272 s |
0.0000143006199868978 s |
2.05 |
hlo_ffi / IPartOpt / cpu / PreRev |
0.000029437000000000003 s |
0.000013980779976918712 s |
2.11 |
hlo_ffi / IPartOpt / cpu / PostRev |
0.000029139 s |
0.000014213119957275922 s |
2.05 |
hlo_ffi / IPartOpt / cpu / BothRev |
0.000029071 s |
0.000014170980020935531 s |
2.05 |
hlo_ffi / DefOpt / cpu / PreRev |
0.000028776 s |
0.000014085239999985788 s |
2.04 |
hlo_ffi / DefOpt / cpu / PostRev |
0.000028943 s |
0.000014310660035334876 s |
2.02 |
hlo_ffi / DefOpt / cpu / BothRev |
0.000029463 s |
0.000013982019991090056 s |
2.11 |
hlo_ffi / IDefOpt / cpu / PreRev |
0.000029611 s |
0.000014316020051410303 s |
2.07 |
hlo_ffi / IDefOpt / cpu / PostRev |
0.000028978 s |
0.000014057119979042908 s |
2.06 |
hlo_ffi / IDefOpt / cpu / BothRev |
0.000028856 s |
0.000014209260025381808 s |
2.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / Primal |
0.0010039214000244 s |
0.0009100650000618 s |
1.10 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / cpu / Primal |
0.0009614745999897 s |
0.0009172600000056 s |
1.05 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / Primal |
0.0010102142000505 s |
0.0010144106002371 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / Primal |
0.000998028199956 s |
0.0008878655999069 s |
1.12 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / Primal |
0.0009538141998746 s |
0.0009339372000795 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / Primal |
0.0009959525999875 s |
0.0009609147998162 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / Primal |
0.0010155622000638 s |
0.0009962112000721 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / Forward |
0.0023812780001208 s |
0.0022266109999691 s |
1.07 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / cpu / Forward |
0.0024514062001799 s |
0.0023936325999784 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / Forward |
0.002346252999996 s |
0.0021506333998331 s |
1.09 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / Forward |
0.0023489485999562 s |
0.0023729827998067 s |
0.99 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / Forward |
0.0023375856000711 s |
0.0022126754000964 s |
1.06 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / Forward |
0.0023471927999707 s |
0.0022777125999709 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / Forward |
0.0023751313999127 s |
0.0021534280000196 s |
1.10 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / PreRev |
0.00564026739994 s |
0.0053284488000826 s |
1.06 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / PostRev |
0.0062279716000375 s |
0.0056835981999938 s |
1.10 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / BothRev |
0.0068182679999154 s |
0.0052150422000522 s |
1.31 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / cpu / BothRev |
0.0073328499999661 s |
0.0060669299999062 s |
1.21 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / PreRev |
0.0058033710000927 s |
0.0037044362001324 s |
1.57 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / PostRev |
0.0060785982000197 s |
0.0064265009998962 s |
0.95 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / BothRev |
0.0058111185998313 s |
0.0037709973999881 s |
1.54 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / PreRev |
0.0059775396000986 s |
0.0061171409999587 s |
0.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / PostRev |
0.0059417072001451 s |
0.003930622000098 s |
1.51 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / BothRev |
0.0065524416000698 s |
0.0062224390000665 s |
1.05 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / PreRev |
0.0055133678000856 s |
0.0037930405999759 s |
1.45 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / PostRev |
0.0060521013999277 s |
0.0063594317998649 s |
0.95 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / BothRev |
0.0063977804000387 s |
0.0037310412000806 s |
1.71 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / PreRev |
0.0061178789999758 s |
0.0063060106000193 s |
0.97 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / PostRev |
0.0049902105999535 s |
0.0037435317999552 s |
1.33 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / BothRev |
0.0054361225999855 s |
0.006533680999928 s |
0.83 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / PreRev |
0.0055036247999851 s |
0.0037383431999842 s |
1.47 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / PostRev |
0.0055093387998567 s |
0.0064990833999218 s |
0.85 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / BothRev |
0.005504897999981 s |
0.0041281814000285 s |
1.33 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cuda / Primal |
0.00029491 s |
0.000280289 s |
1.05 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / cuda / Primal |
0.000295199 s |
0.000279648 s |
1.06 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cuda / Primal |
0.000301438 s |
0.000287072 s |
1.05 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cuda / Primal |
0.000294335 s |
0.000278816 s |
1.06 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cuda / Primal |
0.000294719 s |
0.000279456 s |
1.05 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cuda / Primal |
0.000302719 s |
0.0002867199999999 s |
1.06 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cuda / Primal |
0.000301823 s |
0.000287648 s |
1.05 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cuda / Forward |
0.0005823009999999 s |
0.0005568 s |
1.05 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / cuda / Forward |
0.000567806 s |
0.000538881 s |
1.05 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cuda / Forward |
0.0005823009999999 s |
0.000557632 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cuda / Forward |
0.000582493 s |
0.000557569 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cuda / Forward |
0.0005827489999999 s |
0.00055776 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cuda / Forward |
0.00058275 s |
0.000557344 s |
1.05 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cuda / Forward |
0.000582654 s |
0.000558176 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cuda / PreRev |
0.001055772 s |
0.0010261119999999 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cuda / PostRev |
0.001011708 s |
0.00098528 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cuda / BothRev |
0.001050588 s |
0.001025441 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / cuda / BothRev |
0.00100358 s |
0.00098752 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cuda / PreRev |
0.001036988 s |
0.001013985 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cuda / PostRev |
0.001059932 s |
0.001037569 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cuda / BothRev |
0.001036828 s |
0.001011681 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cuda / PreRev |
0.0010510679999999 s |
0.001027937 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cuda / PostRev |
0.000999292 s |
0.000975713 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cuda / BothRev |
0.0010524759999999 s |
0.001026113 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cuda / PreRev |
0.001051323 s |
0.001026017 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cuda / PostRev |
0.000999612 s |
0.000974785 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cuda / BothRev |
0.0010527 s |
0.001026593 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cuda / PreRev |
0.001052444 s |
0.001022561 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cuda / PostRev |
0.000986972 s |
0.000960865 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cuda / BothRev |
0.001052444 s |
0.001022273 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cuda / PreRev |
0.0010527 s |
0.0010197449999999 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cuda / PostRev |
0.0010538829999999 s |
0.001020033 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cuda / BothRev |
0.001053116 s |
0.001020737 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / tpu / Primal |
0.00012902825 s |
0.00012457525 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / tpu / Primal |
0.000123856 s |
0.000126331 s |
0.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / tpu / Primal |
0.0001572454999999 s |
0.00015273475 s |
1.03 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / tpu / Primal |
0.0001311532499999 s |
0.00013435025 s |
0.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / tpu / Primal |
0.00013611 s |
0.00013136425 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / tpu / Primal |
0.0001448299999999 s |
0.000147822 s |
0.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / tpu / Primal |
0.000156234 s |
0.0001507285 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / tpu / Forward |
0.0002137427499999 s |
0.00021200975 s |
1.01 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / tpu / Forward |
0.00026156525 s |
0.00026122475 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / tpu / Forward |
0.0002200979999999 s |
0.0002122135 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / tpu / Forward |
0.0002134945 s |
0.00021845075 s |
0.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / tpu / Forward |
0.0002163495 s |
0.000212008 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / tpu / Forward |
0.0002181427499999 s |
0.0002185624999999 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / tpu / Forward |
0.000216343 s |
0.00021246625 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / tpu / PreRev |
0.00035519525 s |
0.00035407075 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / tpu / PostRev |
0.000256345 s |
0.0002561415 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / tpu / BothRev |
0.000356134 s |
0.00035483825 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / tpu / BothRev |
0.000257403 s |
0.0002573317499999 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / tpu / PreRev |
0.00035591675 s |
0.00035495725 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / tpu / PostRev |
0.0002921275 s |
0.000291605 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / tpu / BothRev |
0.0003558854999999 s |
0.0003548719999999 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / tpu / PreRev |
0.0003564505 s |
0.00035591275 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / tpu / PostRev |
0.00027174825 s |
0.0002716535 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / tpu / BothRev |
0.0003562185 s |
0.0003560215 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / tpu / PreRev |
0.000356099 s |
0.0003549675 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / tpu / PostRev |
0.000272676 s |
0.00027230025 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / tpu / BothRev |
0.0003562935 s |
0.00035493875 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / tpu / PreRev |
0.0003590067499999 s |
0.0003586415 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / tpu / PostRev |
0.00028354525 s |
0.00028358525 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / tpu / BothRev |
0.0003587524999999 s |
0.0003578824999999 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / tpu / PreRev |
0.0003580875 s |
0.00035715925 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / tpu / PostRev |
0.0003016697499999 s |
0.00030180325 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / tpu / BothRev |
0.00035880775 s |
0.0003571105 s |
1.00 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / Primal |
0.002625761 s |
0.0009100650000618 s |
2.89 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / cpu / Primal |
0.002773359 s |
0.0009172600000056 s |
3.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / Primal |
0.002904247 s |
0.0010144106002371 s |
2.86 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / Primal |
0.00256553 s |
0.0008878655999069 s |
2.89 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / Primal |
0.002778128 s |
0.0009339372000795 s |
2.97 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / Primal |
0.002636032 s |
0.0009609147998162 s |
2.74 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / Primal |
0.002799902 s |
0.0009962112000721 s |
2.81 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / Forward |
0.006817701 s |
0.0022266109999691 s |
3.06 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / cpu / Forward |
0.0064618149999999 s |
0.0023936325999784 s |
2.70 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / Forward |
0.006902682 s |
0.0021506333998331 s |
3.21 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / Forward |
0.006539366 s |
0.0023729827998067 s |
2.76 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / Forward |
0.007164774 s |
0.0022126754000964 s |
3.24 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / Forward |
0.007001921 s |
0.0022777125999709 s |
3.07 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / Forward |
0.006407242 s |
0.0021534280000196 s |
2.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / PreRev |
0.011527896 s |
0.0053284488000826 s |
2.16 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / PostRev |
0.00996614 s |
0.0056835981999938 s |
1.75 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / BothRev |
0.010669916 s |
0.0052150422000522 s |
2.05 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / cpu / BothRev |
0.010400828 s |
0.0060669299999062 s |
1.71 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / PreRev |
0.009659235 s |
0.0037044362001324 s |
2.61 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / PostRev |
0.010672925 s |
0.0064265009998962 s |
1.66 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / BothRev |
0.00973761 s |
0.0037709973999881 s |
2.58 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / PreRev |
0.00932807 s |
0.0061171409999587 s |
1.52 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / PostRev |
0.0097632049999999 s |
0.003930622000098 s |
2.48 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / BothRev |
0.010051062 s |
0.0062224390000665 s |
1.62 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / PreRev |
0.009343837 s |
0.0037930405999759 s |
2.46 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / PostRev |
0.010767216 s |
0.0063594317998649 s |
1.69 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / BothRev |
0.009076604 s |
0.0037310412000806 s |
2.43 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / PreRev |
0.009829074 s |
0.0063060106000193 s |
1.56 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / PostRev |
0.008634329 s |
0.0037435317999552 s |
2.31 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / BothRev |
0.01011538 s |
0.006533680999928 s |
1.55 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / PreRev |
0.009421947 s |
0.0037383431999842 s |
2.52 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / PostRev |
0.009242628 s |
0.0064990833999218 s |
1.42 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / BothRev |
0.010162697 s |
0.0041281814000285 s |
2.46 |
scatter_sum / JaXPipe / cpu / Primal |
0.00000891479998244904 s |
0.000008388459973502904 s |
1.06 |
scatter_sum / Jax / cpu / Primal |
0.000008681560029799584 s |
0.000007979300016813795 s |
1.09 |
scatter_sum / HLOOpt / cpu / Primal |
0.000008318920044985134 s |
0.000008007539981917944 s |
1.04 |
scatter_sum / PartOpt / cpu / Primal |
0.000007885479981268872 s |
0.000008130419992085081 s |
0.97 |
scatter_sum / IPartOpt / cpu / Primal |
0.000008869099983712659 s |
0.000007912760020190035 s |
1.12 |
scatter_sum / DefOpt / cpu / Primal |
0.000007743220076008583 s |
0.000008083239990810397 s |
0.96 |
scatter_sum / IDefOpt / cpu / Primal |
0.000008080520001385593 s |
0.000007748680000077002 s |
1.04 |
scatter_sum / JaXPipe / cpu / Forward |
0.00001307714001086424 s |
0.000011205040054846904 s |
1.17 |
scatter_sum / Jax / cpu / Forward |
0.000013185999996494502 s |
0.000011392160013201649 s |
1.16 |
scatter_sum / HLOOpt / cpu / Forward |
0.00001344131996120268 s |
0.000012204599997858169 s |
1.10 |
scatter_sum / PartOpt / cpu / Forward |
0.00001287555996896117 s |
0.00001159305999863136 s |
1.11 |
scatter_sum / IPartOpt / cpu / Forward |
0.000012895499967271462 s |
0.000012415900000632972 s |
1.04 |
scatter_sum / DefOpt / cpu / Forward |
0.00001320730000770709 s |
0.000011770320006689872 s |
1.12 |
scatter_sum / IDefOpt / cpu / Forward |
0.000013759560006292305 s |
0.000012068499972883727 s |
1.14 |
scatter_sum / JaXPipe / cpu / PreRev |
0.000012424539963831194 s |
0.000011716140024873311 s |
1.06 |
scatter_sum / JaXPipe / cpu / PostRev |
0.000012827079990529457 s |
0.000011641600021903288 s |
1.10 |
scatter_sum / JaXPipe / cpu / BothRev |
0.00001327384000433085 s |
0.000011614340000960513 s |
1.14 |
scatter_sum / Jax / cpu / BothRev |
0.000012478819962780108 s |
0.000012184240022179438 s |
1.02 |
scatter_sum / HLOOpt / cpu / PreRev |
0.00001311911996708659 s |
0.000013060520022918356 s |
1.00 |
scatter_sum / HLOOpt / cpu / PostRev |
0.000015047379993120556 s |
0.00001368204001664708 s |
1.10 |
scatter_sum / HLOOpt / cpu / BothRev |
0.000012374719999570515 s |
0.000011856519995490089 s |
1.04 |
scatter_sum / PartOpt / cpu / PreRev |
0.000012537739967228846 s |
0.000011116820005554472 s |
1.13 |
scatter_sum / PartOpt / cpu / PostRev |
0.000012782399981006163 s |
0.00001186079993203748 s |
1.08 |
scatter_sum / PartOpt / cpu / BothRev |
0.000013314620009623468 s |
0.000012269600038052886 s |
1.09 |
scatter_sum / IPartOpt / cpu / PreRev |
0.00001272332004191412 s |
0.000011251180003455376 s |
1.13 |
scatter_sum / IPartOpt / cpu / PostRev |
0.0000127420800163236 s |
0.000011199540022062138 s |
1.14 |
scatter_sum / IPartOpt / cpu / BothRev |
0.00001244659999429132 s |
0.000011617919954005627 s |
1.07 |
scatter_sum / DefOpt / cpu / PreRev |
0.00001303895995079074 s |
0.000011557839989109198 s |
1.13 |
scatter_sum / DefOpt / cpu / PostRev |
0.000012511300074038443 s |
0.000011769799975809292 s |
1.06 |
scatter_sum / DefOpt / cpu / BothRev |
0.00001265794002392795 s |
0.00001178735999019409 s |
1.07 |
scatter_sum / IDefOpt / cpu / PreRev |
0.000012090279988115073 s |
0.000012042659973303673 s |
1.00 |
scatter_sum / IDefOpt / cpu / PostRev |
0.000012204719960209331 s |
0.000011558019987205625 s |
1.06 |
scatter_sum / IDefOpt / cpu / BothRev |
0.00001252989997738041 s |
0.00001182768003673118 s |
1.06 |
scatter_sum / JaXPipe / cuda / Primal |
0.000010464 s |
0.000009344 s |
1.12 |
scatter_sum / Jax / cuda / Primal |
0.000010624 s |
0.000009472 s |
1.12 |
scatter_sum / HLOOpt / cuda / Primal |
0.000010431 s |
0.0000096 s |
1.09 |
scatter_sum / PartOpt / cuda / Primal |
0.000010496 s |
0.000009727 s |
1.08 |
scatter_sum / IPartOpt / cuda / Primal |
0.000010687 s |
0.000010175 s |
1.05 |
scatter_sum / DefOpt / cuda / Primal |
0.000010719 s |
0.000009952 s |
1.08 |
scatter_sum / IDefOpt / cuda / Primal |
0.000010911 s |
0.000009375 s |
1.16 |
scatter_sum / JaXPipe / cuda / Forward |
0.000016927000000000002 s |
0.000016575 s |
1.02 |
scatter_sum / Jax / cuda / Forward |
0.000017216 s |
0.0000168 s |
1.02 |
scatter_sum / HLOOpt / cuda / Forward |
0.000017216 s |
0.000016864 s |
1.02 |
scatter_sum / PartOpt / cuda / Forward |
0.000017056 s |
0.000017088 s |
1.00 |
scatter_sum / IPartOpt / cuda / Forward |
0.000018048 s |
0.000016736 s |
1.08 |
scatter_sum / DefOpt / cuda / Forward |
0.000017344 s |
0.000016735 s |
1.04 |
scatter_sum / IDefOpt / cuda / Forward |
0.000017344 s |
0.000016864 s |
1.03 |
scatter_sum / JaXPipe / cuda / PreRev |
0.00001808 s |
0.000016544 s |
1.09 |
scatter_sum / JaXPipe / cuda / PostRev |
0.00001712 s |
0.0000168 s |
1.02 |
scatter_sum / JaXPipe / cuda / BothRev |
0.000017184 s |
0.000016832 s |
1.02 |
scatter_sum / Jax / cuda / BothRev |
0.000017823 s |
0.000016672 s |
1.07 |
scatter_sum / HLOOpt / cuda / PreRev |
0.000017152 s |
0.000017216 s |
1.00 |
scatter_sum / HLOOpt / cuda / PostRev |
0.000016768000000000003 s |
0.000016672 s |
1.01 |
scatter_sum / HLOOpt / cuda / BothRev |
0.000016704 s |
0.000016096 s |
1.04 |
scatter_sum / PartOpt / cuda / PreRev |
0.000017344 s |
0.000017024 s |
1.02 |
scatter_sum / PartOpt / cuda / PostRev |
0.000016864 s |
0.000016255999999999998 s |
1.04 |
scatter_sum / PartOpt / cuda / BothRev |
0.000016895 s |
0.000016992 s |
0.99 |
scatter_sum / IPartOpt / cuda / PreRev |
0.000017152 s |
0.000017024 s |
1.01 |
scatter_sum / IPartOpt / cuda / PostRev |
0.000016927999999999998 s |
0.000016063999999999997 s |
1.05 |
scatter_sum / IPartOpt / cuda / BothRev |
0.000017344 s |
0.000016255999999999998 s |
1.07 |
scatter_sum / DefOpt / cuda / PreRev |
0.000017056 s |
0.000016864 s |
1.01 |
scatter_sum / DefOpt / cuda / PostRev |
0.000017023 s |
0.000016224 s |
1.05 |
scatter_sum / DefOpt / cuda / BothRev |
0.000017216 s |
0.000016992 s |
1.01 |
scatter_sum / IDefOpt / cuda / PreRev |
0.000016512 s |
0.00001712 s |
0.96 |
scatter_sum / IDefOpt / cuda / PostRev |
0.000017087 s |
0.000016736 s |
1.02 |
scatter_sum / IDefOpt / cuda / BothRev |
0.000017056 s |
0.000016768000000000003 s |
1.02 |
scatter_sum / JaXPipe / tpu / Primal |
0.000001350375 s |
0.00000134455 s |
1.00 |
scatter_sum / Jax / tpu / Primal |
0.0000014045750000000002 s |
0.0000014054 s |
1.00 |
scatter_sum / HLOOpt / tpu / Primal |
0.000001350675 s |
0.000001344475 s |
1.00 |
scatter_sum / PartOpt / tpu / Primal |
0.0000014045 s |
0.0000014051749999999998 s |
1.00 |
scatter_sum / IPartOpt / tpu / Primal |
0.00000135025 s |
0.000001343975 s |
1.00 |
scatter_sum / DefOpt / tpu / Primal |
0.000001404225 s |
0.0000014051 s |
1.00 |
scatter_sum / IDefOpt / tpu / Primal |
0.0000013498 s |
0.00000134455 s |
1.00 |
scatter_sum / JaXPipe / tpu / Forward |
0.00000270605 s |
0.0000027043 s |
1.00 |
scatter_sum / Jax / tpu / Forward |
0.000002726925 s |
0.0000027198 s |
1.00 |
scatter_sum / HLOOpt / tpu / Forward |
0.000002704975 s |
0.000002700425 s |
1.00 |
scatter_sum / PartOpt / tpu / Forward |
0.00000269205 s |
0.000002684225 s |
1.00 |
scatter_sum / IPartOpt / tpu / Forward |
0.000002711975 s |
0.000002698875 s |
1.00 |
scatter_sum / DefOpt / tpu / Forward |
0.0000026949 s |
0.0000026813 s |
1.01 |
scatter_sum / IDefOpt / tpu / Forward |
0.0000027153 s |
0.000002702775 s |
1.00 |
scatter_sum / JaXPipe / tpu / PreRev |
0.000002686125 s |
0.000002679125 s |
1.00 |
scatter_sum / JaXPipe / tpu / PostRev |
0.0000026841 s |
0.00000268105 s |
1.00 |
scatter_sum / JaXPipe / tpu / BothRev |
0.000002708375 s |
0.00000270165 s |
1.00 |
scatter_sum / Jax / tpu / BothRev |
0.0000027438249999999995 s |
0.000002743075 s |
1.00 |
scatter_sum / HLOOpt / tpu / PreRev |
0.0000027030749999999995 s |
0.000002693675 s |
1.00 |
scatter_sum / HLOOpt / tpu / PostRev |
0.0000027426250000000003 s |
0.0000027449 s |
1.00 |
scatter_sum / HLOOpt / tpu / BothRev |
0.000002703675 s |
0.00000270395 s |
1.00 |
scatter_sum / PartOpt / tpu / PreRev |
0.000002751425 s |
0.0000027547 s |
1.00 |
scatter_sum / PartOpt / tpu / PostRev |
0.000002704425 s |
0.000002690425 s |
1.01 |
scatter_sum / PartOpt / tpu / BothRev |
0.000002741725 s |
0.0000027442 s |
1.00 |
scatter_sum / IPartOpt / tpu / PreRev |
0.0000027050000000000004 s |
0.000002699325 s |
1.00 |
scatter_sum / IPartOpt / tpu / PostRev |
0.000002745 s |
0.0000027351249999999995 s |
1.00 |
scatter_sum / IPartOpt / tpu / BothRev |
0.0000027031 s |
0.0000027066 s |
1.00 |
scatter_sum / DefOpt / tpu / PreRev |
0.0000027501750000000003 s |
0.0000027368500000000003 s |
1.00 |
scatter_sum / DefOpt / tpu / PostRev |
0.00000270405 s |
0.000002691025 s |
1.00 |
scatter_sum / DefOpt / tpu / BothRev |
0.000002743625 s |
0.00000274225 s |
1.00 |
scatter_sum / IDefOpt / tpu / PreRev |
0.0000027037 s |
0.000002698475 s |
1.00 |
scatter_sum / IDefOpt / tpu / PostRev |
0.000002742 s |
0.0000027346 s |
1.00 |
scatter_sum / IDefOpt / tpu / BothRev |
0.000002708125 s |
0.0000027007 s |
1.00 |
scatter_sum / JaXPipe / cpu / Primal |
0.000019616 s |
0.000008388459973502904 s |
2.34 |
scatter_sum / Jax / cpu / Primal |
0.000019654 s |
0.000007979300016813795 s |
2.46 |
scatter_sum / HLOOpt / cpu / Primal |
0.000019547 s |
0.000008007539981917944 s |
2.44 |
scatter_sum / PartOpt / cpu / Primal |
0.000019908 s |
0.000008130419992085081 s |
2.45 |
scatter_sum / IPartOpt / cpu / Primal |
0.000019405 s |
0.000007912760020190035 s |
2.45 |
scatter_sum / DefOpt / cpu / Primal |
0.000019763 s |
0.000008083239990810397 s |
2.44 |
scatter_sum / IDefOpt / cpu / Primal |
0.00001952 s |
0.000007748680000077002 s |
2.52 |
scatter_sum / JaXPipe / cpu / Forward |
0.000028219 s |
0.000011205040054846904 s |
2.52 |
scatter_sum / Jax / cpu / Forward |
0.000027913 s |
0.000011392160013201649 s |
2.45 |
scatter_sum / HLOOpt / cpu / Forward |
0.000027952000000000003 s |
0.000012204599997858169 s |
2.29 |
scatter_sum / PartOpt / cpu / Forward |
0.000027289 s |
0.00001159305999863136 s |
2.35 |
scatter_sum / IPartOpt / cpu / Forward |
0.000028189 s |
0.000012415900000632972 s |
2.27 |
scatter_sum / DefOpt / cpu / Forward |
0.000027962 s |
0.000011770320006689872 s |
2.38 |
scatter_sum / IDefOpt / cpu / Forward |
0.000027716 s |
0.000012068499972883727 s |
2.30 |
scatter_sum / JaXPipe / cpu / PreRev |
0.000028212 s |
0.000011716140024873311 s |
2.41 |
scatter_sum / JaXPipe / cpu / PostRev |
0.000028202 s |
0.000011641600021903288 s |
2.42 |
scatter_sum / JaXPipe / cpu / BothRev |
0.000028132 s |
0.000011614340000960513 s |
2.42 |
scatter_sum / Jax / cpu / BothRev |
0.000028274 s |
0.000012184240022179438 s |
2.32 |
scatter_sum / HLOOpt / cpu / PreRev |
0.00002799 s |
0.000013060520022918356 s |
2.14 |
scatter_sum / HLOOpt / cpu / PostRev |
0.000027682 s |
0.00001368204001664708 s |
2.02 |
scatter_sum / HLOOpt / cpu / BothRev |
0.000028427 s |
0.000011856519995490089 s |
2.40 |
scatter_sum / PartOpt / cpu / PreRev |
0.000027622 s |
0.000011116820005554472 s |
2.48 |
scatter_sum / PartOpt / cpu / PostRev |
0.000028005 s |
0.00001186079993203748 s |
2.36 |
scatter_sum / PartOpt / cpu / BothRev |
0.000028604000000000003 s |
0.000012269600038052886 s |
2.33 |
scatter_sum / IPartOpt / cpu / PreRev |
0.000028467 s |
0.000011251180003455376 s |
2.53 |
scatter_sum / IPartOpt / cpu / PostRev |
0.000028642 s |
0.000011199540022062138 s |
2.56 |
scatter_sum / IPartOpt / cpu / BothRev |
0.000027965 s |
0.000011617919954005627 s |
2.41 |
scatter_sum / DefOpt / cpu / PreRev |
0.00002863 s |
0.000011557839989109198 s |
2.48 |
scatter_sum / DefOpt / cpu / PostRev |
0.000027672 s |
0.000011769799975809292 s |
2.35 |
scatter_sum / DefOpt / cpu / BothRev |
0.000028244 s |
0.00001178735999019409 s |
2.40 |
scatter_sum / IDefOpt / cpu / PreRev |
0.000028516 s |
0.000012042659973303673 s |
2.37 |
scatter_sum / IDefOpt / cpu / PostRev |
0.000028134 s |
0.000011558019987205625 s |
2.43 |
scatter_sum / IDefOpt / cpu / BothRev |
0.000028133 s |
0.00001182768003673118 s |
2.38 |
slicing / JaXPipe / cpu / Primal |
0.0000065482799709570825 s |
0.000006638120012212312 s |
0.99 |
slicing / Jax / cpu / Primal |
0.000006330080004772754 s |
0.000006729740034643328 s |
0.94 |
slicing / HLOOpt / cpu / Primal |
0.0000066157199671579294 s |
0.00000629295998805901 s |
1.05 |
slicing / PartOpt / cpu / Primal |
0.000006220999966899399 s |
0.000006045859981895773 s |
1.03 |
slicing / IPartOpt / cpu / Primal |
0.0000064770999961183404 s |
0.000006430899966289871 s |
1.01 |
slicing / DefOpt / cpu / Primal |
0.000006425020010283333 s |
0.000006045840000297176 s |
1.06 |
slicing / IDefOpt / cpu / Primal |
0.000006333220026135677 s |
0.000006516900029964745 s |
0.97 |
slicing / JaXPipe / cpu / Forward |
0.000010439060006319776 s |
0.00000963860000410932 s |
1.08 |
slicing / Jax / cpu / Forward |
0.00001004757999908179 s |
0.0000093633799951931 s |
1.07 |
slicing / HLOOpt / cpu / Forward |
0.000010833739970621537 s |
0.000009715839969430815 s |
1.12 |
slicing / PartOpt / cpu / Forward |
0.000010022279957411228 s |
0.000009247120015061228 s |
1.08 |
slicing / IPartOpt / cpu / Forward |
0.000010619779968692456 s |
0.000009682860036264171 s |
1.10 |
slicing / DefOpt / cpu / Forward |
0.000010489020014574635 s |
0.00000980009998784226 s |
1.07 |
slicing / IDefOpt / cpu / Forward |
0.000010189799995714566 s |
0.00000932759996430832 s |
1.09 |
slicing / JaXPipe / cpu / PreRev |
0.000011211060036657728 s |
0.000010271939991071124 s |
1.09 |
slicing / JaXPipe / cpu / PostRev |
0.000010807120033859974 s |
0.000011063819965784204 s |
0.98 |
slicing / JaXPipe / cpu / BothRev |
0.00001091166001970123 s |
0.00001043989999743644 s |
1.05 |
slicing / Jax / cpu / BothRev |
0.000010656760023266543 s |
0.000009840040020208107 s |
1.08 |
slicing / HLOOpt / cpu / PreRev |
0.000011326640005790978 s |
0.000010213960003966348 s |
1.11 |
slicing / HLOOpt / cpu / PostRev |
0.000012954499998159009 s |
0.00001261207993593416 s |
1.03 |
slicing / HLOOpt / cpu / BothRev |
0.000010528479997446991 s |
0.000009878719984044436 s |
1.07 |
slicing / PartOpt / cpu / PreRev |
0.000010800219997690876 s |
0.000010214859985353542 s |
1.06 |
slicing / PartOpt / cpu / PostRev |
0.00001103093997699034 s |
0.000009956999983842252 s |
1.11 |
slicing / PartOpt / cpu / BothRev |
0.000011035020033887122 s |
0.000010311199994248454 s |
1.07 |
slicing / IPartOpt / cpu / PreRev |
0.000010606920050122426 s |
0.000009981699986383318 s |
1.06 |
slicing / IPartOpt / cpu / PostRev |
0.000010787960000016027 s |
0.00001045855996380851 s |
1.03 |
slicing / IPartOpt / cpu / BothRev |
0.000010163059932892791 s |
0.000009998220002671588 s |
1.02 |
slicing / DefOpt / cpu / PreRev |
0.000010366580008849269 s |
0.000009611019986550672 s |
1.08 |
slicing / DefOpt / cpu / PostRev |
0.000010809200002768192 s |
0.000009998039986385266 s |
1.08 |
slicing / DefOpt / cpu / BothRev |
0.000010585219988570317 s |
0.00000963705998401565 s |
1.10 |
slicing / IDefOpt / cpu / PreRev |
0.00001079602006029745 s |
0.000010339760019633103 s |
1.04 |
slicing / IDefOpt / cpu / PostRev |
0.000010678720036594312 s |
0.000009949260011126173 s |
1.07 |
slicing / IDefOpt / cpu / BothRev |
0.000010291880025761202 s |
0.000009970660012186271 s |
1.03 |
slicing / JaXPipe / cuda / Primal |
0.000002271 s |
0.000001887 s |
1.20 |
slicing / Jax / cuda / Primal |
0.00000224 s |
0.000001887 s |
1.19 |
slicing / HLOOpt / cuda / Primal |
0.000002271 s |
0.000001887 s |
1.20 |
slicing / PartOpt / cuda / Primal |
0.00000224 s |
0.000001887 s |
1.19 |
slicing / IPartOpt / cuda / Primal |
0.000002271 s |
0.000001888 s |
1.20 |
slicing / DefOpt / cuda / Primal |
0.000002271 s |
0.000001887 s |
1.20 |
slicing / IDefOpt / cuda / Primal |
0.000002271 s |
0.000001887 s |
1.20 |
slicing / JaXPipe / cuda / Forward |
0.000010688 s |
0.000011328 s |
0.94 |
slicing / Jax / cuda / Forward |
0.000010304 s |
0.00001088 s |
0.95 |
slicing / HLOOpt / cuda / Forward |
0.000009792 s |
0.000009823 s |
1.00 |
slicing / PartOpt / cuda / Forward |
0.000010272 s |
0.000010048 s |
1.02 |
slicing / IPartOpt / cuda / Forward |
0.00001088 s |
0.000009824 s |
1.11 |
slicing / DefOpt / cuda / Forward |
0.000010145 s |
0.000009184 s |
1.10 |
slicing / IDefOpt / cuda / Forward |
0.000010303 s |
0.000009952 s |
1.04 |
slicing / JaXPipe / cuda / PreRev |
0.000010207 s |
0.000009632 s |
1.06 |
slicing / JaXPipe / cuda / PostRev |
0.000010209 s |
0.000010016 s |
1.02 |
slicing / JaXPipe / cuda / BothRev |
0.000010592 s |
0.0000096 s |
1.10 |
slicing / Jax / cuda / BothRev |
0.000010047 s |
0.000009728 s |
1.03 |
slicing / HLOOpt / cuda / PreRev |
0.00001024 s |
0.000010112 s |
1.01 |
slicing / HLOOpt / cuda / PostRev |
0.000010272 s |
0.000009728 s |
1.06 |
slicing / HLOOpt / cuda / BothRev |
0.000010399 s |
0.000009472 s |
1.10 |
slicing / PartOpt / cuda / PreRev |
0.0000104 s |
0.000009887 s |
1.05 |
slicing / PartOpt / cuda / PostRev |
0.000010208 s |
0.0000096 s |
1.06 |
slicing / PartOpt / cuda / BothRev |
0.000010176 s |
0.00000912 s |
1.12 |
slicing / IPartOpt / cuda / PreRev |
0.00001056 s |
0.00000992 s |
1.06 |
slicing / IPartOpt / cuda / PostRev |
0.00001024 s |
0.0000096 s |
1.07 |
slicing / IPartOpt / cuda / BothRev |
0.000010431 s |
0.000009504 s |
1.10 |
slicing / DefOpt / cuda / PreRev |
0.000011488 s |
0.000009696 s |
1.18 |
slicing / DefOpt / cuda / PostRev |
0.000011455999999999998 s |
0.0000096 s |
1.19 |
slicing / DefOpt / cuda / BothRev |
0.000010528 s |
0.000010016 s |
1.05 |
slicing / IDefOpt / cuda / PreRev |
0.00001072 s |
0.000011104 s |
0.97 |
slicing / IDefOpt / cuda / PostRev |
0.00000976 s |
0.000009504 s |
1.03 |
slicing / IDefOpt / cuda / BothRev |
0.000009984 s |
0.00000976 s |
1.02 |
slicing / JaXPipe / tpu / Primal |
9.64575e-7 s |
0.00000102565 s |
0.94 |
slicing / Jax / tpu / Primal |
9.7485e-7 s |
9.7245e-7 s |
1.00 |
slicing / HLOOpt / tpu / Primal |
9.66875e-7 s |
0.0000010265 s |
0.94 |
slicing / PartOpt / tpu / Primal |
9.7105e-7 s |
9.73325e-7 s |
1.00 |
slicing / IPartOpt / tpu / Primal |
9.696249999999998e-7 s |
0.0000010236000000000002 s |
0.95 |
slicing / DefOpt / tpu / Primal |
9.68275e-7 s |
9.688499999999998e-7 s |
1.00 |
slicing / IDefOpt / tpu / Primal |
9.71725e-7 s |
0.0000010255 s |
0.95 |
slicing / JaXPipe / tpu / Forward |
0.0000014101749999999998 s |
0.000001410875 s |
1.00 |
slicing / Jax / tpu / Forward |
0.0000014199999999999995 s |
0.0000014758 s |
0.96 |
slicing / HLOOpt / tpu / Forward |
0.000001516125 s |
0.000001517325 s |
1.00 |
slicing / PartOpt / tpu / Forward |
0.0000014393 s |
0.00000150075 s |
0.96 |
slicing / IPartOpt / tpu / Forward |
0.0000015214 s |
0.0000015239249999999998 s |
1.00 |
slicing / DefOpt / tpu / Forward |
0.000001438925 s |
0.0000014960499999999998 s |
0.96 |
slicing / IDefOpt / tpu / Forward |
0.00000151915 s |
0.000001517025 s |
1.00 |
slicing / JaXPipe / tpu / PreRev |
0.000002377825 s |
0.00000257555 s |
0.92 |
slicing / JaXPipe / tpu / PostRev |
0.0000025288500000000004 s |
0.0000025172250000000003 s |
1.00 |
slicing / JaXPipe / tpu / BothRev |
0.000002399275 s |
0.00000258475 s |
0.93 |
slicing / Jax / tpu / BothRev |
0.0000025425500000000003 s |
0.000002545125 s |
1.00 |
slicing / HLOOpt / tpu / PreRev |
0.000002404275 s |
0.000002599825 s |
0.92 |
slicing / HLOOpt / tpu / PostRev |
0.00000253525 s |
0.000002543425 s |
1.00 |
slicing / HLOOpt / tpu / BothRev |
0.00000239775 s |
0.000002587075 s |
0.93 |
slicing / PartOpt / tpu / PreRev |
0.0000025392749999999995 s |
0.0000025336500000000003 s |
1.00 |
slicing / PartOpt / tpu / PostRev |
0.000002402925 s |
0.0000025847 s |
0.93 |
slicing / PartOpt / tpu / BothRev |
0.0000025355 s |
0.000002535825 s |
1.00 |
slicing / IPartOpt / tpu / PreRev |
0.000002404025 s |
0.0000025883499999999995 s |
0.93 |
slicing / IPartOpt / tpu / PostRev |
0.000002539025 s |
0.000002543975 s |
1.00 |
slicing / IPartOpt / tpu / BothRev |
0.0000024053 s |
0.0000025956 s |
0.93 |
slicing / DefOpt / tpu / PreRev |
0.000002545075 s |
0.0000025313750000000004 s |
1.01 |
slicing / DefOpt / tpu / PostRev |
0.0000023991 s |
0.000002591925 s |
0.93 |
slicing / DefOpt / tpu / BothRev |
0.000002545375 s |
0.0000025369750000000004 s |
1.00 |
slicing / IDefOpt / tpu / PreRev |
0.00000239115 s |
0.000002578725 s |
0.93 |
slicing / IDefOpt / tpu / PostRev |
0.000002547625 s |
0.0000025319000000000003 s |
1.01 |
slicing / IDefOpt / tpu / BothRev |
0.0000024014 s |
0.000002579375 s |
0.93 |
slicing / JaXPipe / cpu / Primal |
0.000015819 s |
0.000006638120012212312 s |
2.38 |
slicing / Jax / cpu / Primal |
0.000015948 s |
0.000006729740034643328 s |
2.37 |
slicing / HLOOpt / cpu / Primal |
0.000015993 s |
0.00000629295998805901 s |
2.54 |
slicing / PartOpt / cpu / Primal |
0.000015715 s |
0.000006045859981895773 s |
2.60 |
slicing / IPartOpt / cpu / Primal |
0.000016159 s |
0.000006430899966289871 s |
2.51 |
slicing / DefOpt / cpu / Primal |
0.000015951 s |
0.000006045840000297176 s |
2.64 |
slicing / IDefOpt / cpu / Primal |
0.000015929999999999998 s |
0.000006516900029964745 s |
2.44 |
slicing / JaXPipe / cpu / Forward |
0.000021174 s |
0.00000963860000410932 s |
2.20 |
slicing / Jax / cpu / Forward |
0.000020963 s |
0.0000093633799951931 s |
2.24 |
slicing / HLOOpt / cpu / Forward |
0.000020563000000000003 s |
0.000009715839969430815 s |
2.12 |
slicing / PartOpt / cpu / Forward |
0.00002106 s |
0.000009247120015061228 s |
2.28 |
slicing / IPartOpt / cpu / Forward |
0.000020651 s |
0.000009682860036264171 s |
2.13 |
slicing / DefOpt / cpu / Forward |
0.000021087000000000003 s |
0.00000980009998784226 s |
2.15 |
slicing / IDefOpt / cpu / Forward |
0.000021137 s |
0.00000932759996430832 s |
2.27 |
slicing / JaXPipe / cpu / PreRev |
0.000022157 s |
0.000010271939991071124 s |
2.16 |
slicing / JaXPipe / cpu / PostRev |
0.000021512 s |
0.000011063819965784204 s |
1.94 |
slicing / JaXPipe / cpu / BothRev |
0.000021666 s |
0.00001043989999743644 s |
2.08 |
slicing / Jax / cpu / BothRev |
0.000021633 s |
0.000009840040020208107 s |
2.20 |
slicing / HLOOpt / cpu / PreRev |
0.000021822 s |
0.000010213960003966348 s |
2.14 |
slicing / HLOOpt / cpu / PostRev |
0.000021535 s |
0.00001261207993593416 s |
1.71 |
slicing / HLOOpt / cpu / BothRev |
0.000021792 s |
0.000009878719984044436 s |
2.21 |
slicing / PartOpt / cpu / PreRev |
0.000021958 s |
0.000010214859985353542 s |
2.15 |
slicing / PartOpt / cpu / PostRev |
0.000022592 s |
0.000009956999983842252 s |
2.27 |
slicing / PartOpt / cpu / BothRev |
0.000022035 s |
0.000010311199994248454 s |
2.14 |
slicing / IPartOpt / cpu / PreRev |
0.000021929 s |
0.000009981699986383318 s |
2.20 |
slicing / IPartOpt / cpu / PostRev |
0.000021677 s |
0.00001045855996380851 s |
2.07 |
slicing / IPartOpt / cpu / BothRev |
0.000022 s |
0.000009998220002671588 s |
2.20 |
slicing / DefOpt / cpu / PreRev |
0.000021978 s |
0.000009611019986550672 s |
2.29 |
slicing / DefOpt / cpu / PostRev |
0.000021702 s |
0.000009998039986385266 s |
2.17 |
slicing / DefOpt / cpu / BothRev |
0.000021582 s |
0.00000963705998401565 s |
2.24 |
slicing / IDefOpt / cpu / PreRev |
0.000021962 s |
0.000010339760019633103 s |
2.12 |
slicing / IDefOpt / cpu / PostRev |
0.000021569000000000003 s |
0.000009949260011126173 s |
2.17 |
slicing / IDefOpt / cpu / BothRev |
0.000021586 s |
0.000009970660012186271 s |
2.16 |
sum / JaXPipe / cpu / Primal |
0.000009008359993458726 s |
0.000007645399964530952 s |
1.18 |
sum / Jax / cpu / Primal |
0.000008545260016035172 s |
0.000007648059981875122 s |
1.12 |
sum / HLOOpt / cpu / Primal |
0.000008168699987436411 s |
0.000007830219947209117 s |
1.04 |
sum / PartOpt / cpu / Primal |
0.00000808555999356031 s |
0.000008145459978550208 s |
0.99 |
sum / IPartOpt / cpu / Primal |
0.000008008760005395743 s |
0.000008449280003333114 s |
0.95 |
sum / DefOpt / cpu / Primal |
0.000008466720028081908 s |
0.000007587159980175784 s |
1.12 |
sum / IDefOpt / cpu / Primal |
0.000008163700076693203 s |
0.0000079674000335217 s |
1.02 |
sum / JaXPipe / cpu / Forward |
0.00001200092003273312 s |
0.000011516220010889813 s |
1.04 |
sum / Jax / cpu / Forward |
0.000011746379968826658 s |
0.000011451039999883506 s |
1.03 |
sum / HLOOpt / cpu / Forward |
0.000012756340020132484 s |
0.000011789640011556912 s |
1.08 |
sum / PartOpt / cpu / Forward |
0.00001183330000458227 s |
0.000011053859989260672 s |
1.07 |
sum / IPartOpt / cpu / Forward |
0.00001191765999465133 s |
0.000011822620008388183 s |
1.01 |
sum / DefOpt / cpu / Forward |
0.00001159913997980766 s |
0.000010920239947154187 s |
1.06 |
sum / IDefOpt / cpu / Forward |
0.000012075040012859973 s |
0.000011344999993525562 s |
1.06 |
sum / JaXPipe / cpu / PreRev |
0.00001152241999079706 s |
0.000010926760069196462 s |
1.05 |
sum / JaXPipe / cpu / PostRev |
0.000011665639976854437 s |
0.000010825520002981649 s |
1.08 |
sum / JaXPipe / cpu / BothRev |
0.000011525720001372976 s |
0.00001116623997404531 s |
1.03 |
sum / Jax / cpu / BothRev |
0.00001180508004836156 s |
0.000011224160007259342 s |
1.05 |
sum / HLOOpt / cpu / PreRev |
0.000011804760006270954 s |
0.000011186540041308036 s |
1.06 |
sum / HLOOpt / cpu / PostRev |
0.000013719979988309203 s |
0.000012992799984203885 s |
1.06 |
sum / HLOOpt / cpu / BothRev |
0.000011332519989082355 s |
0.00001103836000766023 s |
1.03 |
sum / PartOpt / cpu / PreRev |
0.000011368540008334092 s |
0.00001072174000000814 s |
1.06 |
sum / PartOpt / cpu / PostRev |
0.000011433200006649713 s |
0.000010569659998509453 s |
1.08 |
sum / PartOpt / cpu / BothRev |
0.00001228032001563406 s |
0.00001155784001639404 s |
1.06 |
sum / IPartOpt / cpu / PreRev |
0.000011059839989684406 s |
0.000011202260011486942 s |
0.99 |
sum / IPartOpt / cpu / PostRev |
0.00001159669999651669 s |
0.000011255660010647262 s |
1.03 |
sum / IPartOpt / cpu / BothRev |
0.000011579119955058558 s |
0.000010993680016326834 s |
1.05 |
sum / DefOpt / cpu / PreRev |
0.000011204459970031166 s |
0.000011120220005977898 s |
1.01 |
sum / DefOpt / cpu / PostRev |
0.000011259659986535551 s |
0.000011071139997511637 s |
1.02 |
sum / DefOpt / cpu / BothRev |
0.000011220119968129438 s |
0.000011151440021421876 s |
1.01 |
sum / IDefOpt / cpu / PreRev |
0.000011430999975345911 s |
0.000010621079964039382 s |
1.08 |
sum / IDefOpt / cpu / PostRev |
0.0000115595999523066 s |
0.000011201700044694008 s |
1.03 |
sum / IDefOpt / cpu / BothRev |
0.000011434259995439789 s |
0.00001039341997966403 s |
1.10 |
sum / JaXPipe / cuda / Primal |
0.000002431 s |
0.000002048 s |
1.19 |
sum / Jax / cuda / Primal |
0.000002431 s |
0.000002048 s |
1.19 |
sum / HLOOpt / cuda / Primal |
0.000002431 s |
0.000002047 s |
1.19 |
sum / PartOpt / cuda / Primal |
0.000002431 s |
0.000002047 s |
1.19 |
sum / IPartOpt / cuda / Primal |
0.000002431 s |
0.000002048 s |
1.19 |
sum / DefOpt / cuda / Primal |
0.000002432 s |
0.000002048 s |
1.19 |
sum / IDefOpt / cuda / Primal |
0.000002432 s |
0.000002048 s |
1.19 |
sum / JaXPipe / cuda / Forward |
0.000010848 s |
0.000010272 s |
1.06 |
sum / Jax / cuda / Forward |
0.000010592 s |
0.000010048 s |
1.05 |
sum / HLOOpt / cuda / Forward |
0.000010431 s |
0.000010368 s |
1.01 |
sum / PartOpt / cuda / Forward |
0.000010656 s |
0.00000992 s |
1.07 |
sum / IPartOpt / cuda / Forward |
0.00001056 s |
0.000010209 s |
1.03 |
sum / DefOpt / cuda / Forward |
0.000010816 s |
0.000010016 s |
1.08 |
sum / IDefOpt / cuda / Forward |
0.0000104 s |
0.000010272 s |
1.01 |
sum / JaXPipe / cuda / PreRev |
0.000010592 s |
0.000010048 s |
1.05 |
sum / JaXPipe / cuda / PostRev |
0.00001024 s |
0.000009633 s |
1.06 |
sum / JaXPipe / cuda / BothRev |
0.000009791 s |
0.000009376 s |
1.04 |
sum / Jax / cuda / BothRev |
0.000010208 s |
0.0000096 s |
1.06 |
sum / HLOOpt / cuda / PreRev |
0.00001024 s |
0.000009567 s |
1.07 |
sum / HLOOpt / cuda / PostRev |
0.000010016 s |
0.00000944 s |
1.06 |
sum / HLOOpt / cuda / BothRev |
0.000010176 s |
0.000009185 s |
1.11 |
sum / PartOpt / cuda / PreRev |
0.000010369 s |
0.000010208 s |
1.02 |
sum / PartOpt / cuda / PostRev |
0.000010273 s |
0.000009824 s |
1.05 |
sum / PartOpt / cuda / BothRev |
0.000010144 s |
0.000009888 s |
1.03 |
sum / IPartOpt / cuda / PreRev |
0.000010368 s |
0.000010208 s |
1.02 |
sum / IPartOpt / cuda / PostRev |
0.000010176 s |
0.000009664 s |
1.05 |
sum / IPartOpt / cuda / BothRev |
0.00001024 s |
0.000009664 s |
1.06 |
sum / DefOpt / cuda / PreRev |
0.000010208 s |
0.000009984 s |
1.02 |
sum / DefOpt / cuda / PostRev |
0.00001024 s |
0.000009664 s |
1.06 |
sum / DefOpt / cuda / BothRev |
0.000010368 s |
0.000009504 s |
1.09 |
sum / IDefOpt / cuda / PreRev |
0.000010176 s |
0.000009856 s |
1.03 |
sum / IDefOpt / cuda / PostRev |
0.000010143 s |
0.000009408 s |
1.08 |
sum / IDefOpt / cuda / BothRev |
0.000010497 s |
0.000009632 s |
1.09 |
sum / JaXPipe / tpu / Primal |
5.102e-7 s |
5.1015e-7 s |
1.00 |
sum / Jax / tpu / Primal |
5.4705e-7 s |
5.471999999999999e-7 s |
1.00 |
sum / HLOOpt / tpu / Primal |
5.099749999999999e-7 s |
5.10525e-7 s |
1.00 |
sum / PartOpt / tpu / Primal |
5.467249999999999e-7 s |
5.4695e-7 s |
1.00 |
sum / IPartOpt / tpu / Primal |
5.10125e-7 s |
5.106750000000001e-7 s |
1.00 |
sum / DefOpt / tpu / Primal |
5.47375e-7 s |
5.473499999999999e-7 s |
1.00 |
sum / IDefOpt / tpu / Primal |
5.102750000000001e-7 s |
5.10425e-7 s |
1.00 |
sum / JaXPipe / tpu / Forward |
0.000001553225 s |
0.000001554225 s |
1.00 |
sum / Jax / tpu / Forward |
0.0000014973 s |
0.0000015011250000000002 s |
1.00 |
sum / HLOOpt / tpu / Forward |
0.000001532475 s |
0.000001527725 s |
1.00 |
sum / PartOpt / tpu / Forward |
0.000001493025 s |
0.000001494675 s |
1.00 |
sum / IPartOpt / tpu / Forward |
0.0000015319749999999998 s |
0.000001532525 s |
1.00 |
sum / DefOpt / tpu / Forward |
0.0000014962500000000005 s |
0.0000014973 s |
1.00 |
sum / IDefOpt / tpu / Forward |
0.00000153685 s |
0.00000152915 s |
1.01 |
sum / JaXPipe / tpu / PreRev |
9.98275e-7 s |
0.00000104985 s |
0.95 |
sum / JaXPipe / tpu / PostRev |
0.0000010403 s |
0.00000108665 s |
0.96 |
sum / JaXPipe / tpu / BothRev |
0.00000100355 s |
0.000001049175 s |
0.96 |
sum / Jax / tpu / BothRev |
0.000001037 s |
0.000001091625 s |
0.95 |
sum / HLOOpt / tpu / PreRev |
0.0000010062 s |
0.0000010556 s |
0.95 |
sum / HLOOpt / tpu / PostRev |
0.000001037925 s |
0.0000010847000000000002 s |
0.96 |
sum / HLOOpt / tpu / BothRev |
0.0000010008999999999998 s |
0.000001045625 s |
0.96 |
sum / PartOpt / tpu / PreRev |
0.000001043825 s |
0.0000010876 s |
0.96 |
sum / PartOpt / tpu / PostRev |
0.0000010074 s |
0.00000104685 s |
0.96 |
sum / PartOpt / tpu / BothRev |
0.00000104105 s |
0.0000010919 s |
0.95 |
sum / IPartOpt / tpu / PreRev |
0.0000010023250000000002 s |
0.000001051 s |
0.95 |
sum / IPartOpt / tpu / PostRev |
0.0000010406 s |
0.00000108285 s |
0.96 |
sum / IPartOpt / tpu / BothRev |
0.0000010006750000000002 s |
0.000001049375 s |
0.95 |
sum / DefOpt / tpu / PreRev |
0.000001036575 s |
0.00000109035 s |
0.95 |
sum / DefOpt / tpu / PostRev |
0.0000010012999999999998 s |
0.000001048725 s |
0.95 |
sum / DefOpt / tpu / BothRev |
0.0000010409 s |
0.0000010904 s |
0.95 |
sum / IDefOpt / tpu / PreRev |
0.00000100815 s |
0.000001045875 s |
0.96 |
sum / IDefOpt / tpu / PostRev |
0.00000104665 s |
0.0000010865 s |
0.96 |
sum / IDefOpt / tpu / BothRev |
0.000001001575 s |
0.000001051825 s |
0.95 |
sum / JaXPipe / cpu / Primal |
0.00001857 s |
0.000007645399964530952 s |
2.43 |
sum / Jax / cpu / Primal |
0.000018236 s |
0.000007648059981875122 s |
2.38 |
sum / HLOOpt / cpu / Primal |
0.000018365 s |
0.000007830219947209117 s |
2.35 |
sum / PartOpt / cpu / Primal |
0.000018303 s |
0.000008145459978550208 s |
2.25 |
sum / IPartOpt / cpu / Primal |
0.000018149 s |
0.000008449280003333114 s |
2.15 |
sum / DefOpt / cpu / Primal |
0.000018068 s |
0.000007587159980175784 s |
2.38 |
sum / IDefOpt / cpu / Primal |
0.000017919000000000002 s |
0.0000079674000335217 s |
2.25 |
sum / JaXPipe / cpu / Forward |
0.000025533 s |
0.000011516220010889813 s |
2.22 |
sum / Jax / cpu / Forward |
0.000024808 s |
0.000011451039999883506 s |
2.17 |
sum / HLOOpt / cpu / Forward |
0.000024778 s |
0.000011789640011556912 s |
2.10 |
sum / PartOpt / cpu / Forward |
0.000024683 s |
0.000011053859989260672 s |
2.23 |
sum / IPartOpt / cpu / Forward |
0.000025597 s |
0.000011822620008388183 s |
2.17 |
sum / DefOpt / cpu / Forward |
0.000025044 s |
0.000010920239947154187 s |
2.29 |
sum / IDefOpt / cpu / Forward |
0.00002502 s |
0.000011344999993525562 s |
2.21 |
sum / JaXPipe / cpu / PreRev |
0.000024141 s |
0.000010926760069196462 s |
2.21 |
sum / JaXPipe / cpu / PostRev |
0.000023639 s |
0.000010825520002981649 s |
2.18 |
sum / JaXPipe / cpu / BothRev |
0.000023534 s |
0.00001116623997404531 s |
2.11 |
sum / Jax / cpu / BothRev |
0.000023691 s |
0.000011224160007259342 s |
2.11 |
sum / HLOOpt / cpu / PreRev |
0.000023652 s |
0.000011186540041308036 s |
2.11 |
sum / HLOOpt / cpu / PostRev |
0.000022948 s |
0.000012992799984203885 s |
1.77 |
sum / HLOOpt / cpu / BothRev |
0.000023056 s |
0.00001103836000766023 s |
2.09 |
sum / PartOpt / cpu / PreRev |
0.000023645 s |
0.00001072174000000814 s |
2.21 |
sum / PartOpt / cpu / PostRev |
0.000023782 s |
0.000010569659998509453 s |
2.25 |
sum / PartOpt / cpu / BothRev |
0.000023532 s |
0.00001155784001639404 s |
2.04 |
sum / IPartOpt / cpu / PreRev |
0.000023668 s |
0.000011202260011486942 s |
2.11 |
sum / IPartOpt / cpu / PostRev |
0.000023593 s |
0.000011255660010647262 s |
2.10 |
sum / IPartOpt / cpu / BothRev |
0.000023265 s |
0.000010993680016326834 s |
2.12 |
sum / DefOpt / cpu / PreRev |
0.000023519000000000003 s |
0.000011120220005977898 s |
2.11 |
sum / DefOpt / cpu / PostRev |
0.000023671 s |
0.000011071139997511637 s |
2.14 |
sum / DefOpt / cpu / BothRev |
0.000023578 s |
0.000011151440021421876 s |
2.11 |
sum / IDefOpt / cpu / PreRev |
0.000023501 s |
0.000010621079964039382 s |
2.21 |
sum / IDefOpt / cpu / PostRev |
0.000023193 s |
0.000011201700044694008 s |
2.07 |
sum / IDefOpt / cpu / BothRev |
0.000023513 s |
0.00001039341997966403 s |
2.26 |
value_and_grad / JaXPipe / cpu / Primal |
0.000015732999991087126 s |
0.000014406580003196723 s |
1.09 |
value_and_grad / Jax / cpu / Primal |
0.000014810059965384426 s |
0.00001402247997248196 s |
1.06 |
value_and_grad / HLOOpt / cpu / Primal |
0.00001470501998483087 s |
0.000013926480032750988 s |
1.06 |
value_and_grad / PartOpt / cpu / Primal |
0.000014893719999236057 s |
0.000013946120016044003 s |
1.07 |
value_and_grad / IPartOpt / cpu / Primal |
0.000014808839996476308 s |
0.000013939880000179985 s |
1.06 |
value_and_grad / DefOpt / cpu / Primal |
0.000015844200024730526 s |
0.000014367180010594894 s |
1.10 |
value_and_grad / IDefOpt / cpu / Primal |
0.0000143204399591923 s |
0.000013935539982412593 s |
1.03 |
value_and_grad / JaXPipe / cuda / Primal |
0.000033696 s |
0.000033759999999999995 s |
1.00 |
value_and_grad / Jax / cuda / Primal |
0.000032800000000000004 s |
0.000033056 s |
0.99 |
value_and_grad / HLOOpt / cuda / Primal |
0.000032959 s |
0.000032416 s |
1.02 |
value_and_grad / PartOpt / cuda / Primal |
0.000033312 s |
0.000033056 s |
1.01 |
value_and_grad / IPartOpt / cuda / Primal |
0.000033376 s |
0.00003264 s |
1.02 |
value_and_grad / DefOpt / cuda / Primal |
0.000037408 s |
0.000032672 s |
1.14 |
value_and_grad / IDefOpt / cuda / Primal |
0.000038304 s |
0.000032064 s |
1.19 |
value_and_grad / JaXPipe / tpu / Primal |
0 s |
0 s |
1 |
value_and_grad / Jax / tpu / Primal |
0 s |
0 s |
1 |
value_and_grad / HLOOpt / tpu / Primal |
0 s |
0 s |
1 |
value_and_grad / PartOpt / tpu / Primal |
0 s |
0 s |
1 |
value_and_grad / IPartOpt / tpu / Primal |
0 s |
0 s |
1 |
value_and_grad / DefOpt / tpu / Primal |
0 s |
0 s |
1 |
value_and_grad / IDefOpt / tpu / Primal |
0 s |
0 s |
1 |
value_and_grad / JaXPipe / cpu / Primal |
0.00002832 s |
0.000014406580003196723 s |
1.97 |
value_and_grad / Jax / cpu / Primal |
0.000027644 s |
0.00001402247997248196 s |
1.97 |
value_and_grad / HLOOpt / cpu / Primal |
0.000028958 s |
0.000013926480032750988 s |
2.08 |
value_and_grad / PartOpt / cpu / Primal |
0.000028077 s |
0.000013946120016044003 s |
2.01 |
value_and_grad / IPartOpt / cpu / Primal |
0.000028116 s |
0.000013939880000179985 s |
2.02 |
value_and_grad / DefOpt / cpu / Primal |
0.000028348 s |
0.000014367180010594894 s |
1.97 |
value_and_grad / IDefOpt / cpu / Primal |
0.000028127 s |
0.000013935539982412593 s |
2.02 |
jaxmd20 / JaXPipe / cuda / Primal |
0.00146473 s |
0.001438656 s |
1.02 |
jaxmd20 / Jax / cuda / Primal |
0.001486554 s |
0.001457794 s |
1.02 |
jaxmd20 / HLOOpt / cuda / Primal |
0.00134841 s |
0.001319074 s |
1.02 |
jaxmd20 / PartOpt / cuda / Primal |
0.002185368 s |
0.001330945 s |
1.64 |
jaxmd20 / IPartOpt / cuda / Primal |
0.001354778 s |
0.001306946 s |
1.04 |
jaxmd20 / DefOpt / cuda / Primal |
0.000933276 s |
0.0009199049999999 s |
1.01 |
jaxmd20 / IDefOpt / cuda / Primal |
0.000962489 s |
0.000942625 s |
1.02 |
jaxmd20 / JaXPipe / cuda / Forward |
0.001615096 s |
0.001553729 s |
1.04 |
jaxmd20 / Jax / cuda / Forward |
0.0018402499999999 s |
0.001784097 s |
1.03 |
jaxmd20 / HLOOpt / cuda / Forward |
0.0017243459999999 s |
0.001622465 s |
1.06 |
jaxmd20 / PartOpt / cuda / Forward |
0.001693848 s |
0.001625025 s |
1.04 |
jaxmd20 / IPartOpt / cuda / Forward |
0.00170233 s |
0.001625729 s |
1.05 |
jaxmd20 / DefOpt / cuda / Forward |
0.001696474 s |
0.001640737 s |
1.03 |
jaxmd20 / IDefOpt / cuda / Forward |
0.001697848 s |
0.001621602 s |
1.05 |
jaxmd20 / JaXPipe / cuda / PreRev |
0.002734709 s |
0.002683234 s |
1.02 |
jaxmd20 / JaXPipe / cuda / PostRev |
0.005466986 s |
0.005323364 s |
1.03 |
jaxmd20 / JaXPipe / cuda / BothRev |
0.002729614 s |
0.00268874 s |
1.02 |
jaxmd20 / Jax / cuda / BothRev |
0.00544833 s |
0.005367429 s |
1.02 |
jaxmd20 / HLOOpt / cuda / PreRev |
0.002818321 s |
0.002735042 s |
1.03 |
jaxmd20 / HLOOpt / cuda / PostRev |
0.005491684 s |
0.0053471399999999 s |
1.03 |
jaxmd20 / HLOOpt / cuda / BothRev |
0.002806739 s |
0.002724066 s |
1.03 |
jaxmd20 / PartOpt / cuda / PreRev |
0.002888757 s |
0.002834625 s |
1.02 |
jaxmd20 / PartOpt / cuda / PostRev |
0.00561831 s |
0.005432037 s |
1.03 |
jaxmd20 / PartOpt / cuda / BothRev |
0.002821075 s |
0.002772929 s |
1.02 |
jaxmd20 / IPartOpt / cuda / PreRev |
0.00289135 s |
0.002814114 s |
1.03 |
jaxmd20 / IPartOpt / cuda / PostRev |
0.005608123 s |
0.005404004 s |
1.04 |
jaxmd20 / IPartOpt / cuda / BothRev |
0.002819157 s |
0.0027513299999999 s |
1.02 |
jaxmd20 / DefOpt / cuda / PreRev |
0.002883508 s |
0.002829603 s |
1.02 |
jaxmd20 / DefOpt / cuda / PostRev |
0.002809719 s |
0.002740963 s |
1.03 |
jaxmd20 / DefOpt / cuda / BothRev |
0.002808598 s |
0.002774787 s |
1.01 |
jaxmd20 / IDefOpt / cuda / PreRev |
0.002899861 s |
0.0027995549999999 s |
1.04 |
jaxmd20 / IDefOpt / cuda / PostRev |
0.002328951 s |
0.002319777 s |
1.00 |
jaxmd20 / IDefOpt / cuda / BothRev |
0.002813973 s |
0.002749858 s |
1.02 |
jaxmd20 / JaXPipe / tpu / Primal |
0.00928997125 s |
0.00927314125 s |
1.00 |
jaxmd20 / Jax / tpu / Primal |
0.00927781875 s |
0.009277410625 s |
1.00 |
jaxmd20 / HLOOpt / tpu / Primal |
0.009164066875 s |
0.0091523299999999 s |
1.00 |
jaxmd20 / PartOpt / tpu / Primal |
0.009197623125 s |
0.0092039425 s |
1.00 |
jaxmd20 / IPartOpt / tpu / Primal |
0.009202970625 s |
0.009203678125 s |
1.00 |
jaxmd20 / DefOpt / tpu / Primal |
0.0087961468749999 s |
0.008808284375 s |
1.00 |
jaxmd20 / IDefOpt / tpu / Primal |
0.00870232375 s |
0.0087018675 s |
1.00 |
jaxmd20 / JaXPipe / tpu / Forward |
0.01742221625 s |
0.017406293125 s |
1.00 |
jaxmd20 / Jax / tpu / Forward |
0.018751168125 s |
0.018734816875 s |
1.00 |
jaxmd20 / HLOOpt / tpu / Forward |
0.0174076375 s |
0.017393216875 s |
1.00 |
jaxmd20 / PartOpt / tpu / Forward |
0.017422039375 s |
0.0174203675 s |
1.00 |
jaxmd20 / IPartOpt / tpu / Forward |
0.017415935 s |
0.017406431875 s |
1.00 |
jaxmd20 / DefOpt / tpu / Forward |
0.017423855 s |
0.017418041875 s |
1.00 |
jaxmd20 / IDefOpt / tpu / Forward |
0.01741325 s |
0.017410129375 s |
1.00 |
jaxmd20 / JaXPipe / tpu / PreRev |
0.02546834875 s |
0.0254688181249999 s |
1.00 |
jaxmd20 / JaXPipe / tpu / PostRev |
0.021871454375 s |
0.0218769525 s |
1.00 |
jaxmd20 / JaXPipe / tpu / BothRev |
0.025455125 s |
0.025468754375 s |
1.00 |
jaxmd20 / Jax / tpu / BothRev |
0.0218732125 s |
0.021861596875 s |
1.00 |
jaxmd20 / HLOOpt / tpu / PreRev |
0.025570619375 s |
0.0255831725 s |
1.00 |
jaxmd20 / HLOOpt / tpu / PostRev |
0.02071977375 s |
0.020709916875 s |
1.00 |
jaxmd20 / HLOOpt / tpu / BothRev |
0.0256775375 s |
0.02568878875 s |
1.00 |
jaxmd20 / PartOpt / tpu / PreRev |
0.02549829125 s |
0.0254527875 s |
1.00 |
jaxmd20 / PartOpt / tpu / PostRev |
0.021519879375 s |
0.02152217 s |
1.00 |
jaxmd20 / PartOpt / tpu / BothRev |
0.02558424 s |
0.0255547325 s |
1.00 |
jaxmd20 / IPartOpt / tpu / PreRev |
0.025462704375 s |
0.025477075625 s |
1.00 |
jaxmd20 / IPartOpt / tpu / PostRev |
0.0215184693749999 s |
0.021248858125 s |
1.01 |
jaxmd20 / IPartOpt / tpu / BothRev |
0.025552276875 s |
0.0255718356249999 s |
1.00 |
jaxmd20 / DefOpt / tpu / PreRev |
0.02549917625 s |
0.025456913125 s |
1.00 |
jaxmd20 / DefOpt / tpu / PostRev |
0.018810454375 s |
0.0188292325 s |
1.00 |
jaxmd20 / DefOpt / tpu / BothRev |
0.025578944375 s |
0.02555605125 s |
1.00 |
jaxmd20 / IDefOpt / tpu / PreRev |
0.025464384375 s |
0.02547475125 s |
1.00 |
jaxmd20 / IDefOpt / tpu / PostRev |
0.018324838125 s |
0.018316490625 s |
1.00 |
jaxmd20 / IDefOpt / tpu / BothRev |
0.025549673125 s |
0.0255632825 s |
1.00 |
jaxmd40 / JaXPipe / cpu / Primal |
0.0747914049999999 s |
0.072844339 s |
1.03 |
jaxmd40 / Jax / cpu / Primal |
0.069468799 s |
0.085290419 s |
0.81 |
jaxmd40 / HLOOpt / cpu / Primal |
0.106450839 s |
0.089723403 s |
1.19 |
jaxmd40 / PartOpt / cpu / Primal |
0.070216272 s |
0.074612173 s |
0.94 |
jaxmd40 / IPartOpt / cpu / Primal |
0.068599852 s |
0.066914133 s |
1.03 |
jaxmd40 / DefOpt / cpu / Primal |
0.106511561 s |
0.093375959 s |
1.14 |
jaxmd40 / IDefOpt / cpu / Primal |
0.091593121 s |
0.0910838289999999 s |
1.01 |
jaxmd40 / JaXPipe / cpu / Forward |
0.187023589 s |
0.170574911 s |
1.10 |
jaxmd40 / Jax / cpu / Forward |
0.092947221 s |
0.091175984 s |
1.02 |
jaxmd40 / HLOOpt / cpu / Forward |
0.185286036 s |
0.172308492 s |
1.08 |
jaxmd40 / PartOpt / cpu / Forward |
0.180664049 s |
0.176623812 s |
1.02 |
jaxmd40 / IPartOpt / cpu / Forward |
0.187013622 s |
0.174147301 s |
1.07 |
jaxmd40 / DefOpt / cpu / Forward |
0.183556958 s |
0.173570474 s |
1.06 |
jaxmd40 / IDefOpt / cpu / Forward |
0.192778608 s |
0.172948483 s |
1.11 |
jaxmd40 / JaXPipe / cpu / PreRev |
0.242472471 s |
0.246458502 s |
0.98 |
jaxmd40 / JaXPipe / cpu / PostRev |
0.153631364 s |
0.145292605 s |
1.06 |
jaxmd40 / JaXPipe / cpu / BothRev |
0.25967822 s |
0.232384171 s |
1.12 |
jaxmd40 / Jax / cpu / BothRev |
0.159423095 s |
0.144972575 s |
1.10 |
jaxmd40 / HLOOpt / cpu / PreRev |
0.265623481 s |
0.209976645 s |
1.27 |
jaxmd40 / HLOOpt / cpu / PostRev |
0.210901206 s |
0.167030558 s |
1.26 |
jaxmd40 / HLOOpt / cpu / BothRev |
0.274567512 s |
0.240362218 s |
1.14 |
jaxmd40 / PartOpt / cpu / PreRev |
0.238989489 s |
0.225781603 s |
1.06 |
jaxmd40 / PartOpt / cpu / PostRev |
0.160843294 s |
0.133505024 s |
1.20 |
jaxmd40 / PartOpt / cpu / BothRev |
0.292582825 s |
0.2396432289999999 s |
1.22 |
jaxmd40 / IPartOpt / cpu / PreRev |
0.255632113 s |
0.210954968 s |
1.21 |
jaxmd40 / IPartOpt / cpu / PostRev |
0.1516275259999999 s |
0.129907668 s |
1.17 |
jaxmd40 / IPartOpt / cpu / BothRev |
0.286090633 s |
0.2442911049999999 s |
1.17 |
jaxmd40 / DefOpt / cpu / PreRev |
0.257849151 s |
0.207436634 s |
1.24 |
jaxmd40 / DefOpt / cpu / PostRev |
0.206645418 s |
0.160227876 s |
1.29 |
jaxmd40 / DefOpt / cpu / BothRev |
0.281099629 s |
0.266801465 s |
1.05 |
jaxmd40 / IDefOpt / cpu / PreRev |
0.255983835 s |
0.213239064 s |
1.20 |
jaxmd40 / IDefOpt / cpu / PostRev |
0.210175975 s |
0.166438509 s |
1.26 |
jaxmd40 / IDefOpt / cpu / BothRev |
0.2749302799999999 s |
0.2551048099999999 s |
1.08 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / JaXPipe / cuda / Primal |
1.6996809780000002 s |
1.702317745 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / Jax / cuda / Primal |
1.70232081 s |
1.705465397 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / HLOOpt / cuda / Primal |
1.711292707 s |
1.716033577 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / PartOpt / cuda / Primal |
1.6942493010000002 s |
1.697429808 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / IPartOpt / cuda / Primal |
1.692028909 s |
1.694712204 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / DefOpt / cuda / Primal |
1.662351114 s |
1.665316659 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / IDefOpt / cuda / Primal |
1.911666814 s |
1.915802135 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / JaXPipe / tpu / Primal |
3.038814636875 s |
3.03911668 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / Jax / tpu / Primal |
3.039413823125 s |
3.0396639975 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / HLOOpt / tpu / Primal |
3.121635935625 s |
3.122058054375 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / PartOpt / tpu / Primal |
3.060370549375 s |
3.06050589875 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / IPartOpt / tpu / Primal |
3.060577015625 s |
3.060716875 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / DefOpt / tpu / Primal |
2.102382259375 s |
2.1026504125 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / IDefOpt / tpu / Primal |
2.948189166875 s |
2.94873416125 s |
1.00 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / JaXPipe / cpu / Primal |
6.840652416 s |
6.26335534 s |
1.09 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / Jax / cpu / Primal |
6.863899384000001 s |
6.275570235999999 s |
1.09 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / HLOOpt / cpu / Primal |
6.724595834 s |
6.183279134 s |
1.09 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / PartOpt / cpu / Primal |
6.896469751 s |
6.324766463 s |
1.09 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / IPartOpt / cpu / Primal |
6.834958245 s |
6.510950545 s |
1.05 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / DefOpt / cpu / Primal |
2.729002233 s |
2.547048578 s |
1.07 |
neuralgcm_v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / IDefOpt / cpu / Primal |
7.604181316999999 s |
6.79261008 s |
1.12 |
This comment was automatically generated by workflow using github-action-benchmark.
Member
Author
|
Member
Author
|
Member
Author
|
okay I'm very confused and my attempt to make a test failed. Relevant dumps: attempted test i created (but didn't trigger): |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.