-
Notifications
You must be signed in to change notification settings - Fork 26
fix: neural gcm enable correctness check #1848
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
Draft
avik-pal
wants to merge
1
commit into
main
Choose a base branch
from
ap/neuralgcm
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
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
78fd642 to
cc427e3
Compare
cc427e3 to
1f83a82
Compare
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: 1f83a82 | Previous: 30eb4e7 | Ratio |
|---|---|---|---|
actmtch / Jax / cpu / Primal |
0.000007145479949031142 s |
0.00000742670001272927 s |
0.96 |
actmtch / JaXPipe / cpu / Primal |
0.000006753499992555589 s |
0.000007178099976954399 s |
0.94 |
actmtch / PartOpt / cpu / Primal |
0.000006432000036511454 s |
0.000008231920019170502 s |
0.78 |
actmtch / IPartOpt / cpu / Primal |
0.000006258779949348536 s |
0.000009108859985644812 s |
0.69 |
actmtch / HLOOpt / cpu / Primal |
0.000007354720000876114 s |
0.00000942116002079274 s |
0.78 |
actmtch / DefOpt / cpu / Primal |
0.000006975239975872682 s |
0.000009177840011034278 s |
0.76 |
actmtch / IDefOpt / cpu / Primal |
0.000007336479966397747 s |
0.000009169459972326876 s |
0.80 |
actmtch / Jax / cpu / Forward |
0.00001002885998786951 s |
0.000011727619985322234 s |
0.86 |
actmtch / JaXPipe / cpu / Forward |
0.000010853100002350402 s |
0.00001240557998244185 s |
0.87 |
actmtch / PartOpt / cpu / Forward |
0.000010932959985439084 s |
0.000012186899984953924 s |
0.90 |
actmtch / IPartOpt / cpu / Forward |
0.000010320439978386275 s |
0.00001277817995287478 s |
0.81 |
actmtch / HLOOpt / cpu / Forward |
0.000010706300017773172 s |
0.000013135259996488456 s |
0.82 |
actmtch / DefOpt / cpu / Forward |
0.000010249259976262692 s |
0.000012611259999175672 s |
0.81 |
actmtch / IDefOpt / cpu / Forward |
0.000010574320003797766 s |
0.000013058779995844815 s |
0.81 |
actmtch / Jax / cpu / BothRev |
0.000009825960005400702 s |
0.0000101748600081919 s |
0.97 |
actmtch / JaXPipe / cpu / PreRev |
0.000010978560067087528 s |
0.000012500760039984015 s |
0.88 |
actmtch / JaXPipe / cpu / PostRev |
0.00000977645999228116 s |
0.000011682659987855004 s |
0.84 |
actmtch / JaXPipe / cpu / BothRev |
0.000011018519981007556 s |
0.000013351459965633694 s |
0.83 |
actmtch / PartOpt / cpu / PreRev |
0.000011567880010261432 s |
0.00001237502001458779 s |
0.93 |
actmtch / PartOpt / cpu / PostRev |
0.00001146364003943745 s |
0.000010807039989231271 s |
1.06 |
actmtch / PartOpt / cpu / BothRev |
0.000010451280022607534 s |
0.000013357679927139543 s |
0.78 |
actmtch / IPartOpt / cpu / PreRev |
0.000009960660008800916 s |
0.000011974959961662535 s |
0.83 |
actmtch / IPartOpt / cpu / PostRev |
0.000009453080001549098 s |
0.000011647979999906963 s |
0.81 |
actmtch / IPartOpt / cpu / BothRev |
0.000011577620034586289 s |
0.000012888160035799956 s |
0.90 |
actmtch / HLOOpt / cpu / PreRev |
0.000010466719986652606 s |
0.000012809399968318758 s |
0.82 |
actmtch / HLOOpt / cpu / PostRev |
0.00001084916004401748 s |
0.000014683079989481484 s |
0.74 |
actmtch / HLOOpt / cpu / BothRev |
0.00001062472002558934 s |
0.000012941140003022156 s |
0.82 |
actmtch / DefOpt / cpu / PreRev |
0.00001111269999455544 s |
0.000012172299993835623 s |
0.91 |
actmtch / DefOpt / cpu / PostRev |
0.000010894040005950956 s |
0.0000126511599864898 s |
0.86 |
actmtch / DefOpt / cpu / BothRev |
0.000010357420005675522 s |
0.000012905660032629384 s |
0.80 |
actmtch / IDefOpt / cpu / PreRev |
0.000010853900021174922 s |
0.00001217844000166224 s |
0.89 |
actmtch / IDefOpt / cpu / PostRev |
0.000011374760015314678 s |
0.000012553719934658148 s |
0.91 |
actmtch / IDefOpt / cpu / BothRev |
0.00001123255997299566 s |
0.000012284119984542483 s |
0.91 |
actmtch / Jax / cuda / Primal |
0.000002015 s |
0.000002015 s |
1 |
actmtch / JaXPipe / cuda / Primal |
0.000002015 s |
0.000002015 s |
1 |
actmtch / PartOpt / cuda / Primal |
0.000002015 s |
0.000002015 s |
1 |
actmtch / IPartOpt / cuda / Primal |
0.000002015 s |
0.000002015 s |
1 |
actmtch / HLOOpt / cuda / Primal |
0.000002015 s |
0.000002015 s |
1 |
actmtch / DefOpt / cuda / Primal |
0.000002016 s |
0.000002015 s |
1.00 |
actmtch / IDefOpt / cuda / Primal |
0.000002016 s |
0.000002016 s |
1 |
actmtch / Jax / cuda / Forward |
0.000009728 s |
0.000009504 s |
1.02 |
actmtch / JaXPipe / cuda / Forward |
0.000010016 s |
0.000009536 s |
1.05 |
actmtch / PartOpt / cuda / Forward |
0.000009376 s |
0.000009664 s |
0.97 |
actmtch / IPartOpt / cuda / Forward |
0.000009792 s |
0.000009568 s |
1.02 |
actmtch / HLOOpt / cuda / Forward |
0.000010144 s |
0.000010016 s |
1.01 |
actmtch / DefOpt / cuda / Forward |
0.00001008 s |
0.000009504 s |
1.06 |
actmtch / IDefOpt / cuda / Forward |
0.000010016 s |
0.000010016 s |
1 |
actmtch / Jax / cuda / BothRev |
0.00001008 s |
0.000009632 s |
1.05 |
actmtch / JaXPipe / cuda / PreRev |
0.000010144 s |
0.00000992 s |
1.02 |
actmtch / JaXPipe / cuda / PostRev |
0.00001024 s |
0.000009696 s |
1.06 |
actmtch / JaXPipe / cuda / BothRev |
0.000009984 s |
0.000009984 s |
1 |
actmtch / PartOpt / cuda / PreRev |
0.000010368 s |
0.000010112 s |
1.03 |
actmtch / PartOpt / cuda / PostRev |
0.000010272 s |
0.000009952 s |
1.03 |
actmtch / PartOpt / cuda / BothRev |
0.000010113 s |
0.00001024 s |
0.99 |
actmtch / IPartOpt / cuda / PreRev |
0.000009824 s |
0.000010112 s |
0.97 |
actmtch / IPartOpt / cuda / PostRev |
0.000010368 s |
0.000009727 s |
1.07 |
actmtch / IPartOpt / cuda / BothRev |
0.000010528 s |
0.0000096 s |
1.10 |
actmtch / HLOOpt / cuda / PreRev |
0.00001024 s |
0.000010688 s |
0.96 |
actmtch / HLOOpt / cuda / PostRev |
0.000010144 s |
0.000010528 s |
0.96 |
actmtch / HLOOpt / cuda / BothRev |
0.00000992 s |
0.000009727 s |
1.02 |
actmtch / DefOpt / cuda / PreRev |
0.000010144 s |
0.000010049 s |
1.01 |
actmtch / DefOpt / cuda / PostRev |
0.00001008 s |
0.000009696 s |
1.04 |
actmtch / DefOpt / cuda / BothRev |
0.00001024 s |
0.00001008 s |
1.02 |
actmtch / IDefOpt / cuda / PreRev |
0.00001056 s |
0.000010176 s |
1.04 |
actmtch / IDefOpt / cuda / PostRev |
0.00000992 s |
0.00001008 s |
0.98 |
actmtch / IDefOpt / cuda / BothRev |
0.000010304 s |
0.000010047 s |
1.03 |
actmtch / Jax / tpu / Primal |
5.638e-7 s |
5.965e-7 s |
0.95 |
actmtch / JaXPipe / tpu / Primal |
5.968500000000001e-7 s |
5.63475e-7 s |
1.06 |
actmtch / PartOpt / tpu / Primal |
5.639e-7 s |
5.968500000000001e-7 s |
0.94 |
actmtch / IPartOpt / tpu / Primal |
5.972749999999999e-7 s |
5.5225e-7 s |
1.08 |
actmtch / HLOOpt / tpu / Primal |
0.000002136925 s |
0.000002103725 s |
1.02 |
actmtch / DefOpt / tpu / Primal |
0.0000021504250000000003 s |
0.000002154625 s |
1.00 |
actmtch / IDefOpt / tpu / Primal |
0.00000213525 s |
0.0000021011750000000003 s |
1.02 |
actmtch / Jax / tpu / Forward |
0.000001251575 s |
0.000001207225 s |
1.04 |
actmtch / JaXPipe / tpu / Forward |
0.00000373705 s |
0.000003833475000000001 s |
0.97 |
actmtch / PartOpt / tpu / Forward |
0.000003938475 s |
0.0000039168 s |
1.01 |
actmtch / IPartOpt / tpu / Forward |
0.000003801825 s |
0.000003937025000000001 s |
0.97 |
actmtch / HLOOpt / tpu / Forward |
0.000003929675000000001 s |
0.000003939525 s |
1.00 |
actmtch / DefOpt / tpu / Forward |
0.00000380375 s |
0.000003927975 s |
0.97 |
actmtch / IDefOpt / tpu / Forward |
0.0000039313 s |
0.000003936375 s |
1.00 |
actmtch / Jax / tpu / BothRev |
0.0000016249250000000002 s |
0.0000016403750000000002 s |
0.99 |
actmtch / JaXPipe / tpu / PreRev |
0.00000348365 s |
0.000003475 s |
1.00 |
actmtch / JaXPipe / tpu / PostRev |
0.000001609025 s |
0.00000163465 s |
0.98 |
actmtch / JaXPipe / tpu / BothRev |
0.0000034667 s |
0.00000349725 s |
0.99 |
actmtch / PartOpt / tpu / PreRev |
0.000003421225 s |
0.0000034052 s |
1.00 |
actmtch / PartOpt / tpu / PostRev |
0.0000016362 s |
0.0000016022 s |
1.02 |
actmtch / PartOpt / tpu / BothRev |
0.0000034207749999999994 s |
0.0000034209750000000003 s |
1.00 |
actmtch / IPartOpt / tpu / PreRev |
0.00000346485 s |
0.0000034736 s |
1.00 |
actmtch / IPartOpt / tpu / PostRev |
0.000001595475 s |
0.000001655825 s |
0.96 |
actmtch / IPartOpt / tpu / BothRev |
0.000003485875 s |
0.0000034814 s |
1.00 |
actmtch / HLOOpt / tpu / PreRev |
0.000003432925 s |
0.000003481025 s |
0.99 |
actmtch / HLOOpt / tpu / PostRev |
0.00000345955 s |
0.00000342085 s |
1.01 |
actmtch / HLOOpt / tpu / BothRev |
0.000003434625 s |
0.000003482925 s |
0.99 |
actmtch / DefOpt / tpu / PreRev |
0.00000346555 s |
0.00000340395 s |
1.02 |
actmtch / DefOpt / tpu / PostRev |
0.0000033695 s |
0.000003402575 s |
0.99 |
actmtch / DefOpt / tpu / BothRev |
0.0000034749000000000004 s |
0.0000034213 s |
1.02 |
actmtch / IDefOpt / tpu / PreRev |
0.0000034312 s |
0.00000348275 s |
0.99 |
actmtch / IDefOpt / tpu / PostRev |
0.0000034561 s |
0.0000034287000000000003 s |
1.01 |
actmtch / IDefOpt / tpu / BothRev |
0.0000034297 s |
0.0000034788 s |
0.99 |
actmtch / Jax / cpu / Primal |
0.000013137 s |
0.00000742670001272927 s |
1.77 |
actmtch / JaXPipe / cpu / Primal |
0.000013234 s |
0.000007178099976954399 s |
1.84 |
actmtch / PartOpt / cpu / Primal |
0.000013296 s |
0.000008231920019170502 s |
1.62 |
actmtch / IPartOpt / cpu / Primal |
0.000013238 s |
0.000009108859985644812 s |
1.45 |
actmtch / HLOOpt / cpu / Primal |
0.000014009 s |
0.00000942116002079274 s |
1.49 |
actmtch / DefOpt / cpu / Primal |
0.000013985 s |
0.000009177840011034278 s |
1.52 |
actmtch / IDefOpt / cpu / Primal |
0.000013967 s |
0.000009169459972326876 s |
1.52 |
actmtch / Jax / cpu / Forward |
0.000018507 s |
0.000011727619985322234 s |
1.58 |
actmtch / JaXPipe / cpu / Forward |
0.000019765 s |
0.00001240557998244185 s |
1.59 |
actmtch / PartOpt / cpu / Forward |
0.000019136 s |
0.000012186899984953924 s |
1.57 |
actmtch / IPartOpt / cpu / Forward |
0.000019592 s |
0.00001277817995287478 s |
1.53 |
actmtch / HLOOpt / cpu / Forward |
0.000019669 s |
0.000013135259996488456 s |
1.50 |
actmtch / DefOpt / cpu / Forward |
0.000019432000000000003 s |
0.000012611259999175672 s |
1.54 |
actmtch / IDefOpt / cpu / Forward |
0.000019785 s |
0.000013058779995844815 s |
1.52 |
actmtch / Jax / cpu / BothRev |
0.000017578 s |
0.0000101748600081919 s |
1.73 |
actmtch / JaXPipe / cpu / PreRev |
0.000020096 s |
0.000012500760039984015 s |
1.61 |
actmtch / JaXPipe / cpu / PostRev |
0.000017406000000000002 s |
0.000011682659987855004 s |
1.49 |
actmtch / JaXPipe / cpu / BothRev |
0.000019236 s |
0.000013351459965633694 s |
1.44 |
actmtch / PartOpt / cpu / PreRev |
0.000019778 s |
0.00001237502001458779 s |
1.60 |
actmtch / PartOpt / cpu / PostRev |
0.000017527 s |
0.000010807039989231271 s |
1.62 |
actmtch / PartOpt / cpu / BothRev |
0.00001962 s |
0.000013357679927139543 s |
1.47 |
actmtch / IPartOpt / cpu / PreRev |
0.000019848 s |
0.000011974959961662535 s |
1.66 |
actmtch / IPartOpt / cpu / PostRev |
0.00001799 s |
0.000011647979999906963 s |
1.54 |
actmtch / IPartOpt / cpu / BothRev |
0.000019666 s |
0.000012888160035799956 s |
1.53 |
actmtch / HLOOpt / cpu / PreRev |
0.000019163 s |
0.000012809399968318758 s |
1.50 |
actmtch / HLOOpt / cpu / PostRev |
0.000019635 s |
0.000014683079989481484 s |
1.34 |
actmtch / HLOOpt / cpu / BothRev |
0.000019729 s |
0.000012941140003022156 s |
1.52 |
actmtch / DefOpt / cpu / PreRev |
0.000019244 s |
0.000012172299993835623 s |
1.58 |
actmtch / DefOpt / cpu / PostRev |
0.000019236 s |
0.0000126511599864898 s |
1.52 |
actmtch / DefOpt / cpu / BothRev |
0.000019168 s |
0.000012905660032629384 s |
1.49 |
actmtch / IDefOpt / cpu / PreRev |
0.000019785 s |
0.00001217844000166224 s |
1.62 |
actmtch / IDefOpt / cpu / PostRev |
0.000019378 s |
0.000012553719934658148 s |
1.54 |
actmtch / IDefOpt / cpu / BothRev |
0.000019814 s |
0.000012284119984542483 s |
1.61 |
actmtch / Jax / cpu / Primal |
0.000008999999999999999 s |
0.00000742670001272927 s |
1.21 |
actmtch / JaXPipe / cpu / Primal |
0.000008999999999999999 s |
0.000007178099976954399 s |
1.25 |
actmtch / PartOpt / cpu / Primal |
0.000008999999999999999 s |
0.000008231920019170502 s |
1.09 |
actmtch / IPartOpt / cpu / Primal |
0.000008999999999999999 s |
0.000009108859985644812 s |
0.99 |
actmtch / HLOOpt / cpu / Primal |
0.000008999999999999999 s |
0.00000942116002079274 s |
0.96 |
actmtch / DefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000009177840011034278 s |
0.98 |
actmtch / IDefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000009169459972326876 s |
0.98 |
actmtch / Jax / cpu / Forward |
0.000012 s |
0.000011727619985322234 s |
1.02 |
actmtch / JaXPipe / cpu / Forward |
0.000013 s |
0.00001240557998244185 s |
1.05 |
actmtch / PartOpt / cpu / Forward |
0.000013 s |
0.000012186899984953924 s |
1.07 |
actmtch / IPartOpt / cpu / Forward |
0.000013 s |
0.00001277817995287478 s |
1.02 |
actmtch / HLOOpt / cpu / Forward |
0.000013 s |
0.000013135259996488456 s |
0.99 |
actmtch / DefOpt / cpu / Forward |
0.000013 s |
0.000012611259999175672 s |
1.03 |
actmtch / IDefOpt / cpu / Forward |
0.000014 s |
0.000013058779995844815 s |
1.07 |
actmtch / Jax / cpu / BothRev |
0.000012 s |
0.0000101748600081919 s |
1.18 |
actmtch / JaXPipe / cpu / PreRev |
0.000013 s |
0.000012500760039984015 s |
1.04 |
actmtch / JaXPipe / cpu / PostRev |
0.000012 s |
0.000011682659987855004 s |
1.03 |
actmtch / JaXPipe / cpu / BothRev |
0.000013 s |
0.000013351459965633694 s |
0.97 |
actmtch / PartOpt / cpu / PreRev |
0.000012 s |
0.00001237502001458779 s |
0.97 |
actmtch / PartOpt / cpu / PostRev |
0.000012 s |
0.000010807039989231271 s |
1.11 |
actmtch / PartOpt / cpu / BothRev |
0.000014 s |
0.000013357679927139543 s |
1.05 |
actmtch / IPartOpt / cpu / PreRev |
0.000014 s |
0.000011974959961662535 s |
1.17 |
actmtch / IPartOpt / cpu / PostRev |
0.000012 s |
0.000011647979999906963 s |
1.03 |
actmtch / IPartOpt / cpu / BothRev |
0.000013 s |
0.000012888160035799956 s |
1.01 |
actmtch / HLOOpt / cpu / PreRev |
0.000013 s |
0.000012809399968318758 s |
1.01 |
actmtch / HLOOpt / cpu / PostRev |
0.000014 s |
0.000014683079989481484 s |
0.95 |
actmtch / HLOOpt / cpu / BothRev |
0.000013 s |
0.000012941140003022156 s |
1.00 |
actmtch / DefOpt / cpu / PreRev |
0.000012 s |
0.000012172299993835623 s |
0.99 |
actmtch / DefOpt / cpu / PostRev |
0.000013 s |
0.0000126511599864898 s |
1.03 |
actmtch / DefOpt / cpu / BothRev |
0.000013 s |
0.000012905660032629384 s |
1.01 |
actmtch / IDefOpt / cpu / PreRev |
0.000013 s |
0.00001217844000166224 s |
1.07 |
actmtch / IDefOpt / cpu / PostRev |
0.000014 s |
0.000012553719934658148 s |
1.12 |
actmtch / IDefOpt / cpu / BothRev |
0.000013 s |
0.000012284119984542483 s |
1.06 |
add_one / Jax / cpu / Primal |
0.000006606699989788467 s |
0.000007734440014246502 s |
0.85 |
add_one / JaXPipe / cpu / Primal |
0.000008377960020879983 s |
0.000007177039997259271 s |
1.17 |
add_one / PartOpt / cpu / Primal |
0.000007127599983505206 s |
0.000007244479984365171 s |
0.98 |
add_one / IPartOpt / cpu / Primal |
0.00000716028001079394 s |
0.000007930979982120335 s |
0.90 |
add_one / HLOOpt / cpu / Primal |
0.0000070212200262176335 s |
0.00000762009998652502 s |
0.92 |
add_one / DefOpt / cpu / Primal |
0.000006434580000131973 s |
0.000007669920023545274 s |
0.84 |
add_one / IDefOpt / cpu / Primal |
0.000006417139984478127 s |
0.000007121160024325945 s |
0.90 |
add_one / Jax / cpu / Forward |
0.000009672160003901807 s |
0.000011104940058430656 s |
0.87 |
add_one / JaXPipe / cpu / Forward |
0.000009569960011504007 s |
0.00001077120000445575 s |
0.89 |
add_one / PartOpt / cpu / Forward |
0.000009811939953578986 s |
0.000010968379992846168 s |
0.89 |
add_one / IPartOpt / cpu / Forward |
0.000009472199981246376 s |
0.000011612179969233694 s |
0.82 |
add_one / HLOOpt / cpu / Forward |
0.000009871639986158695 s |
0.000010922199990091033 s |
0.90 |
add_one / DefOpt / cpu / Forward |
0.000009985140022763516 s |
0.000011284179972790298 s |
0.88 |
add_one / IDefOpt / cpu / Forward |
0.000009580040032233228 s |
0.000010938719979094458 s |
0.88 |
add_one / Jax / cpu / BothRev |
0.000011034779990950485 s |
0.000012893459916085705 s |
0.86 |
add_one / JaXPipe / cpu / PreRev |
0.000011440239995863522 s |
0.000012953139976161765 s |
0.88 |
add_one / JaXPipe / cpu / PostRev |
0.000011649839998426614 s |
0.000013293079982759082 s |
0.88 |
add_one / JaXPipe / cpu / BothRev |
0.0000110355999913736 s |
0.000014024859983692296 s |
0.79 |
add_one / PartOpt / cpu / PreRev |
0.000011522860022523672 s |
0.00001265406001039082 s |
0.91 |
add_one / PartOpt / cpu / PostRev |
0.00001319560000411002 s |
0.000013283080015753512 s |
0.99 |
add_one / PartOpt / cpu / BothRev |
0.00001143308007158339 s |
0.00001378497997393424 s |
0.83 |
add_one / IPartOpt / cpu / PreRev |
0.000011201979959878373 s |
0.000013247099986983811 s |
0.85 |
add_one / IPartOpt / cpu / PostRev |
0.000011328259970468937 s |
0.00001345441994999419 s |
0.84 |
add_one / IPartOpt / cpu / BothRev |
0.000011376800021025702 s |
0.000013223599971752264 s |
0.86 |
add_one / HLOOpt / cpu / PreRev |
0.00001149518007878214 s |
0.00001295961996220285 s |
0.89 |
add_one / HLOOpt / cpu / PostRev |
0.000011727179989975411 s |
0.000015428020005856525 s |
0.76 |
add_one / HLOOpt / cpu / BothRev |
0.000011205900000277324 s |
0.00001350904002720199 s |
0.83 |
add_one / DefOpt / cpu / PreRev |
0.000011422900015531923 s |
0.000012625260042113953 s |
0.90 |
add_one / DefOpt / cpu / PostRev |
0.000011725759986802586 s |
0.000013961339964225773 s |
0.84 |
add_one / DefOpt / cpu / BothRev |
0.000011595240011956776 s |
0.000013434940001388895 s |
0.86 |
add_one / IDefOpt / cpu / PreRev |
0.000011602579988903016 s |
0.00001282082000216178 s |
0.90 |
add_one / IDefOpt / cpu / PostRev |
0.000011377459977666148 s |
0.000013155759997971472 s |
0.86 |
add_one / IDefOpt / cpu / BothRev |
0.000011419040010878234 s |
0.00001394135998452839 s |
0.82 |
add_one / Jax / cuda / Primal |
0.0000019200000000000003 s |
0.000001919 s |
1.00 |
add_one / JaXPipe / cuda / Primal |
0.0000019200000000000003 s |
0.000001919 s |
1.00 |
add_one / PartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000019200000000000003 s |
1 |
add_one / IPartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000001919 s |
1.00 |
add_one / HLOOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000001919 s |
1.00 |
add_one / DefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000001919 s |
1.00 |
add_one / IDefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000019200000000000003 s |
1 |
add_one / Jax / cuda / Forward |
0.000009952 s |
0.000014623 s |
0.68 |
add_one / JaXPipe / cuda / Forward |
0.000010656 s |
0.000009408 s |
1.13 |
add_one / PartOpt / cuda / Forward |
0.000010271 s |
0.000010144 s |
1.01 |
add_one / IPartOpt / cuda / Forward |
0.000010112 s |
0.000010176 s |
0.99 |
add_one / HLOOpt / cuda / Forward |
0.000010208 s |
0.00000976 s |
1.05 |
add_one / DefOpt / cuda / Forward |
0.000010112 s |
0.000009696 s |
1.04 |
add_one / IDefOpt / cuda / Forward |
0.000010432 s |
0.000010144 s |
1.03 |
add_one / Jax / cuda / BothRev |
0.000025216 s |
0.000024895 s |
1.01 |
add_one / JaXPipe / cuda / PreRev |
0.000025344 s |
0.000026847 s |
0.94 |
add_one / JaXPipe / cuda / PostRev |
0.0000256 s |
0.00002496 s |
1.03 |
add_one / JaXPipe / cuda / BothRev |
0.00002544 s |
0.000024639 s |
1.03 |
add_one / PartOpt / cuda / PreRev |
0.00002656 s |
0.000024576 s |
1.08 |
add_one / PartOpt / cuda / PostRev |
0.000024992 s |
0.00002448 s |
1.02 |
add_one / PartOpt / cuda / BothRev |
0.000025152 s |
0.000024768 s |
1.02 |
add_one / IPartOpt / cuda / PreRev |
0.000025728 s |
0.000024896 s |
1.03 |
add_one / IPartOpt / cuda / PostRev |
0.000025249 s |
0.000025024 s |
1.01 |
add_one / IPartOpt / cuda / BothRev |
0.00002496 s |
0.000025024 s |
1.00 |
add_one / HLOOpt / cuda / PreRev |
0.00002592 s |
0.000038112 s |
0.68 |
add_one / HLOOpt / cuda / PostRev |
0.000025344 s |
0.000028256 s |
0.90 |
add_one / HLOOpt / cuda / BothRev |
0.000024576 s |
0.00002816 s |
0.87 |
add_one / DefOpt / cuda / PreRev |
0.000025216 s |
0.000024991 s |
1.01 |
add_one / DefOpt / cuda / PostRev |
0.000025792 s |
0.000024448 s |
1.05 |
add_one / DefOpt / cuda / BothRev |
0.000025728 s |
0.000024576 s |
1.05 |
add_one / IDefOpt / cuda / PreRev |
0.00002496 s |
0.000025055 s |
1.00 |
add_one / IDefOpt / cuda / PostRev |
0.000025024 s |
0.000024735 s |
1.01 |
add_one / IDefOpt / cuda / BothRev |
0.000025248 s |
0.000032608 s |
0.77 |
add_one / Jax / tpu / Primal |
0.000001424275 s |
0.0000014049 s |
1.01 |
add_one / JaXPipe / tpu / Primal |
0.000001441675 s |
0.0000014201 s |
1.02 |
add_one / PartOpt / tpu / Primal |
0.000001412875 s |
0.0000014039999999999998 s |
1.01 |
add_one / IPartOpt / tpu / Primal |
0.000001423275 s |
0.0000014377750000000002 s |
0.99 |
add_one / HLOOpt / tpu / Primal |
0.00000141655 s |
0.000001435675 s |
0.99 |
add_one / DefOpt / tpu / Primal |
0.000001425325 s |
0.0000014016500000000002 s |
1.02 |
add_one / IDefOpt / tpu / Primal |
0.0000014223250000000002 s |
0.00000144195 s |
0.99 |
add_one / Jax / tpu / Forward |
0.000001879675 s |
0.000001836275 s |
1.02 |
add_one / JaXPipe / tpu / Forward |
0.0000018313 s |
0.000001850925 s |
0.99 |
add_one / PartOpt / tpu / Forward |
0.000001880175 s |
0.00000184635 s |
1.02 |
add_one / IPartOpt / tpu / Forward |
0.00000183445 s |
0.000001853875 s |
0.99 |
add_one / HLOOpt / tpu / Forward |
0.0000018857 s |
0.0000018559 s |
1.02 |
add_one / DefOpt / tpu / Forward |
0.000001833725 s |
0.000001841125 s |
1.00 |
add_one / IDefOpt / tpu / Forward |
0.000001879475 s |
0.0000018604 s |
1.01 |
add_one / Jax / tpu / BothRev |
0.0000022308 s |
0.000002232875 s |
1.00 |
add_one / JaXPipe / tpu / PreRev |
0.00000225905 s |
0.0000022337250000000004 s |
1.01 |
add_one / JaXPipe / tpu / PostRev |
0.0000022284750000000003 s |
0.000002251875 s |
0.99 |
add_one / JaXPipe / tpu / BothRev |
0.000002272525 s |
0.000002245775 s |
1.01 |
add_one / PartOpt / tpu / PreRev |
0.000002228875 s |
0.000002236475 s |
1.00 |
add_one / PartOpt / tpu / PostRev |
0.000002264975 s |
0.000002253325 s |
1.01 |
add_one / PartOpt / tpu / BothRev |
0.0000022306000000000003 s |
0.0000022447 s |
0.99 |
add_one / IPartOpt / tpu / PreRev |
0.000002271825 s |
0.0000022506750000000003 s |
1.01 |
add_one / IPartOpt / tpu / PostRev |
0.000002232375 s |
0.00000225235 s |
0.99 |
add_one / IPartOpt / tpu / BothRev |
0.000002264225 s |
0.0000022373 s |
1.01 |
add_one / HLOOpt / tpu / PreRev |
0.00000223035 s |
0.0000022363 s |
1.00 |
add_one / HLOOpt / tpu / PostRev |
0.000002266025 s |
0.00000224635 s |
1.01 |
add_one / HLOOpt / tpu / BothRev |
0.0000022334 s |
0.00000224005 s |
1.00 |
add_one / DefOpt / tpu / PreRev |
0.000002270475 s |
0.000002243875 s |
1.01 |
add_one / DefOpt / tpu / PostRev |
0.000002223475 s |
0.000002236525 s |
0.99 |
add_one / DefOpt / tpu / BothRev |
0.000002262375 s |
0.000002253425 s |
1.00 |
add_one / IDefOpt / tpu / PreRev |
0.0000022244000000000003 s |
0.0000022355 s |
1.00 |
add_one / IDefOpt / tpu / PostRev |
0.000002266825 s |
0.00000224675 s |
1.01 |
add_one / IDefOpt / tpu / BothRev |
0.00000223285 s |
0.00000224285 s |
1.00 |
add_one / Jax / cpu / Primal |
0.000013325 s |
0.000007734440014246502 s |
1.72 |
add_one / JaXPipe / cpu / Primal |
0.000013027 s |
0.000007177039997259271 s |
1.82 |
add_one / PartOpt / cpu / Primal |
0.000012988 s |
0.000007244479984365171 s |
1.79 |
add_one / IPartOpt / cpu / Primal |
0.000012866 s |
0.000007930979982120335 s |
1.62 |
add_one / HLOOpt / cpu / Primal |
0.000012901 s |
0.00000762009998652502 s |
1.69 |
add_one / DefOpt / cpu / Primal |
0.00001315 s |
0.000007669920023545274 s |
1.71 |
add_one / IDefOpt / cpu / Primal |
0.000013224 s |
0.000007121160024325945 s |
1.86 |
add_one / Jax / cpu / Forward |
0.000017873 s |
0.000011104940058430656 s |
1.61 |
add_one / JaXPipe / cpu / Forward |
0.000017669 s |
0.00001077120000445575 s |
1.64 |
add_one / PartOpt / cpu / Forward |
0.000018088 s |
0.000010968379992846168 s |
1.65 |
add_one / IPartOpt / cpu / Forward |
0.00001743 s |
0.000011612179969233694 s |
1.50 |
add_one / HLOOpt / cpu / Forward |
0.000017618000000000003 s |
0.000010922199990091033 s |
1.61 |
add_one / DefOpt / cpu / Forward |
0.000017827 s |
0.000011284179972790298 s |
1.58 |
add_one / IDefOpt / cpu / Forward |
0.000017697 s |
0.000010938719979094458 s |
1.62 |
add_one / Jax / cpu / BothRev |
0.000019962 s |
0.000012893459916085705 s |
1.55 |
add_one / JaXPipe / cpu / PreRev |
0.000019966 s |
0.000012953139976161765 s |
1.54 |
add_one / JaXPipe / cpu / PostRev |
0.000019912 s |
0.000013293079982759082 s |
1.50 |
add_one / JaXPipe / cpu / BothRev |
0.000019691 s |
0.000014024859983692296 s |
1.40 |
add_one / PartOpt / cpu / PreRev |
0.000019730000000000003 s |
0.00001265406001039082 s |
1.56 |
add_one / PartOpt / cpu / PostRev |
0.000019977 s |
0.000013283080015753512 s |
1.50 |
add_one / PartOpt / cpu / BothRev |
0.000019856 s |
0.00001378497997393424 s |
1.44 |
add_one / IPartOpt / cpu / PreRev |
0.000020147 s |
0.000013247099986983811 s |
1.52 |
add_one / IPartOpt / cpu / PostRev |
0.000019713000000000003 s |
0.00001345441994999419 s |
1.47 |
add_one / IPartOpt / cpu / BothRev |
0.00001998 s |
0.000013223599971752264 s |
1.51 |
add_one / HLOOpt / cpu / PreRev |
0.00001957 s |
0.00001295961996220285 s |
1.51 |
add_one / HLOOpt / cpu / PostRev |
0.000019689 s |
0.000015428020005856525 s |
1.28 |
add_one / HLOOpt / cpu / BothRev |
0.000019627 s |
0.00001350904002720199 s |
1.45 |
add_one / DefOpt / cpu / PreRev |
0.00001971 s |
0.000012625260042113953 s |
1.56 |
add_one / DefOpt / cpu / PostRev |
0.000019314 s |
0.000013961339964225773 s |
1.38 |
add_one / DefOpt / cpu / BothRev |
0.000019689 s |
0.000013434940001388895 s |
1.47 |
add_one / IDefOpt / cpu / PreRev |
0.000019308 s |
0.00001282082000216178 s |
1.51 |
add_one / IDefOpt / cpu / PostRev |
0.000019743 s |
0.000013155759997971472 s |
1.50 |
add_one / IDefOpt / cpu / BothRev |
0.000019808 s |
0.00001394135998452839 s |
1.42 |
add_one / Jax / cpu / Primal |
0.000008999999999999999 s |
0.000007734440014246502 s |
1.16 |
add_one / JaXPipe / cpu / Primal |
0.000008999999999999999 s |
0.000007177039997259271 s |
1.25 |
add_one / PartOpt / cpu / Primal |
0.000008999999999999999 s |
0.000007244479984365171 s |
1.24 |
add_one / IPartOpt / cpu / Primal |
0.000008999999999999999 s |
0.000007930979982120335 s |
1.13 |
add_one / HLOOpt / cpu / Primal |
0.000008999999999999999 s |
0.00000762009998652502 s |
1.18 |
add_one / DefOpt / cpu / Primal |
0.000008 s |
0.000007669920023545274 s |
1.04 |
add_one / IDefOpt / cpu / Primal |
0.000008 s |
0.000007121160024325945 s |
1.12 |
add_one / Jax / cpu / Forward |
0.000012 s |
0.000011104940058430656 s |
1.08 |
add_one / JaXPipe / cpu / Forward |
0.000011 s |
0.00001077120000445575 s |
1.02 |
add_one / PartOpt / cpu / Forward |
0.000012 s |
0.000010968379992846168 s |
1.09 |
add_one / IPartOpt / cpu / Forward |
0.000011 s |
0.000011612179969233694 s |
0.95 |
add_one / HLOOpt / cpu / Forward |
0.000011 s |
0.000010922199990091033 s |
1.01 |
add_one / DefOpt / cpu / Forward |
0.000011 s |
0.000011284179972790298 s |
0.97 |
add_one / IDefOpt / cpu / Forward |
0.000011 s |
0.000010938719979094458 s |
1.01 |
add_one / Jax / cpu / BothRev |
0.000013 s |
0.000012893459916085705 s |
1.01 |
add_one / JaXPipe / cpu / PreRev |
0.000014 s |
0.000012953139976161765 s |
1.08 |
add_one / JaXPipe / cpu / PostRev |
0.000013 s |
0.000013293079982759082 s |
0.98 |
add_one / JaXPipe / cpu / BothRev |
0.000013 s |
0.000014024859983692296 s |
0.93 |
add_one / PartOpt / cpu / PreRev |
0.000014 s |
0.00001265406001039082 s |
1.11 |
add_one / PartOpt / cpu / PostRev |
0.000014 s |
0.000013283080015753512 s |
1.05 |
add_one / PartOpt / cpu / BothRev |
0.000013 s |
0.00001378497997393424 s |
0.94 |
add_one / IPartOpt / cpu / PreRev |
0.000014 s |
0.000013247099986983811 s |
1.06 |
add_one / IPartOpt / cpu / PostRev |
0.000014 s |
0.00001345441994999419 s |
1.04 |
add_one / IPartOpt / cpu / BothRev |
0.000014 s |
0.000013223599971752264 s |
1.06 |
add_one / HLOOpt / cpu / PreRev |
0.000013 s |
0.00001295961996220285 s |
1.00 |
add_one / HLOOpt / cpu / PostRev |
0.000013 s |
0.000015428020005856525 s |
0.84 |
add_one / HLOOpt / cpu / BothRev |
0.000014 s |
0.00001350904002720199 s |
1.04 |
add_one / DefOpt / cpu / PreRev |
0.000014 s |
0.000012625260042113953 s |
1.11 |
add_one / DefOpt / cpu / PostRev |
0.000014 s |
0.000013961339964225773 s |
1.00 |
add_one / DefOpt / cpu / BothRev |
0.000014 s |
0.000013434940001388895 s |
1.04 |
add_one / IDefOpt / cpu / PreRev |
0.000044 s |
0.00001282082000216178 s |
3.43 |
add_one / IDefOpt / cpu / PostRev |
0.000014 s |
0.000013155759997971472 s |
1.06 |
add_one / IDefOpt / cpu / BothRev |
0.000014 s |
0.00001394135998452839 s |
1.00 |
add_two / Jax / cpu / Primal |
0.000007644019970030058 s |
0.000007353320033871569 s |
1.04 |
add_two / JaXPipe / cpu / Primal |
0.000007238519956445089 s |
0.000007506659994760412 s |
0.96 |
add_two / PartOpt / cpu / Primal |
0.000007344160003412981 s |
0.000007316919982258696 s |
1.00 |
add_two / IPartOpt / cpu / Primal |
0.000006778479992135545 s |
0.000007347219980147201 s |
0.92 |
add_two / HLOOpt / cpu / Primal |
0.000006918500012034201 s |
0.000007573599987154012 s |
0.91 |
add_two / DefOpt / cpu / Primal |
0.00000688921999426384 s |
0.0000074251600290153874 s |
0.93 |
add_two / IDefOpt / cpu / Primal |
0.000006743880012436421 s |
0.000006994880013735383 s |
0.96 |
add_two / Jax / cpu / Forward |
0.00001017954000417376 s |
0.000011223360015719663 s |
0.91 |
add_two / JaXPipe / cpu / Forward |
0.000010253500022372464 s |
0.000010793679984999472 s |
0.95 |
add_two / PartOpt / cpu / Forward |
0.000010622900017551728 s |
0.000011552759970072657 s |
0.92 |
add_two / IPartOpt / cpu / Forward |
0.000010425280015624594 s |
0.000011149400006615904 s |
0.94 |
add_two / HLOOpt / cpu / Forward |
0.00001059259999237838 s |
0.00001163689995337336 s |
0.91 |
add_two / DefOpt / cpu / Forward |
0.000010422440000183996 s |
0.000010866600005101646 s |
0.96 |
add_two / IDefOpt / cpu / Forward |
0.00001001818000986532 s |
0.00001085120003153861 s |
0.92 |
add_two / Jax / cpu / BothRev |
0.000014424779992623373 s |
0.000016008080037863693 s |
0.90 |
add_two / JaXPipe / cpu / PreRev |
0.000013913600087107623 s |
0.00001607411998520547 s |
0.87 |
add_two / JaXPipe / cpu / PostRev |
0.00001373355998111947 s |
0.000015767160030009108 s |
0.87 |
add_two / JaXPipe / cpu / BothRev |
0.000013714719998461076 s |
0.00001591828001437534 s |
0.86 |
add_two / PartOpt / cpu / PreRev |
0.000013927040008638869 s |
0.000016130079948197818 s |
0.86 |
add_two / PartOpt / cpu / PostRev |
0.000015251899976647107 s |
0.00001545496003018343 s |
0.99 |
add_two / PartOpt / cpu / BothRev |
0.000013967240001875324 s |
0.000015658540050935698 s |
0.89 |
add_two / IPartOpt / cpu / PreRev |
0.000014473480032393128 s |
0.000015700720014137913 s |
0.92 |
add_two / IPartOpt / cpu / PostRev |
0.00001346009996268549 s |
0.000015940499997668668 s |
0.84 |
add_two / IPartOpt / cpu / BothRev |
0.000013677539991476806 s |
0.000016176559984160122 s |
0.85 |
add_two / HLOOpt / cpu / PreRev |
0.000013977800035718246 s |
0.000016023040034269796 s |
0.87 |
add_two / HLOOpt / cpu / PostRev |
0.000014047619979464798 s |
0.00001724719999401714 s |
0.81 |
add_two / HLOOpt / cpu / BothRev |
0.000013694560011572322 s |
0.000015348320039265674 s |
0.89 |
add_two / DefOpt / cpu / PreRev |
0.000014618359964515548 s |
0.00001615454000784666 s |
0.90 |
add_two / DefOpt / cpu / PostRev |
0.000013513180037989514 s |
0.000016489659992657833 s |
0.82 |
add_two / DefOpt / cpu / BothRev |
0.000013663840018125484 s |
0.00001642914002331963 s |
0.83 |
add_two / IDefOpt / cpu / PreRev |
0.000014010159957251744 s |
0.00001574142003846646 s |
0.89 |
add_two / IDefOpt / cpu / PostRev |
0.000013709559980270569 s |
0.000016233939986705083 s |
0.84 |
add_two / IDefOpt / cpu / BothRev |
0.000013408219956545508 s |
0.000016458300024169148 s |
0.81 |
add_two / Jax / cuda / Primal |
0.0000019200000000000003 s |
0.000001887 s |
1.02 |
add_two / JaXPipe / cuda / Primal |
0.0000019200000000000003 s |
0.000001887 s |
1.02 |
add_two / PartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000001888 s |
1.02 |
add_two / IPartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000001887 s |
1.02 |
add_two / HLOOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000001887 s |
1.02 |
add_two / DefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000001888 s |
1.02 |
add_two / IDefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000001887 s |
1.02 |
add_two / Jax / cuda / Forward |
0.000009536 s |
0.000009792 s |
0.97 |
add_two / JaXPipe / cuda / Forward |
0.000009632 s |
0.000009632 s |
1 |
add_two / PartOpt / cuda / Forward |
0.000009952 s |
0.00000992 s |
1.00 |
add_two / IPartOpt / cuda / Forward |
0.000009952 s |
0.000009952 s |
1 |
add_two / HLOOpt / cuda / Forward |
0.000009792 s |
0.000009472 s |
1.03 |
add_two / DefOpt / cuda / Forward |
0.000009856 s |
0.000009408 s |
1.05 |
add_two / IDefOpt / cuda / Forward |
0.000009983 s |
0.000009824 s |
1.02 |
add_two / Jax / cuda / BothRev |
0.000032127999999999995 s |
0.000032319 s |
0.99 |
add_two / JaXPipe / cuda / PreRev |
0.000032991 s |
0.000031199000000000004 s |
1.06 |
add_two / JaXPipe / cuda / PostRev |
0.000032416 s |
0.000031744 s |
1.02 |
add_two / JaXPipe / cuda / BothRev |
0.000031968 s |
0.000031711 s |
1.01 |
add_two / PartOpt / cuda / PreRev |
0.000033729 s |
0.000031808000000000004 s |
1.06 |
add_two / PartOpt / cuda / PostRev |
0.000031904000000000005 s |
0.000031584 s |
1.01 |
add_two / PartOpt / cuda / BothRev |
0.000032512 s |
0.000031585 s |
1.03 |
add_two / IPartOpt / cuda / PreRev |
0.000032864 s |
0.000031455 s |
1.04 |
add_two / IPartOpt / cuda / PostRev |
0.000032321000000000004 s |
0.000031808000000000004 s |
1.02 |
add_two / IPartOpt / cuda / BothRev |
0.000032416 s |
0.000031872 s |
1.02 |
add_two / HLOOpt / cuda / PreRev |
0.00003232 s |
0.000032287000000000004 s |
1.00 |
add_two / HLOOpt / cuda / PostRev |
0.000032704 s |
0.000032064 s |
1.02 |
add_two / HLOOpt / cuda / BothRev |
0.000032352 s |
0.000032032 s |
1.01 |
add_two / DefOpt / cuda / PreRev |
0.000033024 s |
0.000031808000000000004 s |
1.04 |
add_two / DefOpt / cuda / PostRev |
0.000032736 s |
0.00003232 s |
1.01 |
add_two / DefOpt / cuda / BothRev |
0.000032191 s |
0.000031968 s |
1.01 |
add_two / IDefOpt / cuda / PreRev |
0.000032416 s |
0.000032672 s |
0.99 |
add_two / IDefOpt / cuda / PostRev |
0.000032767999999999995 s |
0.000032352 s |
1.01 |
add_two / IDefOpt / cuda / BothRev |
0.00003264 s |
0.000032736 s |
1.00 |
add_two / Jax / tpu / Primal |
0.0000013927999999999998 s |
0.0000014727 s |
0.95 |
add_two / JaXPipe / tpu / Primal |
0.00000144465 s |
0.000001433525 s |
1.01 |
add_two / PartOpt / tpu / Primal |
0.00000140195 s |
0.0000014754249999999995 s |
0.95 |
add_two / IPartOpt / tpu / Primal |
0.00000145215 s |
0.0000014310999999999995 s |
1.01 |
add_two / HLOOpt / tpu / Primal |
0.0000014074 s |
0.00000142615 s |
0.99 |
add_two / DefOpt / tpu / Primal |
0.000001467825 s |
0.000001473875 s |
1.00 |
add_two / IDefOpt / tpu / Primal |
0.00000139605 s |
0.0000014331749999999998 s |
0.97 |
add_two / Jax / tpu / Forward |
0.000001816825 s |
0.000001836725 s |
0.99 |
add_two / JaXPipe / tpu / Forward |
0.000001799525 s |
0.000001824325 s |
0.99 |
add_two / PartOpt / tpu / Forward |
0.000001808975 s |
0.000001831475 s |
0.99 |
add_two / IPartOpt / tpu / Forward |
0.0000017883 s |
0.00000183205 s |
0.98 |
add_two / HLOOpt / tpu / Forward |
0.00000180355 s |
0.000001826375 s |
0.99 |
add_two / DefOpt / tpu / Forward |
0.000001789675 s |
0.00000183725 s |
0.97 |
add_two / IDefOpt / tpu / Forward |
0.000001808725 s |
0.000001828525 s |
0.99 |
add_two / Jax / tpu / BothRev |
0.000002796125 s |
0.0000027576 s |
1.01 |
add_two / JaXPipe / tpu / PreRev |
0.000002723475 s |
0.000002843875 s |
0.96 |
add_two / JaXPipe / tpu / PostRev |
0.000002804925 s |
0.00000276105 s |
1.02 |
add_two / JaXPipe / tpu / BothRev |
0.00000272715 s |
0.0000028427 s |
0.96 |
add_two / PartOpt / tpu / PreRev |
0.0000028038500000000003 s |
0.0000027584750000000003 s |
1.02 |
add_two / PartOpt / tpu / PostRev |
0.000002719175 s |
0.0000028425 s |
0.96 |
add_two / PartOpt / tpu / BothRev |
0.0000027927000000000004 s |
0.0000027695 s |
1.01 |
add_two / IPartOpt / tpu / PreRev |
0.0000027214000000000003 s |
0.00000285875 s |
0.95 |
add_two / IPartOpt / tpu / PostRev |
0.0000027944000000000003 s |
0.00000276865 s |
1.01 |
add_two / IPartOpt / tpu / BothRev |
0.0000027183750000000005 s |
0.000002844875 s |
0.96 |
add_two / HLOOpt / tpu / PreRev |
0.00000279995 s |
0.000002844375 s |
0.98 |
add_two / HLOOpt / tpu / PostRev |
0.000002714575 s |
0.000002748775 s |
0.99 |
add_two / HLOOpt / tpu / BothRev |
0.00000279065 s |
0.0000028381250000000005 s |
0.98 |
add_two / DefOpt / tpu / PreRev |
0.0000027304 s |
0.0000027608 s |
0.99 |
add_two / DefOpt / tpu / PostRev |
0.000002803075 s |
0.00000283915 s |
0.99 |
add_two / DefOpt / tpu / BothRev |
0.000002716475 s |
0.0000027521250000000004 s |
0.99 |
add_two / IDefOpt / tpu / PreRev |
0.0000027982750000000003 s |
0.0000028433000000000004 s |
0.98 |
add_two / IDefOpt / tpu / PostRev |
0.0000027234000000000005 s |
0.00000276145 s |
0.99 |
add_two / IDefOpt / tpu / BothRev |
0.0000027907500000000003 s |
0.0000028359250000000003 s |
0.98 |
add_two / Jax / cpu / Primal |
0.000013507999999999998 s |
0.000007353320033871569 s |
1.84 |
add_two / JaXPipe / cpu / Primal |
0.000013455 s |
0.000007506659994760412 s |
1.79 |
add_two / PartOpt / cpu / Primal |
0.000013432 s |
0.000007316919982258696 s |
1.84 |
add_two / IPartOpt / cpu / Primal |
0.000013427 s |
0.000007347219980147201 s |
1.83 |
add_two / HLOOpt / cpu / Primal |
0.000013521 s |
0.000007573599987154012 s |
1.79 |
add_two / DefOpt / cpu / Primal |
0.000013296 s |
0.0000074251600290153874 s |
1.79 |
add_two / IDefOpt / cpu / Primal |
0.000021233 s |
0.000006994880013735383 s |
3.04 |
add_two / Jax / cpu / Forward |
0.000018294 s |
0.000011223360015719663 s |
1.63 |
add_two / JaXPipe / cpu / Forward |
0.000018158 s |
0.000010793679984999472 s |
1.68 |
add_two / PartOpt / cpu / Forward |
0.000018047 s |
0.000011552759970072657 s |
1.56 |
add_two / IPartOpt / cpu / Forward |
0.000018206 s |
0.000011149400006615904 s |
1.63 |
add_two / HLOOpt / cpu / Forward |
0.000018037 s |
0.00001163689995337336 s |
1.55 |
add_two / DefOpt / cpu / Forward |
0.000018762 s |
0.000010866600005101646 s |
1.73 |
add_two / IDefOpt / cpu / Forward |
0.000017760999999999998 s |
0.00001085120003153861 s |
1.64 |
add_two / Jax / cpu / BothRev |
0.000023998 s |
0.000016008080037863693 s |
1.50 |
add_two / JaXPipe / cpu / PreRev |
0.000023729 s |
0.00001607411998520547 s |
1.48 |
add_two / JaXPipe / cpu / PostRev |
0.000023352000000000003 s |
0.000015767160030009108 s |
1.48 |
add_two / JaXPipe / cpu / BothRev |
0.00002295 s |
0.00001591828001437534 s |
1.44 |
add_two / PartOpt / cpu / PreRev |
0.000023331 s |
0.000016130079948197818 s |
1.45 |
add_two / PartOpt / cpu / PostRev |
0.000023832 s |
0.00001545496003018343 s |
1.54 |
add_two / PartOpt / cpu / BothRev |
0.000023423 s |
0.000015658540050935698 s |
1.50 |
add_two / IPartOpt / cpu / PreRev |
0.000023291 s |
0.000015700720014137913 s |
1.48 |
add_two / IPartOpt / cpu / PostRev |
0.000023461 s |
0.000015940499997668668 s |
1.47 |
add_two / IPartOpt / cpu / BothRev |
0.000023413 s |
0.000016176559984160122 s |
1.45 |
add_two / HLOOpt / cpu / PreRev |
0.000023304 s |
0.000016023040034269796 s |
1.45 |
add_two / HLOOpt / cpu / PostRev |
0.000023477 s |
0.00001724719999401714 s |
1.36 |
add_two / HLOOpt / cpu / BothRev |
0.000023565 s |
0.000015348320039265674 s |
1.54 |
add_two / DefOpt / cpu / PreRev |
0.00002354 s |
0.00001615454000784666 s |
1.46 |
add_two / DefOpt / cpu / PostRev |
0.000023242 s |
0.000016489659992657833 s |
1.41 |
add_two / DefOpt / cpu / BothRev |
0.000023282 s |
0.00001642914002331963 s |
1.42 |
add_two / IDefOpt / cpu / PreRev |
0.000023095 s |
0.00001574142003846646 s |
1.47 |
add_two / IDefOpt / cpu / PostRev |
0.00002309 s |
0.000016233939986705083 s |
1.42 |
add_two / IDefOpt / cpu / BothRev |
0.000023583 s |
0.000016458300024169148 s |
1.43 |
add_two / Jax / cpu / Primal |
0.00001 s |
0.000007353320033871569 s |
1.36 |
add_two / JaXPipe / cpu / Primal |
0.000008999999999999999 s |
0.000007506659994760412 s |
1.20 |
add_two / PartOpt / cpu / Primal |
0.000008999999999999999 s |
0.000007316919982258696 s |
1.23 |
add_two / IPartOpt / cpu / Primal |
0.000008999999999999999 s |
0.000007347219980147201 s |
1.22 |
add_two / HLOOpt / cpu / Primal |
0.000008999999999999999 s |
0.000007573599987154012 s |
1.19 |
add_two / DefOpt / cpu / Primal |
0.000008999999999999999 s |
0.0000074251600290153874 s |
1.21 |
add_two / IDefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000006994880013735383 s |
1.29 |
add_two / Jax / cpu / Forward |
0.000039 s |
0.000011223360015719663 s |
3.47 |
add_two / JaXPipe / cpu / Forward |
0.000012 s |
0.000010793679984999472 s |
1.11 |
add_two / PartOpt / cpu / Forward |
0.000012 s |
0.000011552759970072657 s |
1.04 |
add_two / IPartOpt / cpu / Forward |
0.000012 s |
0.000011149400006615904 s |
1.08 |
add_two / HLOOpt / cpu / Forward |
0.000012 s |
0.00001163689995337336 s |
1.03 |
add_two / DefOpt / cpu / Forward |
0.000013 s |
0.000010866600005101646 s |
1.20 |
add_two / IDefOpt / cpu / Forward |
0.000012 s |
0.00001085120003153861 s |
1.11 |
add_two / Jax / cpu / BothRev |
0.000017 s |
0.000016008080037863693 s |
1.06 |
add_two / JaXPipe / cpu / PreRev |
0.000017 s |
0.00001607411998520547 s |
1.06 |
add_two / JaXPipe / cpu / PostRev |
0.000017 s |
0.000015767160030009108 s |
1.08 |
add_two / JaXPipe / cpu / BothRev |
0.000017 s |
0.00001591828001437534 s |
1.07 |
add_two / PartOpt / cpu / PreRev |
0.000016 s |
0.000016130079948197818 s |
0.99 |
add_two / PartOpt / cpu / PostRev |
0.000017 s |
0.00001545496003018343 s |
1.10 |
add_two / PartOpt / cpu / BothRev |
0.000016 s |
0.000015658540050935698 s |
1.02 |
add_two / IPartOpt / cpu / PreRev |
0.00005 s |
0.000015700720014137913 s |
3.18 |
add_two / IPartOpt / cpu / PostRev |
0.000017 s |
0.000015940499997668668 s |
1.07 |
add_two / IPartOpt / cpu / BothRev |
0.000016 s |
0.000016176559984160122 s |
0.99 |
add_two / HLOOpt / cpu / PreRev |
0.000017 s |
0.000016023040034269796 s |
1.06 |
add_two / HLOOpt / cpu / PostRev |
0.000017 s |
0.00001724719999401714 s |
0.99 |
add_two / HLOOpt / cpu / BothRev |
0.000016 s |
0.000015348320039265674 s |
1.04 |
add_two / DefOpt / cpu / PreRev |
0.000016 s |
0.00001615454000784666 s |
0.99 |
add_two / DefOpt / cpu / PostRev |
0.000016 s |
0.000016489659992657833 s |
0.97 |
add_two / DefOpt / cpu / BothRev |
0.000016 s |
0.00001642914002331963 s |
0.97 |
add_two / IDefOpt / cpu / PreRev |
0.000016 s |
0.00001574142003846646 s |
1.02 |
add_two / IDefOpt / cpu / PostRev |
0.000016 s |
0.000016233939986705083 s |
0.99 |
add_two / IDefOpt / cpu / BothRev |
0.000016 s |
0.000016458300024169148 s |
0.97 |
cache / Jax / cpu / Primal |
0.000006283039947447833 s |
0.000007059020026645157 s |
0.89 |
cache / JaXPipe / cpu / Primal |
0.000006358699956763303 s |
0.0000072663399805605875 s |
0.88 |
cache / PartOpt / cpu / Primal |
0.000005984600011288421 s |
0.000007266960028573521 s |
0.82 |
cache / IPartOpt / cpu / Primal |
0.000006060760006221244 s |
0.000006997760056037805 s |
0.87 |
cache / HLOOpt / cpu / Primal |
0.000006286220050242264 s |
0.00000714279999556311 s |
0.88 |
cache / DefOpt / cpu / Primal |
0.000005981880003673723 s |
0.000007151300005716621 s |
0.84 |
cache / IDefOpt / cpu / Primal |
0.0000060759200096072165 s |
0.00000695411999913631 s |
0.87 |
cache / Jax / cpu / Forward |
0.000014679639980386127 s |
0.00001483424003708933 s |
0.99 |
cache / JaXPipe / cpu / Forward |
0.000014764039960937225 s |
0.000015701859983892063 s |
0.94 |
cache / PartOpt / cpu / Forward |
0.000015008400041551794 s |
0.00001612193999790179 s |
0.93 |
cache / IPartOpt / cpu / Forward |
0.000015140379991862572 s |
0.00001666036001552129 s |
0.91 |
cache / HLOOpt / cpu / Forward |
0.000014918640017640428 s |
0.000016832900009831064 s |
0.89 |
cache / DefOpt / cpu / Forward |
0.000014261760015870096 s |
0.00001574375998643518 s |
0.91 |
cache / IDefOpt / cpu / Forward |
0.000014590700029657457 s |
0.00001478907997807255 s |
0.99 |
cache / Jax / cpu / BothRev |
0.00001967360001799534 s |
0.000021109800045451265 s |
0.93 |
cache / JaXPipe / cpu / PreRev |
0.000015705979994891094 s |
0.00001646296000217262 s |
0.95 |
cache / JaXPipe / cpu / PostRev |
0.000021246699998300755 s |
0.00002128442002685915 s |
1.00 |
cache / JaXPipe / cpu / BothRev |
0.0000151911799730442 s |
0.000016913399995246437 s |
0.90 |
cache / PartOpt / cpu / PreRev |
0.000016084719991340535 s |
0.00001996600002712512 s |
0.81 |
cache / PartOpt / cpu / PostRev |
0.00002228207998086873 s |
0.000022108299999672452 s |
1.01 |
cache / PartOpt / cpu / BothRev |
0.0000154900400320912 s |
0.000016975299977275427 s |
0.91 |
cache / IPartOpt / cpu / PreRev |
0.000016139099971042013 s |
0.000017175520024466096 s |
0.94 |
cache / IPartOpt / cpu / PostRev |
0.00002020814000388782 s |
0.00002078946001347504 s |
0.97 |
cache / IPartOpt / cpu / BothRev |
0.000016047920053097186 s |
0.000017755019971446018 s |
0.90 |
cache / HLOOpt / cpu / PreRev |
0.00001586960002896376 s |
0.00001809326004149625 s |
0.88 |
cache / HLOOpt / cpu / PostRev |
0.00001532479999696079 s |
0.00001996429998143867 s |
0.77 |
cache / HLOOpt / cpu / BothRev |
0.000015679339976486518 s |
0.000018035499979305315 s |
0.87 |
cache / DefOpt / cpu / PreRev |
0.000015241480023178155 s |
0.00001808053998502146 s |
0.84 |
cache / DefOpt / cpu / PostRev |
0.000015952379999362166 s |
0.000018206260010629192 s |
0.88 |
cache / DefOpt / cpu / BothRev |
0.000015198259943645098 s |
0.00001633273996958451 s |
0.93 |
cache / IDefOpt / cpu / PreRev |
0.00001574565998453181 s |
0.000017065619977074677 s |
0.92 |
cache / IDefOpt / cpu / PostRev |
0.000014969300073062186 s |
0.000017194100000779144 s |
0.87 |
cache / IDefOpt / cpu / BothRev |
0.000015216999972835764 s |
0.00003606621998187621 s |
0.42 |
cache / Jax / cuda / Primal |
0.000002304 s |
0.000002336 s |
0.99 |
cache / JaXPipe / cuda / Primal |
0.000002335 s |
0.000002336 s |
1.00 |
cache / PartOpt / cuda / Primal |
0.000002271 s |
0.000002304 s |
0.99 |
cache / IPartOpt / cuda / Primal |
0.00000224 s |
0.000002335 s |
0.96 |
cache / HLOOpt / cuda / Primal |
0.000002304 s |
0.000002272 s |
1.01 |
cache / DefOpt / cuda / Primal |
0.000002272 s |
0.000002304 s |
0.99 |
cache / IDefOpt / cuda / Primal |
0.000002272 s |
0.000002272 s |
1 |
cache / Jax / cuda / Forward |
0.000002335 s |
0.0000023670000000000004 s |
0.99 |
cache / JaXPipe / cuda / Forward |
0.000002335 s |
0.0000023670000000000004 s |
0.99 |
cache / PartOpt / cuda / Forward |
0.000002335 s |
0.0000023670000000000004 s |
0.99 |
cache / IPartOpt / cuda / Forward |
0.000002335 s |
0.0000023670000000000004 s |
0.99 |
cache / HLOOpt / cuda / Forward |
0.000002335 s |
0.0000023670000000000004 s |
0.99 |
cache / DefOpt / cuda / Forward |
0.000002304 s |
0.000002304 s |
1 |
cache / IDefOpt / cuda / Forward |
0.000002336 s |
0.0000023670000000000004 s |
0.99 |
cache / Jax / cuda / BothRev |
0.00001088 s |
0.000011008 s |
0.99 |
cache / JaXPipe / cuda / PreRev |
0.000010528 s |
0.00001024 s |
1.03 |
cache / JaXPipe / cuda / PostRev |
0.000010689 s |
0.000010496 s |
1.02 |
cache / JaXPipe / cuda / BothRev |
0.000010912 s |
0.000010433 s |
1.05 |
cache / PartOpt / cuda / PreRev |
0.000010816 s |
0.00001088 s |
0.99 |
cache / PartOpt / cuda / PostRev |
0.000010816 s |
0.000010816 s |
1 |
cache / PartOpt / cuda / BothRev |
0.000010944 s |
0.000010913 s |
1.00 |
cache / IPartOpt / cuda / PreRev |
0.000010752 s |
0.000011103 s |
0.97 |
cache / IPartOpt / cuda / PostRev |
0.000011009 s |
0.000010912 s |
1.01 |
cache / IPartOpt / cuda / BothRev |
0.000012224 s |
0.00001056 s |
1.16 |
cache / HLOOpt / cuda / PreRev |
0.000013248 s |
0.000013087 s |
1.01 |
cache / HLOOpt / cuda / PostRev |
0.000015808 s |
0.000013055 s |
1.21 |
cache / HLOOpt / cuda / BothRev |
0.000013216 s |
0.000013087 s |
1.01 |
cache / DefOpt / cuda / PreRev |
0.000010784 s |
0.000011712 s |
0.92 |
cache / DefOpt / cuda / PostRev |
0.000010848 s |
0.000010943 s |
0.99 |
cache / DefOpt / cuda / BothRev |
0.000011072 s |
0.000010496 s |
1.05 |
cache / IDefOpt / cuda / PreRev |
0.000010976 s |
0.000010848 s |
1.01 |
cache / IDefOpt / cuda / PostRev |
0.000010624 s |
0.000010816 s |
0.98 |
cache / IDefOpt / cuda / BothRev |
0.000010496 s |
0.000010753 s |
0.98 |
cache / Jax / tpu / Primal |
0.0000024777 s |
0.000002462875 s |
1.01 |
cache / JaXPipe / tpu / Primal |
0.0000024611 s |
0.000002475475 s |
0.99 |
cache / PartOpt / tpu / Primal |
0.0000024629 s |
0.0000024692 s |
1.00 |
cache / IPartOpt / tpu / Primal |
0.000002468175 s |
0.000002475325 s |
1.00 |
cache / HLOOpt / tpu / Primal |
0.000002471325 s |
0.000002463575 s |
1.00 |
cache / DefOpt / tpu / Primal |
0.00000244765 s |
0.000002473 s |
0.99 |
cache / IDefOpt / tpu / Primal |
0.000002468375 s |
0.00000245865 s |
1.00 |
cache / Jax / tpu / Forward |
0.00000356425 s |
0.000003542725 s |
1.01 |
cache / JaXPipe / tpu / Forward |
0.000003519375 s |
0.000003546375 s |
0.99 |
cache / PartOpt / tpu / Forward |
0.000003545725 s |
0.000003531725 s |
1.00 |
cache / IPartOpt / tpu / Forward |
0.000003541775 s |
0.000003584575 s |
0.99 |
cache / HLOOpt / tpu / Forward |
0.0000035644 s |
0.000003557725 s |
1.00 |
cache / DefOpt / tpu / Forward |
0.00000351815 s |
0.000003544125000000001 s |
0.99 |
cache / IDefOpt / tpu / Forward |
0.0000035711 s |
0.00000355125 s |
1.01 |
cache / Jax / tpu / BothRev |
0.000004958375 s |
0.000004971324999999999 s |
1.00 |
cache / JaXPipe / tpu / PreRev |
0.0000049832 s |
0.000004941975 s |
1.01 |
cache / JaXPipe / tpu / PostRev |
0.000004971525 s |
0.000004950099999999999 s |
1.00 |
cache / JaXPipe / tpu / BothRev |
0.00000499375 s |
0.0000049529250000000005 s |
1.01 |
cache / PartOpt / tpu / PreRev |
0.000004977475 s |
0.000004969925 s |
1.00 |
cache / PartOpt / tpu / PostRev |
0.000005009924999999999 s |
0.0000049710500000000005 s |
1.01 |
cache / PartOpt / tpu / BothRev |
0.0000049935000000000006 s |
0.0000049886 s |
1.00 |
cache / IPartOpt / tpu / PreRev |
0.0000050193750000000005 s |
0.000004944075 s |
1.02 |
cache / IPartOpt / tpu / PostRev |
0.0000050042 s |
0.000004964275000000001 s |
1.01 |
cache / IPartOpt / tpu / BothRev |
0.0000050166 s |
0.000004961025 s |
1.01 |
cache / HLOOpt / tpu / PreRev |
0.000004130275 s |
0.0000039344 s |
1.05 |
cache / HLOOpt / tpu / PostRev |
0.00000413485 s |
0.000004119175 s |
1.00 |
cache / HLOOpt / tpu / BothRev |
0.000004123125 s |
0.000003933925 s |
1.05 |
cache / DefOpt / tpu / PreRev |
0.000004996975 s |
0.00000497215 s |
1.00 |
cache / DefOpt / tpu / PostRev |
0.00000498135 s |
0.000004977124999999999 s |
1.00 |
cache / DefOpt / tpu / BothRev |
0.000005021825 s |
0.000004970425 s |
1.01 |
cache / IDefOpt / tpu / PreRev |
0.00000497655 s |
0.0000049747 s |
1.00 |
cache / IDefOpt / tpu / PostRev |
0.0000050097000000000005 s |
0.0000049627 s |
1.01 |
cache / IDefOpt / tpu / BothRev |
0.00000497575 s |
0.00000497935 s |
1.00 |
cache / Jax / cpu / Primal |
0.000012874 s |
0.000007059020026645157 s |
1.82 |
cache / JaXPipe / cpu / Primal |
0.000012742 s |
0.0000072663399805605875 s |
1.75 |
cache / PartOpt / cpu / Primal |
0.000012893 s |
0.000007266960028573521 s |
1.77 |
cache / IPartOpt / cpu / Primal |
0.000012559 s |
0.000006997760056037805 s |
1.79 |
cache / HLOOpt / cpu / Primal |
0.000012751 s |
0.00000714279999556311 s |
1.79 |
cache / DefOpt / cpu / Primal |
0.000012759 s |
0.000007151300005716621 s |
1.78 |
cache / IDefOpt / cpu / Primal |
0.000012735 s |
0.00000695411999913631 s |
1.83 |
cache / Jax / cpu / Forward |
0.000021528 s |
0.00001483424003708933 s |
1.45 |
cache / JaXPipe / cpu / Forward |
0.000016924999999999998 s |
0.000015701859983892063 s |
1.08 |
cache / PartOpt / cpu / Forward |
0.000017191000000000002 s |
0.00001612193999790179 s |
1.07 |
cache / IPartOpt / cpu / Forward |
0.000017726 s |
0.00001666036001552129 s |
1.06 |
cache / HLOOpt / cpu / Forward |
0.000025834 s |
0.000016832900009831064 s |
1.53 |
cache / DefOpt / cpu / Forward |
0.000026391 s |
0.00001574375998643518 s |
1.68 |
cache / IDefOpt / cpu / Forward |
0.00002263 s |
0.00001478907997807255 s |
1.53 |
cache / Jax / cpu / BothRev |
0.000034541 s |
0.000021109800045451265 s |
1.64 |
cache / JaXPipe / cpu / PreRev |
0.000030137 s |
0.00001646296000217262 s |
1.83 |
cache / JaXPipe / cpu / PostRev |
0.000031296999999999995 s |
0.00002128442002685915 s |
1.47 |
cache / JaXPipe / cpu / BothRev |
0.000026573 s |
0.000016913399995246437 s |
1.57 |
cache / PartOpt / cpu / PreRev |
0.000028239 s |
0.00001996600002712512 s |
1.41 |
cache / PartOpt / cpu / PostRev |
0.000026171 s |
0.000022108299999672452 s |
1.18 |
cache / PartOpt / cpu / BothRev |
0.000024439 s |
0.000016975299977275427 s |
1.44 |
cache / IPartOpt / cpu / PreRev |
0.000017833 s |
0.000017175520024466096 s |
1.04 |
cache / IPartOpt / cpu / PostRev |
0.000033238 s |
0.00002078946001347504 s |
1.60 |
cache / IPartOpt / cpu / BothRev |
0.000029311 s |
0.000017755019971446018 s |
1.65 |
cache / HLOOpt / cpu / PreRev |
0.000026934 s |
0.00001809326004149625 s |
1.49 |
cache / HLOOpt / cpu / PostRev |
0.000026779 s |
0.00001996429998143867 s |
1.34 |
cache / HLOOpt / cpu / BothRev |
0.000025696 s |
0.000018035499979305315 s |
1.42 |
cache / DefOpt / cpu / PreRev |
0.000025233 s |
0.00001808053998502146 s |
1.40 |
cache / DefOpt / cpu / PostRev |
0.000026813 s |
0.000018206260010629192 s |
1.47 |
cache / DefOpt / cpu / BothRev |
0.000027562 s |
0.00001633273996958451 s |
1.69 |
cache / IDefOpt / cpu / PreRev |
0.000029016 s |
0.000017065619977074677 s |
1.70 |
cache / IDefOpt / cpu / PostRev |
0.000026644 s |
0.000017194100000779144 s |
1.55 |
cache / IDefOpt / cpu / BothRev |
0.000033375000000000005 s |
0.00003606621998187621 s |
0.93 |
cache / Jax / cpu / Primal |
0.000008 s |
0.000007059020026645157 s |
1.13 |
cache / JaXPipe / cpu / Primal |
0.000008999999999999999 s |
0.0000072663399805605875 s |
1.24 |
cache / PartOpt / cpu / Primal |
0.000008 s |
0.000007266960028573521 s |
1.10 |
cache / IPartOpt / cpu / Primal |
0.000008999999999999999 s |
0.000006997760056037805 s |
1.29 |
cache / HLOOpt / cpu / Primal |
0.000008 s |
0.00000714279999556311 s |
1.12 |
cache / DefOpt / cpu / Primal |
0.000008 s |
0.000007151300005716621 s |
1.12 |
cache / IDefOpt / cpu / Primal |
0.000008 s |
0.00000695411999913631 s |
1.15 |
cache / Jax / cpu / Forward |
0.000019 s |
0.00001483424003708933 s |
1.28 |
cache / JaXPipe / cpu / Forward |
0.000011 s |
0.000015701859983892063 s |
0.70 |
cache / PartOpt / cpu / Forward |
0.00001 s |
0.00001612193999790179 s |
0.62 |
cache / IPartOpt / cpu / Forward |
0.00005 s |
0.00001666036001552129 s |
3.00 |
cache / HLOOpt / cpu / Forward |
0.000033 s |
0.000016832900009831064 s |
1.96 |
cache / DefOpt / cpu / Forward |
0.00001 s |
0.00001574375998643518 s |
0.64 |
cache / IDefOpt / cpu / Forward |
0.000017999999999999997 s |
0.00001478907997807255 s |
1.22 |
cache / Jax / cpu / BothRev |
0.000012 s |
0.000021109800045451265 s |
0.57 |
cache / JaXPipe / cpu / PreRev |
0.00001 s |
0.00001646296000217262 s |
0.61 |
cache / JaXPipe / cpu / PostRev |
0.000038 s |
0.00002128442002685915 s |
1.79 |
cache / JaXPipe / cpu / BothRev |
0.000011 s |
0.000016913399995246437 s |
0.65 |
cache / PartOpt / cpu / PreRev |
0.00001 s |
0.00001996600002712512 s |
0.50 |
cache / PartOpt / cpu / PostRev |
0.000031 s |
0.000022108299999672452 s |
1.40 |
cache / PartOpt / cpu / BothRev |
0.000012 s |
0.000016975299977275427 s |
0.71 |
cache / IPartOpt / cpu / PreRev |
0.00001 s |
0.000017175520024466096 s |
0.58 |
cache / IPartOpt / cpu / PostRev |
0.000038 s |
0.00002078946001347504 s |
1.83 |
cache / IPartOpt / cpu / BothRev |
0.000011 s |
0.000017755019971446018 s |
0.62 |
cache / HLOOpt / cpu / PreRev |
0.00001 s |
0.00001809326004149625 s |
0.55 |
cache / HLOOpt / cpu / PostRev |
0.000011 s |
0.00001996429998143867 s |
0.55 |
cache / HLOOpt / cpu / BothRev |
0.000035000000000000004 s |
0.000018035499979305315 s |
1.94 |
cache / DefOpt / cpu / PreRev |
0.00001 s |
0.00001808053998502146 s |
0.55 |
cache / DefOpt / cpu / PostRev |
0.000035999999999999994 s |
0.000018206260010629192 s |
1.98 |
cache / DefOpt / cpu / BothRev |
0.000011 s |
0.00001633273996958451 s |
0.67 |
cache / IDefOpt / cpu / PreRev |
0.000012 s |
0.000017065619977074677 s |
0.70 |
cache / IDefOpt / cpu / PostRev |
0.000011 s |
0.000017194100000779144 s |
0.64 |
cache / IDefOpt / cpu / BothRev |
0.000011 s |
0.00003606621998187621 s |
0.30 |
Concat / Jax / cpu / Primal |
0.000006423960039683152 s |
0.000007469840011253837 s |
0.86 |
Concat / JaXPipe / cpu / Primal |
0.000006773340019208263 s |
0.000007722380005361628 s |
0.88 |
Concat / PartOpt / cpu / Primal |
0.0000068309999824123226 s |
0.00000716315999852668 s |
0.95 |
Concat / IPartOpt / cpu / Primal |
0.000006303960017248755 s |
0.0000073569000232964755 s |
0.86 |
Concat / HLOOpt / cpu / Primal |
0.000006941520014152047 s |
0.000007509980005124816 s |
0.92 |
Concat / DefOpt / cpu / Primal |
0.000006781939955544658 s |
0.000006935940000403207 s |
0.98 |
Concat / IDefOpt / cpu / Primal |
0.0000062701800379727504 s |
0.000007187700048234547 s |
0.87 |
Concat / Jax / cpu / Forward |
0.000009941519983840408 s |
0.000011150919972351405 s |
0.89 |
Concat / JaXPipe / cpu / Forward |
0.000009746299983817153 s |
0.00001155280003331427 s |
0.84 |
Concat / PartOpt / cpu / Forward |
0.000009931419990607535 s |
0.00001142896002420457 s |
0.87 |
Concat / IPartOpt / cpu / Forward |
0.000009769800008143648 s |
0.000011185860003024571 s |
0.87 |
Concat / HLOOpt / cpu / Forward |
0.000009719660001792362 s |
0.000010956260020975605 s |
0.89 |
Concat / DefOpt / cpu / Forward |
0.000009629000032873591 s |
0.000011048579999624053 s |
0.87 |
Concat / IDefOpt / cpu / Forward |
0.000010161139998672296 s |
0.000011640999982773792 s |
0.87 |
Concat / Jax / cpu / BothRev |
0.00001143007998507528 s |
0.00001323239996963821 s |
0.86 |
Concat / JaXPipe / cpu / PreRev |
0.000011107940044894347 s |
0.000013337879954633535 s |
0.83 |
Concat / JaXPipe / cpu / PostRev |
0.0000110124799721234 s |
0.00001346205998743244 s |
0.82 |
Concat / JaXPipe / cpu / BothRev |
0.00001089051997041679 s |
0.000012496040026235278 s |
0.87 |
Concat / PartOpt / cpu / PreRev |
0.000012172760025350726 s |
0.000012892439972347347 s |
0.94 |
Concat / PartOpt / cpu / PostRev |
0.000013254100022095372 s |
0.000012447819972294383 s |
1.06 |
Concat / PartOpt / cpu / BothRev |
0.00001085023996893142 s |
0.000014018979973116077 s |
0.77 |
Concat / IPartOpt / cpu / PreRev |
0.000010839939996003525 s |
0.000013137420000930434 s |
0.83 |
Concat / IPartOpt / cpu / PostRev |
0.00001103691998650902 s |
0.00001297132000217971 s |
0.85 |
Concat / IPartOpt / cpu / BothRev |
0.000011952400018344634 s |
0.000013204779988882364 s |
0.91 |
Concat / HLOOpt / cpu / PreRev |
0.000011175040044690832 s |
0.000013045039950156931 s |
0.86 |
Concat / HLOOpt / cpu / PostRev |
0.000011062100020353682 s |
0.000015257439999913913 s |
0.73 |
Concat / HLOOpt / cpu / BothRev |
0.00001098090001505625 s |
0.00001330468005107832 s |
0.83 |
Concat / DefOpt / cpu / PreRev |
0.00001116033999096544 s |
0.0000141949400131125 s |
0.79 |
Concat / DefOpt / cpu / PostRev |
0.000011017819988410336 s |
0.00001276810002309503 s |
0.86 |
Concat / DefOpt / cpu / BothRev |
0.000011265920011283016 s |
0.000013300199989316751 s |
0.85 |
Concat / IDefOpt / cpu / PreRev |
0.000011744120001822012 s |
0.000013066080000498916 s |
0.90 |
Concat / IDefOpt / cpu / PostRev |
0.000011325160030537518 s |
0.000013508679958249558 s |
0.84 |
Concat / IDefOpt / cpu / BothRev |
0.000011554180027815163 s |
0.000012933540010635624 s |
0.89 |
Concat / Jax / cuda / Primal |
0.0000019200000000000003 s |
0.0000019200000000000003 s |
1 |
Concat / JaXPipe / cuda / Primal |
0.0000019200000000000003 s |
0.000001888 s |
1.02 |
Concat / PartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000001919 s |
1.00 |
Concat / IPartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000019200000000000003 s |
1 |
Concat / HLOOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000019200000000000003 s |
1 |
Concat / DefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000019200000000000003 s |
1 |
Concat / IDefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000019200000000000003 s |
1 |
Concat / Jax / cuda / Forward |
0.00000992 s |
0.0000096 s |
1.03 |
Concat / JaXPipe / cuda / Forward |
0.000010176 s |
0.000009408 s |
1.08 |
Concat / PartOpt / cuda / Forward |
0.000009952 s |
0.000009728 s |
1.02 |
Concat / IPartOpt / cuda / Forward |
0.000010208 s |
0.000009824 s |
1.04 |
Concat / HLOOpt / cuda / Forward |
0.000010016 s |
0.000009472 s |
1.06 |
Concat / DefOpt / cuda / Forward |
0.000010176 s |
0.000009824 s |
1.04 |
Concat / IDefOpt / cuda / Forward |
0.000009824 s |
0.000009792 s |
1.00 |
Concat / Jax / cuda / BothRev |
0.000016416 s |
0.000016448000000000002 s |
1.00 |
Concat / JaXPipe / cuda / PreRev |
0.000017152 s |
0.000015743 s |
1.09 |
Concat / JaXPipe / cuda / PostRev |
0.000016063999999999997 s |
0.000015999 s |
1.00 |
Concat / JaXPipe / cuda / BothRev |
0.000016255999999999998 s |
0.000025088 s |
0.65 |
Concat / PartOpt / cuda / PreRev |
0.000016352 s |
0.000016 s |
1.02 |
Concat / PartOpt / cuda / PostRev |
0.00001664 s |
0.000016352 s |
1.02 |
Concat / PartOpt / cuda / BothRev |
0.000016672 s |
0.000016063999999999997 s |
1.04 |
Concat / IPartOpt / cuda / PreRev |
0.00001648 s |
0.00001632 s |
1.01 |
Concat / IPartOpt / cuda / PostRev |
0.000016255999999999998 s |
0.000016224 s |
1.00 |
Concat / IPartOpt / cuda / BothRev |
0.000016544 s |
0.000016288 s |
1.02 |
Concat / HLOOpt / cuda / PreRev |
0.000016544 s |
0.00001632 s |
1.01 |
Concat / HLOOpt / cuda / PostRev |
0.000016128 s |
0.000015999 s |
1.01 |
Concat / HLOOpt / cuda / BothRev |
0.000016608 s |
0.000015966999999999998 s |
1.04 |
Concat / DefOpt / cuda / PreRev |
0.000016383999999999998 s |
0.000016032 s |
1.02 |
Concat / DefOpt / cuda / PostRev |
0.000016288 s |
0.000015872 s |
1.03 |
Concat / DefOpt / cuda / BothRev |
0.000016896999999999998 s |
0.000016224 s |
1.04 |
Concat / IDefOpt / cuda / PreRev |
0.000016576000000000002 s |
0.000016576000000000002 s |
1 |
Concat / IDefOpt / cuda / PostRev |
0.000017057 s |
0.000015999 s |
1.07 |
Concat / IDefOpt / cuda / BothRev |
0.000016670999999999997 s |
0.00001632 s |
1.02 |
Concat / Jax / tpu / Primal |
0.000001519025 s |
0.000001526325 s |
1.00 |
Concat / JaXPipe / tpu / Primal |
0.000001517425 s |
0.00000153335 s |
0.99 |
Concat / PartOpt / tpu / Primal |
0.0000015185499999999998 s |
0.00000153295 s |
0.99 |
Concat / IPartOpt / tpu / Primal |
0.000001516425 s |
0.000001527325 s |
0.99 |
Concat / HLOOpt / tpu / Primal |
0.0000015305 s |
0.0000015363 s |
1.00 |
Concat / DefOpt / tpu / Primal |
0.0000015271000000000002 s |
0.000001520875 s |
1.00 |
Concat / IDefOpt / tpu / Primal |
0.0000015231 s |
0.0000015308250000000005 s |
0.99 |
Concat / Jax / tpu / Forward |
0.000001543 s |
0.00000154745 s |
1.00 |
Concat / JaXPipe / tpu / Forward |
0.000001553975 s |
0.000001571175 s |
0.99 |
Concat / PartOpt / tpu / Forward |
0.000001535875 s |
0.000001550125 s |
0.99 |
Concat / IPartOpt / tpu / Forward |
0.0000015431749999999998 s |
0.0000015801 s |
0.98 |
Concat / HLOOpt / tpu / Forward |
0.000001583625 s |
0.0000015902 s |
1.00 |
Concat / DefOpt / tpu / Forward |
0.0000015516750000000005 s |
0.00000155265 s |
1.00 |
Concat / IDefOpt / tpu / Forward |
0.000001564625 s |
0.0000015643999999999998 s |
1.00 |
Concat / Jax / tpu / BothRev |
0.00000203175 s |
0.000002071975 s |
0.98 |
Concat / JaXPipe / tpu / PreRev |
0.000001993225 s |
0.0000020065500000000003 s |
0.99 |
Concat / JaXPipe / tpu / PostRev |
0.00000202035 s |
0.000002083225 s |
0.97 |
Concat / JaXPipe / tpu / BothRev |
0.0000019901 s |
0.000002003425 s |
0.99 |
Concat / PartOpt / tpu / PreRev |
0.00000202825 s |
0.0000020772 s |
0.98 |
Concat / PartOpt / tpu / PostRev |
0.00000199275 s |
0.000002007975 s |
0.99 |
Concat / PartOpt / tpu / BothRev |
0.000002025925 s |
0.0000020912 s |
0.97 |
Concat / IPartOpt / tpu / PreRev |
0.000001998 s |
0.00000200175 s |
1.00 |
Concat / IPartOpt / tpu / PostRev |
0.0000020238 s |
0.000002068875 s |
0.98 |
Concat / IPartOpt / tpu / BothRev |
0.000001992375 s |
0.000002016125 s |
0.99 |
Concat / HLOOpt / tpu / PreRev |
0.0000020245 s |
0.0000020164000000000003 s |
1.00 |
Concat / HLOOpt / tpu / PostRev |
0.000001996825 s |
0.00000206995 s |
0.96 |
Concat / HLOOpt / tpu / BothRev |
0.0000020313000000000004 s |
0.0000020086 s |
1.01 |
Concat / DefOpt / tpu / PreRev |
0.0000020105 s |
0.00000207255 s |
0.97 |
Concat / DefOpt / tpu / PostRev |
0.0000020375 s |
0.0000020205 s |
1.01 |
Concat / DefOpt / tpu / BothRev |
0.000001992775 s |
0.000002074075 s |
0.96 |
Concat / IDefOpt / tpu / PreRev |
0.0000020438 s |
0.0000020079 s |
1.02 |
Concat / IDefOpt / tpu / PostRev |
0.00000198635 s |
0.000002076925 s |
0.96 |
Concat / IDefOpt / tpu / BothRev |
0.00000203185 s |
0.000002008125 s |
1.01 |
Concat / Jax / cpu / Primal |
0.00001277 s |
0.000007469840011253837 s |
1.71 |
Concat / JaXPipe / cpu / Primal |
0.000012502 s |
0.000007722380005361628 s |
1.62 |
Concat / PartOpt / cpu / Primal |
0.000012724 s |
0.00000716315999852668 s |
1.78 |
Concat / IPartOpt / cpu / Primal |
0.000013088 s |
0.0000073569000232964755 s |
1.78 |
Concat / HLOOpt / cpu / Primal |
0.000012868 s |
0.000007509980005124816 s |
1.71 |
Concat / DefOpt / cpu / Primal |
0.000012763 s |
0.000006935940000403207 s |
1.84 |
Concat / IDefOpt / cpu / Primal |
0.00001291 s |
0.000007187700048234547 s |
1.80 |
Concat / Jax / cpu / Forward |
0.000017605 s |
0.000011150919972351405 s |
1.58 |
Concat / JaXPipe / cpu / Forward |
0.000017899999999999998 s |
0.00001155280003331427 s |
1.55 |
Concat / PartOpt / cpu / Forward |
0.00001748 s |
0.00001142896002420457 s |
1.53 |
Concat / IPartOpt / cpu / Forward |
0.00001745 s |
0.000011185860003024571 s |
1.56 |
Concat / HLOOpt / cpu / Forward |
0.000017808 s |
0.000010956260020975605 s |
1.63 |
Concat / DefOpt / cpu / Forward |
0.000017509 s |
0.000011048579999624053 s |
1.58 |
Concat / IDefOpt / cpu / Forward |
0.000017544 s |
0.000011640999982773792 s |
1.51 |
Concat / Jax / cpu / BothRev |
0.000020154 s |
0.00001323239996963821 s |
1.52 |
Concat / JaXPipe / cpu / PreRev |
0.000020241 s |
0.000013337879954633535 s |
1.52 |
Concat / JaXPipe / cpu / PostRev |
0.000019459 s |
0.00001346205998743244 s |
1.45 |
Concat / JaXPipe / cpu / BothRev |
0.000019719 s |
0.000012496040026235278 s |
1.58 |
Concat / PartOpt / cpu / PreRev |
0.000020303 s |
0.000012892439972347347 s |
1.57 |
Concat / PartOpt / cpu / PostRev |
0.000019711 s |
0.000012447819972294383 s |
1.58 |
Concat / PartOpt / cpu / BothRev |
0.000019573 s |
0.000014018979973116077 s |
1.40 |
Concat / IPartOpt / cpu / PreRev |
0.000019679 s |
0.000013137420000930434 s |
1.50 |
Concat / IPartOpt / cpu / PostRev |
0.000019634 s |
0.00001297132000217971 s |
1.51 |
Concat / IPartOpt / cpu / BothRev |
0.000019227 s |
0.000013204779988882364 s |
1.46 |
Concat / HLOOpt / cpu / PreRev |
0.00002016 s |
0.000013045039950156931 s |
1.55 |
Concat / HLOOpt / cpu / PostRev |
0.000019901 s |
0.000015257439999913913 s |
1.30 |
Concat / HLOOpt / cpu / BothRev |
0.000019489 s |
0.00001330468005107832 s |
1.46 |
Concat / DefOpt / cpu / PreRev |
0.000019633 s |
0.0000141949400131125 s |
1.38 |
Concat / DefOpt / cpu / PostRev |
0.00001988 s |
0.00001276810002309503 s |
1.56 |
Concat / DefOpt / cpu / BothRev |
0.000019478 s |
0.000013300199989316751 s |
1.46 |
Concat / IDefOpt / cpu / PreRev |
0.000019983 s |
0.000013066080000498916 s |
1.53 |
Concat / IDefOpt / cpu / PostRev |
0.000019864 s |
0.000013508679958249558 s |
1.47 |
Concat / IDefOpt / cpu / BothRev |
0.00001947 s |
0.000012933540010635624 s |
1.51 |
Concat / Jax / cpu / Primal |
0.000008999999999999999 s |
0.000007469840011253837 s |
1.20 |
Concat / JaXPipe / cpu / Primal |
0.000008 s |
0.000007722380005361628 s |
1.04 |
Concat / PartOpt / cpu / Primal |
0.000008999999999999999 s |
0.00000716315999852668 s |
1.26 |
Concat / IPartOpt / cpu / Primal |
0.000008999999999999999 s |
0.0000073569000232964755 s |
1.22 |
Concat / HLOOpt / cpu / Primal |
0.000008999999999999999 s |
0.000007509980005124816 s |
1.20 |
Concat / DefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000006935940000403207 s |
1.30 |
Concat / IDefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000007187700048234547 s |
1.25 |
Concat / Jax / cpu / Forward |
0.000012 s |
0.000011150919972351405 s |
1.08 |
Concat / JaXPipe / cpu / Forward |
0.000012 s |
0.00001155280003331427 s |
1.04 |
Concat / PartOpt / cpu / Forward |
0.000012 s |
0.00001142896002420457 s |
1.05 |
Concat / IPartOpt / cpu / Forward |
0.000013 s |
0.000011185860003024571 s |
1.16 |
Concat / HLOOpt / cpu / Forward |
0.000013 s |
0.000010956260020975605 s |
1.19 |
Concat / DefOpt / cpu / Forward |
0.000012 s |
0.000011048579999624053 s |
1.09 |
Concat / IDefOpt / cpu / Forward |
0.000013 s |
0.000011640999982773792 s |
1.12 |
Concat / Jax / cpu / BothRev |
0.000014 s |
0.00001323239996963821 s |
1.06 |
Concat / JaXPipe / cpu / PreRev |
0.000014 s |
0.000013337879954633535 s |
1.05 |
Concat / JaXPipe / cpu / PostRev |
0.000014 s |
0.00001346205998743244 s |
1.04 |
Concat / JaXPipe / cpu / BothRev |
0.000014 s |
0.000012496040026235278 s |
1.12 |
Concat / PartOpt / cpu / PreRev |
0.000014 s |
0.000012892439972347347 s |
1.09 |
Concat / PartOpt / cpu / PostRev |
0.000014 s |
0.000012447819972294383 s |
1.12 |
Concat / PartOpt / cpu / BothRev |
0.000014 s |
0.000014018979973116077 s |
1.00 |
Concat / IPartOpt / cpu / PreRev |
0.000014 s |
0.000013137420000930434 s |
1.07 |
Concat / IPartOpt / cpu / PostRev |
0.000014 s |
0.00001297132000217971 s |
1.08 |
Concat / IPartOpt / cpu / BothRev |
0.000014 s |
0.000013204779988882364 s |
1.06 |
Concat / HLOOpt / cpu / PreRev |
0.000014 s |
0.000013045039950156931 s |
1.07 |
Concat / HLOOpt / cpu / PostRev |
0.000014 s |
0.000015257439999913913 s |
0.92 |
Concat / HLOOpt / cpu / BothRev |
0.000014 s |
0.00001330468005107832 s |
1.05 |
Concat / DefOpt / cpu / PreRev |
0.000014 s |
0.0000141949400131125 s |
0.99 |
Concat / DefOpt / cpu / PostRev |
0.000015 s |
0.00001276810002309503 s |
1.17 |
Concat / DefOpt / cpu / BothRev |
0.000014 s |
0.000013300199989316751 s |
1.05 |
Concat / IDefOpt / cpu / PreRev |
0.000014 s |
0.000013066080000498916 s |
1.07 |
Concat / IDefOpt / cpu / PostRev |
0.000014 s |
0.000013508679958249558 s |
1.04 |
Concat / IDefOpt / cpu / BothRev |
0.000014 s |
0.000012933540010635624 s |
1.08 |
const_scatter / Jax / cpu / Primal |
0.000006040440021024551 s |
0.000007548859975941014 s |
0.80 |
const_scatter / JaXPipe / cpu / Primal |
0.000006631900005231728 s |
0.000006842320008217939 s |
0.97 |
const_scatter / PartOpt / cpu / Primal |
0.000006169600019347854 s |
0.000006784740025977953 s |
0.91 |
const_scatter / IPartOpt / cpu / Primal |
0.000006359620010698564 s |
0.000007173680005507777 s |
0.89 |
const_scatter / HLOOpt / cpu / Primal |
0.000007212460013761302 s |
0.000008170320033968893 s |
0.88 |
const_scatter / DefOpt / cpu / Primal |
0.000006910539987075026 s |
0.000007593259997520363 s |
0.91 |
const_scatter / IDefOpt / cpu / Primal |
0.00000665872003082768 s |
0.000007684459988013259 s |
0.87 |
const_scatter / Jax / cpu / Forward |
0.000009155800034932326 s |
0.000011410720007916098 s |
0.80 |
const_scatter / JaXPipe / cpu / Forward |
0.000010043160036730116 s |
0.000011905840028703095 s |
0.84 |
const_scatter / PartOpt / cpu / Forward |
0.000010773659978440264 s |
0.0000117505800062645 s |
0.92 |
const_scatter / IPartOpt / cpu / Forward |
0.000010530919980737963 s |
0.0000122887799898308 s |
0.86 |
const_scatter / HLOOpt / cpu / Forward |
0.000010226780023003813 s |
0.000012375200003589271 s |
0.83 |
const_scatter / DefOpt / cpu / Forward |
0.000009931100030371454 s |
0.0000120592799885344 s |
0.82 |
const_scatter / IDefOpt / cpu / Forward |
0.000010337959947719357 s |
0.000011614740005825297 s |
0.89 |
const_scatter / Jax / cpu / BothRev |
0.0002863066200188 s |
0.0002843011199638 s |
1.01 |
const_scatter / JaXPipe / cpu / PreRev |
0.0002830270599679 s |
0.0002893409799889 s |
0.98 |
const_scatter / JaXPipe / cpu / PostRev |
0.000280803359974 s |
0.0002851822799402 s |
0.98 |
const_scatter / JaXPipe / cpu / BothRev |
0.0002835456400407 s |
0.0002877293199799 s |
0.99 |
const_scatter / PartOpt / cpu / PreRev |
0.0002842232000239 s |
0.0002882542400038 s |
0.99 |
const_scatter / PartOpt / cpu / PostRev |
0.0002845012600027 s |
0.0002828643999964 s |
1.01 |
const_scatter / PartOpt / cpu / BothRev |
0.0002830862800055 s |
0.0002836606200071 s |
1.00 |
const_scatter / IPartOpt / cpu / PreRev |
0.0002817907600092 s |
0.0002861782600211 s |
0.98 |
const_scatter / IPartOpt / cpu / PostRev |
0.0002848484400328 s |
0.0002866531799645 s |
0.99 |
const_scatter / IPartOpt / cpu / BothRev |
0.0002808699399975 s |
0.0002857870600018 s |
0.98 |
const_scatter / HLOOpt / cpu / PreRev |
0.0002827985399835 s |
0.0002843069400023 s |
0.99 |
const_scatter / HLOOpt / cpu / PostRev |
0.0002900225999655 s |
0.000288153240026 s |
1.01 |
const_scatter / HLOOpt / cpu / BothRev |
0.000285481539995 s |
0.0002838666400111 s |
1.01 |
const_scatter / DefOpt / cpu / PreRev |
0.0002845760199943 s |
0.0002845654799966 s |
1.00 |
const_scatter / DefOpt / cpu / PostRev |
0.0002853884000069 s |
0.0002846889000102 s |
1.00 |
const_scatter / DefOpt / cpu / BothRev |
0.0002927902600367 s |
0.0002862369200192 s |
1.02 |
const_scatter / IDefOpt / cpu / PreRev |
0.0002897689999826 s |
0.000284361999993 s |
1.02 |
const_scatter / IDefOpt / cpu / PostRev |
0.0002844517799348 s |
0.0002850745399882 s |
1.00 |
const_scatter / IDefOpt / cpu / BothRev |
0.0002842027399947 s |
0.0002843939999911 s |
1.00 |
const_scatter / Jax / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
const_scatter / JaXPipe / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
const_scatter / PartOpt / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
const_scatter / IPartOpt / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
const_scatter / HLOOpt / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
const_scatter / DefOpt / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
const_scatter / IDefOpt / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
const_scatter / Jax / cuda / Forward |
0.000010144 s |
0.000010047 s |
1.01 |
const_scatter / JaXPipe / cuda / Forward |
0.000009823 s |
0.000009472 s |
1.04 |
const_scatter / PartOpt / cuda / Forward |
0.000009984 s |
0.000009919 s |
1.01 |
const_scatter / IPartOpt / cuda / Forward |
0.000009248 s |
0.000009599 s |
0.96 |
const_scatter / HLOOpt / cuda / Forward |
0.000009952 s |
0.000008736 s |
1.14 |
const_scatter / DefOpt / cuda / Forward |
0.000009823 s |
0.000009472 s |
1.04 |
const_scatter / IDefOpt / cuda / Forward |
0.00000944 s |
0.000009952 s |
0.95 |
const_scatter / Jax / cuda / BothRev |
0.000016672 s |
0.000016096 s |
1.04 |
const_scatter / JaXPipe / cuda / PreRev |
0.000016096 s |
0.00001632 s |
0.99 |
const_scatter / JaXPipe / cuda / PostRev |
0.000015712 s |
0.000015904000000000002 s |
0.99 |
const_scatter / JaXPipe / cuda / BothRev |
0.000017088 s |
0.000015872 s |
1.08 |
const_scatter / PartOpt / cuda / PreRev |
0.000016096 s |
0.000016192 s |
0.99 |
const_scatter / PartOpt / cuda / PostRev |
0.000016128 s |
0.000015743 s |
1.02 |
const_scatter / PartOpt / cuda / BothRev |
0.000016416 s |
0.000016 s |
1.03 |
const_scatter / IPartOpt / cuda / PreRev |
0.00001616 s |
0.000016128 s |
1.00 |
const_scatter / IPartOpt / cuda / PostRev |
0.000016768000000000003 s |
0.000015968 s |
1.05 |
const_scatter / IPartOpt / cuda / BothRev |
0.000017247999999999998 s |
0.000015776 s |
1.09 |
const_scatter / HLOOpt / cuda / PreRev |
0.000017056 s |
0.000015968 s |
1.07 |
const_scatter / HLOOpt / cuda / PostRev |
0.000017023 s |
0.000016 s |
1.06 |
const_scatter / HLOOpt / cuda / BothRev |
0.000016768000000000003 s |
0.000015776 s |
1.06 |
const_scatter / DefOpt / cuda / PreRev |
0.000017056 s |
0.000016 s |
1.07 |
const_scatter / DefOpt / cuda / PostRev |
0.000018016 s |
0.000015424 s |
1.17 |
const_scatter / DefOpt / cuda / BothRev |
0.00001712 s |
0.000015904000000000002 s |
1.08 |
const_scatter / IDefOpt / cuda / PreRev |
0.00001648 s |
0.0000152 s |
1.08 |
const_scatter / IDefOpt / cuda / PostRev |
0.000016 s |
0.000014848 s |
1.08 |
const_scatter / IDefOpt / cuda / BothRev |
0.000016512 s |
0.000015648 s |
1.06 |
const_scatter / Jax / tpu / Primal |
0.000003789275 s |
0.000003836575 s |
0.99 |
const_scatter / JaXPipe / tpu / Primal |
0.000003815725 s |
0.000003797925 s |
1.00 |
const_scatter / PartOpt / tpu / Primal |
0.000003790275 s |
0.000003830325 s |
0.99 |
const_scatter / IPartOpt / tpu / Primal |
0.00000386075 s |
0.0000037967 s |
1.02 |
const_scatter / HLOOpt / tpu / Primal |
0.00000379635 s |
0.0000037955 s |
1.00 |
const_scatter / DefOpt / tpu / Primal |
0.0000038268500000000005 s |
0.0000038172000000000005 s |
1.00 |
const_scatter / IDefOpt / tpu / Primal |
0.000003774075 s |
0.000003794975 s |
0.99 |
const_scatter / Jax / tpu / Forward |
0.000006488525 s |
0.0000064799250000000005 s |
1.00 |
const_scatter / JaXPipe / tpu / Forward |
0.00000645495 s |
0.000006446174999999999 s |
1.00 |
const_scatter / PartOpt / tpu / Forward |
0.000006483925000000001 s |
0.000006470350000000001 s |
1.00 |
const_scatter / IPartOpt / tpu / Forward |
0.000006455275 s |
0.000006477775 s |
1.00 |
const_scatter / HLOOpt / tpu / Forward |
0.0000065084 s |
0.00000645555 s |
1.01 |
const_scatter / DefOpt / tpu / Forward |
0.0000064793 s |
0.000006482825 s |
1.00 |
const_scatter / IDefOpt / tpu / Forward |
0.000006493600000000001 s |
0.00000645875 s |
1.01 |
const_scatter / Jax / tpu / BothRev |
0.000006623425 s |
0.0000066286750000000005 s |
1.00 |
const_scatter / JaXPipe / tpu / PreRev |
0.000006641974999999999 s |
0.000006622525000000001 s |
1.00 |
const_scatter / JaXPipe / tpu / PostRev |
0.000006620825 s |
0.000006631975 s |
1.00 |
const_scatter / JaXPipe / tpu / BothRev |
0.00000664145 s |
0.000006599350000000001 s |
1.01 |
const_scatter / PartOpt / tpu / PreRev |
0.000006590899999999999 s |
0.000006621200000000001 s |
1.00 |
const_scatter / PartOpt / tpu / PostRev |
0.0000066398 s |
0.00000661575 s |
1.00 |
const_scatter / PartOpt / tpu / BothRev |
0.000006595925 s |
0.00000662395 s |
1.00 |
const_scatter / IPartOpt / tpu / PreRev |
0.000006646025 s |
0.000006612 s |
1.01 |
const_scatter / IPartOpt / tpu / PostRev |
0.000006610374999999999 s |
0.0000066036 s |
1.00 |
const_scatter / IPartOpt / tpu / BothRev |
0.00000665035 s |
0.0000066035750000000006 s |
1.01 |
const_scatter / HLOOpt / tpu / PreRev |
0.000006626175 s |
0.00000662385 s |
1.00 |
const_scatter / HLOOpt / tpu / PostRev |
0.0000066213000000000005 s |
0.000006609475 s |
1.00 |
const_scatter / HLOOpt / tpu / BothRev |
0.0000065947000000000006 s |
0.000006623925 s |
1.00 |
const_scatter / DefOpt / tpu / PreRev |
0.0000066526 s |
0.000006590049999999999 s |
1.01 |
const_scatter / DefOpt / tpu / PostRev |
0.000006594925 s |
0.0000065854 s |
1.00 |
const_scatter / DefOpt / tpu / BothRev |
0.0000066444 s |
0.0000066295 s |
1.00 |
const_scatter / IDefOpt / tpu / PreRev |
0.000006605175 s |
0.00000660685 s |
1.00 |
const_scatter / IDefOpt / tpu / PostRev |
0.000006646275 s |
0.00000661475 s |
1.00 |
const_scatter / IDefOpt / tpu / BothRev |
0.000006616575 s |
0.000006601825 s |
1.00 |
const_scatter / Jax / cpu / Primal |
0.000013443 s |
0.000007548859975941014 s |
1.78 |
const_scatter / JaXPipe / cpu / Primal |
0.000013601 s |
0.000006842320008217939 s |
1.99 |
const_scatter / PartOpt / cpu / Primal |
0.000012664 s |
0.000006784740025977953 s |
1.87 |
const_scatter / IPartOpt / cpu / Primal |
0.000012657 s |
0.000007173680005507777 s |
1.76 |
const_scatter / HLOOpt / cpu / Primal |
0.000013449 s |
0.000008170320033968893 s |
1.65 |
const_scatter / DefOpt / cpu / Primal |
0.00001354 s |
0.000007593259997520363 s |
1.78 |
const_scatter / IDefOpt / cpu / Primal |
0.000013261 s |
0.000007684459988013259 s |
1.73 |
const_scatter / Jax / cpu / Forward |
0.000016879000000000002 s |
0.000011410720007916098 s |
1.48 |
const_scatter / JaXPipe / cpu / Forward |
0.00001782 s |
0.000011905840028703095 s |
1.50 |
const_scatter / PartOpt / cpu / Forward |
0.000017796 s |
0.0000117505800062645 s |
1.51 |
const_scatter / IPartOpt / cpu / Forward |
0.000018132 s |
0.0000122887799898308 s |
1.48 |
const_scatter / HLOOpt / cpu / Forward |
0.000017959 s |
0.000012375200003589271 s |
1.45 |
const_scatter / DefOpt / cpu / Forward |
0.000018153 s |
0.0000120592799885344 s |
1.51 |
const_scatter / IDefOpt / cpu / Forward |
0.000017971 s |
0.000011614740005825297 s |
1.55 |
const_scatter / Jax / cpu / BothRev |
0.000506958 s |
0.0002843011199638 s |
1.78 |
const_scatter / JaXPipe / cpu / PreRev |
0.000519011 s |
0.0002893409799889 s |
1.79 |
const_scatter / JaXPipe / cpu / PostRev |
0.000523888 s |
0.0002851822799402 s |
1.84 |
const_scatter / JaXPipe / cpu / BothRev |
0.00050128 s |
0.0002877293199799 s |
1.74 |
const_scatter / PartOpt / cpu / PreRev |
0.000513708 s |
0.0002882542400038 s |
1.78 |
const_scatter / PartOpt / cpu / PostRev |
0.000512856 s |
0.0002828643999964 s |
1.81 |
const_scatter / PartOpt / cpu / BothRev |
0.00050107 s |
0.0002836606200071 s |
1.77 |
const_scatter / IPartOpt / cpu / PreRev |
0.000516662 s |
0.0002861782600211 s |
1.81 |
const_scatter / IPartOpt / cpu / PostRev |
0.000511838 s |
0.0002866531799645 s |
1.79 |
const_scatter / IPartOpt / cpu / BothRev |
0.000511885 s |
0.0002857870600018 s |
1.79 |
const_scatter / HLOOpt / cpu / PreRev |
0.000504391 s |
0.0002843069400023 s |
1.77 |
const_scatter / HLOOpt / cpu / PostRev |
0.0005293139999999 s |
0.000288153240026 s |
1.84 |
const_scatter / HLOOpt / cpu / BothRev |
0.000523872 s |
0.0002838666400111 s |
1.85 |
const_scatter / DefOpt / cpu / PreRev |
0.000531192 s |
0.0002845654799966 s |
1.87 |
const_scatter / DefOpt / cpu / PostRev |
0.000518872 s |
0.0002846889000102 s |
1.82 |
const_scatter / DefOpt / cpu / BothRev |
0.000515576 s |
0.0002862369200192 s |
1.80 |
const_scatter / IDefOpt / cpu / PreRev |
0.00052459 s |
0.000284361999993 s |
1.84 |
const_scatter / IDefOpt / cpu / PostRev |
0.000530331 s |
0.0002850745399882 s |
1.86 |
const_scatter / IDefOpt / cpu / BothRev |
0.000497892 s |
0.0002843939999911 s |
1.75 |
const_scatter / Jax / cpu / Primal |
0.000008 s |
0.000007548859975941014 s |
1.06 |
const_scatter / JaXPipe / cpu / Primal |
0.000008 s |
0.000006842320008217939 s |
1.17 |
const_scatter / PartOpt / cpu / Primal |
0.000008 s |
0.000006784740025977953 s |
1.18 |
const_scatter / IPartOpt / cpu / Primal |
0.000008 s |
0.000007173680005507777 s |
1.12 |
const_scatter / HLOOpt / cpu / Primal |
0.000008999999999999999 s |
0.000008170320033968893 s |
1.10 |
const_scatter / DefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000007593259997520363 s |
1.19 |
const_scatter / IDefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000007684459988013259 s |
1.17 |
const_scatter / Jax / cpu / Forward |
0.000011 s |
0.000011410720007916098 s |
0.96 |
const_scatter / JaXPipe / cpu / Forward |
0.000013 s |
0.000011905840028703095 s |
1.09 |
const_scatter / PartOpt / cpu / Forward |
0.000012 s |
0.0000117505800062645 s |
1.02 |
const_scatter / IPartOpt / cpu / Forward |
0.000013 s |
0.0000122887799898308 s |
1.06 |
const_scatter / HLOOpt / cpu / Forward |
0.000012 s |
0.000012375200003589271 s |
0.97 |
const_scatter / DefOpt / cpu / Forward |
0.000013 s |
0.0000120592799885344 s |
1.08 |
const_scatter / IDefOpt / cpu / Forward |
0.000013 s |
0.000011614740005825297 s |
1.12 |
const_scatter / Jax / cpu / BothRev |
0.000364 s |
0.0002843011199638 s |
1.28 |
const_scatter / JaXPipe / cpu / PreRev |
0.000368 s |
0.0002893409799889 s |
1.27 |
const_scatter / JaXPipe / cpu / PostRev |
0.0003689999999999 s |
0.0002851822799402 s |
1.29 |
const_scatter / JaXPipe / cpu / BothRev |
0.0003689999999999 s |
0.0002877293199799 s |
1.28 |
const_scatter / PartOpt / cpu / PreRev |
0.000347 s |
0.0002882542400038 s |
1.20 |
const_scatter / PartOpt / cpu / PostRev |
0.00039 s |
0.0002828643999964 s |
1.38 |
const_scatter / PartOpt / cpu / BothRev |
0.000403 s |
0.0002836606200071 s |
1.42 |
const_scatter / IPartOpt / cpu / PreRev |
0.0004179999999999 s |
0.0002861782600211 s |
1.46 |
const_scatter / IPartOpt / cpu / PostRev |
0.000354 s |
0.0002866531799645 s |
1.23 |
const_scatter / IPartOpt / cpu / BothRev |
0.000383 s |
0.0002857870600018 s |
1.34 |
const_scatter / HLOOpt / cpu / PreRev |
0.0003529999999999 s |
0.0002843069400023 s |
1.24 |
const_scatter / HLOOpt / cpu / PostRev |
0.000343 s |
0.000288153240026 s |
1.19 |
const_scatter / HLOOpt / cpu / BothRev |
0.000332 s |
0.0002838666400111 s |
1.17 |
const_scatter / DefOpt / cpu / PreRev |
0.000386 s |
0.0002845654799966 s |
1.36 |
const_scatter / DefOpt / cpu / PostRev |
0.000337 s |
0.0002846889000102 s |
1.18 |
const_scatter / DefOpt / cpu / BothRev |
0.000368 s |
0.0002862369200192 s |
1.29 |
const_scatter / IDefOpt / cpu / PreRev |
0.000335 s |
0.000284361999993 s |
1.18 |
const_scatter / IDefOpt / cpu / PostRev |
0.000433 s |
0.0002850745399882 s |
1.52 |
const_scatter / IDefOpt / cpu / BothRev |
0.000342 s |
0.0002843939999911 s |
1.20 |
GenDot / Jax / cpu / Primal |
0.000007140220013752696 s |
0.000008939100025600055 s |
0.80 |
GenDot / JaXPipe / cpu / Primal |
0.000006777740009056288 s |
0.000009136419994320022 s |
0.74 |
GenDot / PartOpt / cpu / Primal |
0.000007503019996875082 s |
0.00000840610002342146 s |
0.89 |
GenDot / IPartOpt / cpu / Primal |
0.000006583799959116732 s |
0.000008393619991693412 s |
0.78 |
GenDot / HLOOpt / cpu / Primal |
0.00000721823999811022 s |
0.00000937842002713296 s |
0.77 |
GenDot / DefOpt / cpu / Primal |
0.000007215239984361687 s |
0.000008787400020082714 s |
0.82 |
GenDot / IDefOpt / cpu / Primal |
0.000006892519995744806 s |
0.000008077780030362192 s |
0.85 |
GenDot / Jax / cpu / Forward |
0.00000998017999336298 s |
0.00001215408001371543 s |
0.82 |
GenDot / JaXPipe / cpu / Forward |
0.000011222859993722525 s |
0.00001278371995795169 s |
0.88 |
GenDot / PartOpt / cpu / Forward |
0.000010720160016717273 s |
0.000013168640016374411 s |
0.81 |
GenDot / IPartOpt / cpu / Forward |
0.000010384860024714726 s |
0.000012963319986738498 s |
0.80 |
GenDot / HLOOpt / cpu / Forward |
0.00001100445998417854 s |
0.000013325959980647894 s |
0.83 |
GenDot / DefOpt / cpu / Forward |
0.000011288220039205045 s |
0.00001290447997234878 s |
0.87 |
GenDot / IDefOpt / cpu / Forward |
0.000010814599991135764 s |
0.000012347279953246471 s |
0.88 |
GenDot / Jax / cpu / BothRev |
0.00001058369999554998 s |
0.000011685120052788988 s |
0.91 |
GenDot / JaXPipe / cpu / PreRev |
0.000010755519979284144 s |
0.000012486799978432827 s |
0.86 |
GenDot / JaXPipe / cpu / PostRev |
0.000010759360038719024 s |
0.000010974139977406594 s |
0.98 |
GenDot / JaXPipe / cpu / BothRev |
0.000010995739976351616 s |
0.000013244699966890038 s |
0.83 |
GenDot / PartOpt / cpu / PreRev |
0.000010855360014829783 s |
0.000012681280022661667 s |
0.86 |
GenDot / PartOpt / cpu / PostRev |
0.000011859080013891798 s |
0.000011119320033685652 s |
1.07 |
GenDot / PartOpt / cpu / BothRev |
0.000010615880009936518 s |
0.0000128565000341041 s |
0.83 |
GenDot / IPartOpt / cpu / PreRev |
0.0000107433600078366 s |
0.000012805879996449222 s |
0.84 |
GenDot / IPartOpt / cpu / PostRev |
0.000010924759953923056 s |
0.000011597299971981556 s |
0.94 |
GenDot / IPartOpt / cpu / BothRev |
0.00001152634001300612 s |
0.000013051699979769185 s |
0.88 |
GenDot / HLOOpt / cpu / PreRev |
0.000010866259990507388 s |
0.00001274009998269321 s |
0.85 |
GenDot / HLOOpt / cpu / PostRev |
0.00001076518001354998 s |
0.000015062699985719518 s |
0.71 |
GenDot / HLOOpt / cpu / BothRev |
0.000010824279997905251 s |
0.000012676980022661156 s |
0.85 |
GenDot / DefOpt / cpu / PreRev |
0.000011220840069654517 s |
0.000012490140024965512 s |
0.90 |
GenDot / DefOpt / cpu / PostRev |
0.00001149008002357732 s |
0.000012669499974435891 s |
0.91 |
GenDot / DefOpt / cpu / BothRev |
0.00001081760003216914 s |
0.000012742800045089098 s |
0.85 |
GenDot / IDefOpt / cpu / PreRev |
0.000010744560013336011 s |
0.000012604300027305724 s |
0.85 |
GenDot / IDefOpt / cpu / PostRev |
0.000010967340040224372 s |
0.000012143400017521344 s |
0.90 |
GenDot / IDefOpt / cpu / BothRev |
0.00001060246001543419 s |
0.000012777719985024304 s |
0.83 |
GenDot / Jax / cuda / Primal |
0.000002015 s |
0.000002016 s |
1.00 |
GenDot / JaXPipe / cuda / Primal |
0.000002016 s |
0.000002016 s |
1 |
GenDot / PartOpt / cuda / Primal |
0.000002015 s |
0.000002015 s |
1 |
GenDot / IPartOpt / cuda / Primal |
0.000002016 s |
0.000002015 s |
1.00 |
GenDot / HLOOpt / cuda / Primal |
0.000001984 s |
0.000001984 s |
1 |
GenDot / DefOpt / cuda / Primal |
0.000001984 s |
0.000002016 s |
0.98 |
GenDot / IDefOpt / cuda / Primal |
0.000002015 s |
0.000002015 s |
1 |
GenDot / Jax / cuda / Forward |
0.000009792 s |
0.000009728 s |
1.01 |
GenDot / JaXPipe / cuda / Forward |
0.000009888 s |
0.00001008 s |
0.98 |
GenDot / PartOpt / cuda / Forward |
0.000009696 s |
0.000009791 s |
0.99 |
GenDot / IPartOpt / cuda / Forward |
0.00001104 s |
0.000009696 s |
1.14 |
GenDot / HLOOpt / cuda / Forward |
0.00001008 s |
0.000009856 s |
1.02 |
GenDot / DefOpt / cuda / Forward |
0.00001072 s |
0.00000944 s |
1.14 |
GenDot / IDefOpt / cuda / Forward |
0.000010433 s |
0.00000928 s |
1.12 |
GenDot / Jax / cuda / BothRev |
0.000011168 s |
0.000009856 s |
1.13 |
GenDot / JaXPipe / cuda / PreRev |
0.000009952 s |
0.000009568 s |
1.04 |
GenDot / JaXPipe / cuda / PostRev |
0.000010016 s |
0.000009952 s |
1.01 |
GenDot / JaXPipe / cuda / BothRev |
0.000009632 s |
0.000009888 s |
0.97 |
GenDot / PartOpt / cuda / PreRev |
0.000009824 s |
0.000009728 s |
1.01 |
GenDot / PartOpt / cuda / PostRev |
0.000009633 s |
0.000009664 s |
1.00 |
GenDot / PartOpt / cuda / BothRev |
0.000010048 s |
0.000009632 s |
1.04 |
GenDot / IPartOpt / cuda / PreRev |
0.000009728 s |
0.000009632 s |
1.01 |
GenDot / IPartOpt / cuda / PostRev |
0.000009697 s |
0.000009504 s |
1.02 |
GenDot / IPartOpt / cuda / BothRev |
0.000009888 s |
0.000009536 s |
1.04 |
GenDot / HLOOpt / cuda / PreRev |
0.00001008 s |
0.000009856 s |
1.02 |
GenDot / HLOOpt / cuda / PostRev |
0.000009472 s |
0.000009376 s |
1.01 |
GenDot / HLOOpt / cuda / BothRev |
0.000010144 s |
0.000010048 s |
1.01 |
GenDot / DefOpt / cuda / PreRev |
0.000010047 s |
0.000009536 s |
1.05 |
GenDot / DefOpt / cuda / PostRev |
0.000010144 s |
0.000009472 s |
1.07 |
GenDot / DefOpt / cuda / BothRev |
0.000009888 s |
0.000009793 s |
1.01 |
GenDot / IDefOpt / cuda / PreRev |
0.00001008 s |
0.00000928 s |
1.09 |
GenDot / IDefOpt / cuda / PostRev |
0.000010176 s |
0.000009759 s |
1.04 |
GenDot / IDefOpt / cuda / BothRev |
0.000010144 s |
0.000009888 s |
1.03 |
GenDot / Jax / tpu / Primal |
9.4355e-7 s |
9.2575e-7 s |
1.02 |
GenDot / JaXPipe / tpu / Primal |
9.301e-7 s |
9.3015e-7 s |
1.00 |
GenDot / PartOpt / tpu / Primal |
9.43e-7 s |
9.25575e-7 s |
1.02 |
GenDot / IPartOpt / tpu / Primal |
9.30025e-7 s |
9.30375e-7 s |
1.00 |
GenDot / HLOOpt / tpu / Primal |
0.00000159665 s |
0.000001571925 s |
1.02 |
GenDot / DefOpt / tpu / Primal |
0.000001499275 s |
0.000001487025 s |
1.01 |
GenDot / IDefOpt / tpu / Primal |
0.0000015945999999999995 s |
0.000001566975 s |
1.02 |
GenDot / Jax / tpu / Forward |
0.000002313525 s |
0.000002316875 s |
1.00 |
GenDot / JaXPipe / tpu / Forward |
0.0000031524750000000003 s |
0.000003157 s |
1.00 |
GenDot / PartOpt / tpu / Forward |
0.0000031078 s |
0.0000032048500000000003 s |
0.97 |
GenDot / IPartOpt / tpu / Forward |
0.0000031431 s |
0.0000031134250000000006 s |
1.01 |
GenDot / HLOOpt / tpu / Forward |
0.0000031204749999999995 s |
0.0000031079000000000003 s |
1.00 |
GenDot / DefOpt / tpu / Forward |
0.00000313495 s |
0.00000321465 s |
0.98 |
GenDot / IDefOpt / tpu / Forward |
0.000003122925 s |
0.00000311865 s |
1.00 |
GenDot / Jax / tpu / BothRev |
0.000002437125 s |
0.00000240435 s |
1.01 |
GenDot / JaXPipe / tpu / PreRev |
0.0000029426 s |
0.0000029508 s |
1.00 |
GenDot / JaXPipe / tpu / PostRev |
0.000002417 s |
0.0000023988 s |
1.01 |
GenDot / JaXPipe / tpu / BothRev |
0.000002939525 s |
0.00000295575 s |
0.99 |
GenDot / PartOpt / tpu / PreRev |
0.0000030111500000000004 s |
0.000002933975 s |
1.03 |
GenDot / PartOpt / tpu / PostRev |
0.000002381075 s |
0.000002391025 s |
1.00 |
GenDot / PartOpt / tpu / BothRev |
0.000003006725 s |
0.0000029292000000000003 s |
1.03 |
GenDot / IPartOpt / tpu / PreRev |
0.000002929425 s |
0.0000029615000000000004 s |
0.99 |
GenDot / IPartOpt / tpu / PostRev |
0.000002419925 s |
0.000002405875 s |
1.01 |
GenDot / IPartOpt / tpu / BothRev |
0.00000294985 s |
0.000002958875 s |
1.00 |
GenDot / HLOOpt / tpu / PreRev |
0.000003011075 s |
0.000002953375 s |
1.02 |
GenDot / HLOOpt / tpu / PostRev |
0.00000294275 s |
0.000002926775 s |
1.01 |
GenDot / HLOOpt / tpu / BothRev |
0.000003016925 s |
0.0000029604 s |
1.02 |
GenDot / DefOpt / tpu / PreRev |
0.000002933525 s |
0.00000293265 s |
1.00 |
GenDot / DefOpt / tpu / PostRev |
0.000003011225 s |
0.0000029616749999999995 s |
1.02 |
GenDot / DefOpt / tpu / BothRev |
0.0000029429250000000003 s |
0.000002943025 s |
1.00 |
GenDot / IDefOpt / tpu / PreRev |
0.0000030097 s |
0.00000296195 s |
1.02 |
GenDot / IDefOpt / tpu / PostRev |
0.000002939375 s |
0.000002926125 s |
1.00 |
GenDot / IDefOpt / tpu / BothRev |
0.0000030134499999999995 s |
0.000002955175 s |
1.02 |
GenDot / Jax / cpu / Primal |
0.000014554 s |
0.000008939100025600055 s |
1.63 |
GenDot / JaXPipe / cpu / Primal |
0.000014841 s |
0.000009136419994320022 s |
1.62 |
GenDot / PartOpt / cpu / Primal |
0.000014704 s |
0.00000840610002342146 s |
1.75 |
GenDot / IPartOpt / cpu / Primal |
0.000015243 s |
0.000008393619991693412 s |
1.82 |
GenDot / HLOOpt / cpu / Primal |
0.000014341 s |
0.00000937842002713296 s |
1.53 |
GenDot / DefOpt / cpu / Primal |
0.000014254 s |
0.000008787400020082714 s |
1.62 |
GenDot / IDefOpt / cpu / Primal |
0.00001413 s |
0.000008077780030362192 s |
1.75 |
GenDot / Jax / cpu / Forward |
0.000021455 s |
0.00001215408001371543 s |
1.77 |
GenDot / JaXPipe / cpu / Forward |
0.000019129 s |
0.00001278371995795169 s |
1.50 |
GenDot / PartOpt / cpu / Forward |
0.000019945 s |
0.000013168640016374411 s |
1.51 |
GenDot / IPartOpt / cpu / Forward |
0.000019503 s |
0.000012963319986738498 s |
1.50 |
GenDot / HLOOpt / cpu / Forward |
0.000019193 s |
0.000013325959980647894 s |
1.44 |
GenDot / DefOpt / cpu / Forward |
0.000019697 s |
0.00001290447997234878 s |
1.53 |
GenDot / IDefOpt / cpu / Forward |
0.000020563000000000003 s |
0.000012347279953246471 s |
1.67 |
GenDot / Jax / cpu / BothRev |
0.000020419 s |
0.000011685120052788988 s |
1.75 |
GenDot / JaXPipe / cpu / PreRev |
0.00001972 s |
0.000012486799978432827 s |
1.58 |
GenDot / JaXPipe / cpu / PostRev |
0.000020376 s |
0.000010974139977406594 s |
1.86 |
GenDot / JaXPipe / cpu / BothRev |
0.000019482 s |
0.000013244699966890038 s |
1.47 |
GenDot / PartOpt / cpu / PreRev |
0.000019163 s |
0.000012681280022661667 s |
1.51 |
GenDot / PartOpt / cpu / PostRev |
0.00002063 s |
0.000011119320033685652 s |
1.86 |
GenDot / PartOpt / cpu / BothRev |
0.00001986 s |
0.0000128565000341041 s |
1.54 |
GenDot / IPartOpt / cpu / PreRev |
0.000019492 s |
0.000012805879996449222 s |
1.52 |
GenDot / IPartOpt / cpu / PostRev |
0.000020553 s |
0.000011597299971981556 s |
1.77 |
GenDot / IPartOpt / cpu / BothRev |
0.000019627 s |
0.000013051699979769185 s |
1.50 |
GenDot / HLOOpt / cpu / PreRev |
0.000019299 s |
0.00001274009998269321 s |
1.51 |
GenDot / HLOOpt / cpu / PostRev |
0.00001912 s |
0.000015062699985719518 s |
1.27 |
GenDot / HLOOpt / cpu / BothRev |
0.000019184 s |
0.000012676980022661156 s |
1.51 |
GenDot / DefOpt / cpu / PreRev |
0.000030503 s |
0.000012490140024965512 s |
2.44 |
GenDot / DefOpt / cpu / PostRev |
0.000019242 s |
0.000012669499974435891 s |
1.52 |
GenDot / DefOpt / cpu / BothRev |
0.000019462 s |
0.000012742800045089098 s |
1.53 |
GenDot / IDefOpt / cpu / PreRev |
0.000018949 s |
0.000012604300027305724 s |
1.50 |
GenDot / IDefOpt / cpu / PostRev |
0.000019444 s |
0.000012143400017521344 s |
1.60 |
GenDot / IDefOpt / cpu / BothRev |
0.000019479 s |
0.000012777719985024304 s |
1.52 |
GenDot / Jax / cpu / Primal |
0.00001 s |
0.000008939100025600055 s |
1.12 |
GenDot / JaXPipe / cpu / Primal |
0.00001 s |
0.000009136419994320022 s |
1.09 |
GenDot / PartOpt / cpu / Primal |
0.00001 s |
0.00000840610002342146 s |
1.19 |
GenDot / IPartOpt / cpu / Primal |
0.00001 s |
0.000008393619991693412 s |
1.19 |
GenDot / HLOOpt / cpu / Primal |
0.00001 s |
0.00000937842002713296 s |
1.07 |
GenDot / DefOpt / cpu / Primal |
0.00001 s |
0.000008787400020082714 s |
1.14 |
GenDot / IDefOpt / cpu / Primal |
0.00001 s |
0.000008077780030362192 s |
1.24 |
GenDot / Jax / cpu / Forward |
0.000015 s |
0.00001215408001371543 s |
1.23 |
GenDot / JaXPipe / cpu / Forward |
0.000013 s |
0.00001278371995795169 s |
1.02 |
GenDot / PartOpt / cpu / Forward |
0.000014 s |
0.000013168640016374411 s |
1.06 |
GenDot / IPartOpt / cpu / Forward |
0.000013 s |
0.000012963319986738498 s |
1.00 |
GenDot / HLOOpt / cpu / Forward |
0.000014 s |
0.000013325959980647894 s |
1.05 |
GenDot / DefOpt / cpu / Forward |
0.000014 s |
0.00001290447997234878 s |
1.08 |
GenDot / IDefOpt / cpu / Forward |
0.000013 s |
0.000012347279953246471 s |
1.05 |
GenDot / Jax / cpu / BothRev |
0.000015 s |
0.000011685120052788988 s |
1.28 |
GenDot / JaXPipe / cpu / PreRev |
0.000014 s |
0.000012486799978432827 s |
1.12 |
GenDot / JaXPipe / cpu / PostRev |
0.000014 s |
0.000010974139977406594 s |
1.28 |
GenDot / JaXPipe / cpu / BothRev |
0.000014 s |
0.000013244699966890038 s |
1.06 |
GenDot / PartOpt / cpu / PreRev |
0.000014 s |
0.000012681280022661667 s |
1.10 |
GenDot / PartOpt / cpu / PostRev |
0.000015 s |
0.000011119320033685652 s |
1.35 |
GenDot / PartOpt / cpu / BothRev |
0.000014 s |
0.0000128565000341041 s |
1.09 |
GenDot / IPartOpt / cpu / PreRev |
0.000015 s |
0.000012805879996449222 s |
1.17 |
GenDot / IPartOpt / cpu / PostRev |
0.000017999999999999997 s |
0.000011597299971981556 s |
1.55 |
GenDot / IPartOpt / cpu / BothRev |
0.000014 s |
0.000013051699979769185 s |
1.07 |
GenDot / HLOOpt / cpu / PreRev |
0.000014 s |
0.00001274009998269321 s |
1.10 |
GenDot / HLOOpt / cpu / PostRev |
0.000045 s |
0.000015062699985719518 s |
2.99 |
GenDot / HLOOpt / cpu / BothRev |
0.000014 s |
0.000012676980022661156 s |
1.10 |
GenDot / DefOpt / cpu / PreRev |
0.000015 s |
0.000012490140024965512 s |
1.20 |
GenDot / DefOpt / cpu / PostRev |
0.000014 s |
0.000012669499974435891 s |
1.11 |
GenDot / DefOpt / cpu / BothRev |
0.000046 s |
0.000012742800045089098 s |
3.61 |
GenDot / IDefOpt / cpu / PreRev |
0.000014 s |
0.000012604300027305724 s |
1.11 |
GenDot / IDefOpt / cpu / PostRev |
0.000014 s |
0.000012143400017521344 s |
1.15 |
GenDot / IDefOpt / cpu / BothRev |
0.000014 s |
0.000012777719985024304 s |
1.10 |
hlo_ffi / Jax / cpu / Primal |
0.000011394920011298382 s |
0.000011390040008336656 s |
1.00 |
hlo_ffi / JaXPipe / cpu / Primal |
0.00001086426000256324 s |
0.000011769219991037972 s |
0.92 |
hlo_ffi / PartOpt / cpu / Primal |
0.000010733499957495953 s |
0.000010834639997483464 s |
0.99 |
hlo_ffi / IPartOpt / cpu / Primal |
0.000010180999997828622 s |
0.000011298039999019238 s |
0.90 |
hlo_ffi / HLOOpt / cpu / Primal |
0.000011371640021025086 s |
0.00001107128002331592 s |
1.03 |
hlo_ffi / DefOpt / cpu / Primal |
0.000010911280005529989 s |
0.000010621599985825014 s |
1.03 |
hlo_ffi / IDefOpt / cpu / Primal |
0.00001037781999912113 s |
0.000010755800030892714 s |
0.96 |
hlo_ffi / Jax / cpu / Forward |
0.000016466480001327 s |
0.000016056699996624958 s |
1.03 |
hlo_ffi / JaXPipe / cpu / Forward |
0.000016425720032202664 s |
0.000016757680014052313 s |
0.98 |
hlo_ffi / PartOpt / cpu / Forward |
0.00001703185999758716 s |
0.000015897820067038992 s |
1.07 |
hlo_ffi / IPartOpt / cpu / Forward |
0.000016086460018414073 s |
0.000016493580014866895 s |
0.98 |
hlo_ffi / HLOOpt / cpu / Forward |
0.00001597605995812046 s |
0.000016304439968735094 s |
0.98 |
hlo_ffi / DefOpt / cpu / Forward |
0.000015901599972494296 s |
0.0000166749799700483 s |
0.95 |
hlo_ffi / IDefOpt / cpu / Forward |
0.00001648333995944995 s |
0.00001626992002456973 s |
1.01 |
hlo_ffi / Jax / cpu / BothRev |
0.00001659051999922667 s |
0.000016992420014503296 s |
0.98 |
hlo_ffi / JaXPipe / cpu / PreRev |
0.000016041440030676313 s |
0.000016673420032020658 s |
0.96 |
hlo_ffi / JaXPipe / cpu / PostRev |
0.000015255659964168444 s |
0.000014827939985480045 s |
1.03 |
hlo_ffi / JaXPipe / cpu / BothRev |
0.000015623399976902875 s |
0.00001554261997625872 s |
1.01 |
hlo_ffi / PartOpt / cpu / PreRev |
0.00001634271999137127 s |
0.000016054180032369914 s |
1.02 |
hlo_ffi / PartOpt / cpu / PostRev |
0.00001903620000121009 s |
0.000019289579959149703 s |
0.99 |
hlo_ffi / PartOpt / cpu / BothRev |
0.00001507417998254823 s |
0.00001536798000415729 s |
0.98 |
hlo_ffi / IPartOpt / cpu / PreRev |
0.00001657564002016443 s |
0.00001672369996413181 s |
0.99 |
hlo_ffi / IPartOpt / cpu / PostRev |
0.00001545839999380405 s |
0.0000154835399644071 s |
1.00 |
hlo_ffi / IPartOpt / cpu / BothRev |
0.000015703100034443194 s |
0.000016247380035565584 s |
0.97 |
hlo_ffi / HLOOpt / cpu / PreRev |
0.000016196799997487687 s |
0.000016757339963078267 s |
0.97 |
hlo_ffi / HLOOpt / cpu / PostRev |
0.000015392840023196186 s |
0.00001766755997778091 s |
0.87 |
hlo_ffi / HLOOpt / cpu / BothRev |
0.000015630920006515226 s |
0.000015197859993349991 s |
1.03 |
hlo_ffi / DefOpt / cpu / PreRev |
0.000016644300003463287 s |
0.00001578282000082254 s |
1.05 |
hlo_ffi / DefOpt / cpu / PostRev |
0.00001573785999426036 s |
0.000015375199964182685 s |
1.02 |
hlo_ffi / DefOpt / cpu / BothRev |
0.000015420659992742002 s |
0.000015243000007103548 s |
1.01 |
hlo_ffi / IDefOpt / cpu / PreRev |
0.000015622040027665207 s |
0.000016734960063331527 s |
0.93 |
hlo_ffi / IDefOpt / cpu / PostRev |
0.00001556674001221836 s |
0.00001536071995360544 s |
1.01 |
hlo_ffi / IDefOpt / cpu / BothRev |
0.000014806859981035814 s |
0.000015463039990208926 s |
0.96 |
hlo_ffi / Jax / cuda / Primal |
0.000001983 s |
0.000001952 s |
1.02 |
hlo_ffi / JaXPipe / cuda / Primal |
0.000001983 s |
0.000001952 s |
1.02 |
hlo_ffi / PartOpt / cuda / Primal |
0.000001983 s |
0.000001983 s |
1 |
hlo_ffi / IPartOpt / cuda / Primal |
0.000001983 s |
0.000001983 s |
1 |
hlo_ffi / HLOOpt / cuda / Primal |
0.000001983 s |
0.000001984 s |
1.00 |
hlo_ffi / DefOpt / cuda / Primal |
0.000001983 s |
0.000001952 s |
1.02 |
hlo_ffi / IDefOpt / cuda / Primal |
0.000001983 s |
0.000001952 s |
1.02 |
hlo_ffi / Jax / cuda / Forward |
0.000002049 s |
0.000002047 s |
1.00 |
hlo_ffi / JaXPipe / cuda / Forward |
0.000002048 s |
0.000002047 s |
1.00 |
hlo_ffi / PartOpt / cuda / Forward |
0.000002048 s |
0.000002047 s |
1.00 |
hlo_ffi / IPartOpt / cuda / Forward |
0.000002048 s |
0.000002047 s |
1.00 |
hlo_ffi / HLOOpt / cuda / Forward |
0.000002048 s |
0.000002048 s |
1 |
hlo_ffi / DefOpt / cuda / Forward |
0.000002048 s |
0.000002047 s |
1.00 |
hlo_ffi / IDefOpt / cuda / Forward |
0.000002048 s |
0.000002047 s |
1.00 |
hlo_ffi / Jax / cuda / BothRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / JaXPipe / cuda / PreRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / JaXPipe / cuda / PostRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / JaXPipe / cuda / BothRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / PartOpt / cuda / PreRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / PartOpt / cuda / PostRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / PartOpt / cuda / BothRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / IPartOpt / cuda / PreRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / IPartOpt / cuda / PostRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / IPartOpt / cuda / BothRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / HLOOpt / cuda / PreRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / HLOOpt / cuda / PostRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / HLOOpt / cuda / BothRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / DefOpt / cuda / PreRev |
0.000002048 s |
0.000002047 s |
1.00 |
hlo_ffi / DefOpt / cuda / PostRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / DefOpt / cuda / BothRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / IDefOpt / cuda / PreRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / IDefOpt / cuda / PostRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / IDefOpt / cuda / BothRev |
0.000002047 s |
0.000002047 s |
1 |
hlo_ffi / Jax / tpu / Primal |
9.1705e-7 s |
9.5445e-7 s |
0.96 |
hlo_ffi / JaXPipe / tpu / Primal |
9.53475e-7 s |
9.29025e-7 s |
1.03 |
hlo_ffi / PartOpt / tpu / Primal |
9.21975e-7 s |
9.53725e-7 s |
0.97 |
hlo_ffi / IPartOpt / tpu / Primal |
9.5655e-7 s |
9.1555e-7 s |
1.04 |
hlo_ffi / HLOOpt / tpu / Primal |
9.1695e-7 s |
9.07425e-7 s |
1.01 |
hlo_ffi / DefOpt / tpu / Primal |
9.51725e-7 s |
9.55225e-7 s |
1.00 |
hlo_ffi / IDefOpt / tpu / Primal |
9.176e-7 s |
9.09475e-7 s |
1.01 |
hlo_ffi / Jax / tpu / Forward |
9.49475e-7 s |
9.81125e-7 s |
0.97 |
hlo_ffi / JaXPipe / tpu / Forward |
9.81725e-7 s |
9.492e-7 s |
1.03 |
hlo_ffi / PartOpt / tpu / Forward |
9.74075e-7 s |
9.34175e-7 s |
1.04 |
hlo_ffi / IPartOpt / tpu / Forward |
9.472e-7 s |
9.74175e-7 s |
0.97 |
hlo_ffi / HLOOpt / tpu / Forward |
9.73625e-7 s |
9.7465e-7 s |
1.00 |
hlo_ffi / DefOpt / tpu / Forward |
9.46525e-7 s |
9.33975e-7 s |
1.01 |
hlo_ffi / IDefOpt / tpu / Forward |
9.73875e-7 s |
9.74625e-7 s |
1.00 |
hlo_ffi / Jax / tpu / BothRev |
9.35425e-7 s |
9.65e-7 s |
0.97 |
hlo_ffi / JaXPipe / tpu / PreRev |
9.652e-7 s |
9.3795e-7 s |
1.03 |
hlo_ffi / JaXPipe / tpu / PostRev |
9.822749999999998e-7 s |
9.657499999999998e-7 s |
1.02 |
hlo_ffi / JaXPipe / tpu / BothRev |
9.65125e-7 s |
9.62875e-7 s |
1.00 |
hlo_ffi / PartOpt / tpu / PreRev |
9.8245e-7 s |
9.6495e-7 s |
1.02 |
hlo_ffi / PartOpt / tpu / PostRev |
9.6475e-7 s |
9.625749999999998e-7 s |
1.00 |
hlo_ffi / PartOpt / tpu / BothRev |
9.82325e-7 s |
9.65425e-7 s |
1.02 |
hlo_ffi / IPartOpt / tpu / PreRev |
9.6505e-7 s |
9.6275e-7 s |
1.00 |
hlo_ffi / IPartOpt / tpu / PostRev |
9.82325e-7 s |
9.650749999999998e-7 s |
1.02 |
hlo_ffi / IPartOpt / tpu / BothRev |
9.649e-7 s |
9.62725e-7 s |
1.00 |
hlo_ffi / HLOOpt / tpu / PreRev |
9.82425e-7 s |
9.625250000000002e-7 s |
1.02 |
hlo_ffi / HLOOpt / tpu / PostRev |
9.6475e-7 s |
9.647e-7 s |
1.00 |
hlo_ffi / HLOOpt / tpu / BothRev |
9.825e-7 s |
9.618e-7 s |
1.02 |
hlo_ffi / DefOpt / tpu / PreRev |
9.6515e-7 s |
9.65325e-7 s |
1.00 |
hlo_ffi / DefOpt / tpu / PostRev |
9.8215e-7 s |
9.6215e-7 s |
1.02 |
hlo_ffi / DefOpt / tpu / BothRev |
9.649e-7 s |
9.652e-7 s |
1.00 |
hlo_ffi / IDefOpt / tpu / PreRev |
9.8205e-7 s |
9.624e-7 s |
1.02 |
hlo_ffi / IDefOpt / tpu / PostRev |
9.64875e-7 s |
9.654749999999998e-7 s |
1.00 |
hlo_ffi / IDefOpt / tpu / BothRev |
9.82025e-7 s |
9.625e-7 s |
1.02 |
hlo_ffi / Jax / cpu / Primal |
0.000017583 s |
0.000011390040008336656 s |
1.54 |
hlo_ffi / JaXPipe / cpu / Primal |
0.000017416 s |
0.000011769219991037972 s |
1.48 |
hlo_ffi / PartOpt / cpu / Primal |
0.00001731 s |
0.000010834639997483464 s |
1.60 |
hlo_ffi / IPartOpt / cpu / Primal |
0.000016958999999999998 s |
0.000011298039999019238 s |
1.50 |
hlo_ffi / HLOOpt / cpu / Primal |
0.000017456 s |
0.00001107128002331592 s |
1.58 |
hlo_ffi / DefOpt / cpu / Primal |
0.000017317 s |
0.000010621599985825014 s |
1.63 |
hlo_ffi / IDefOpt / cpu / Primal |
0.000017602 s |
0.000010755800030892714 s |
1.64 |
hlo_ffi / Jax / cpu / Forward |
0.000024398 s |
0.000016056699996624958 s |
1.52 |
hlo_ffi / JaXPipe / cpu / Forward |
0.000023765 s |
0.000016757680014052313 s |
1.42 |
hlo_ffi / PartOpt / cpu / Forward |
0.000023845000000000003 s |
0.000015897820067038992 s |
1.50 |
hlo_ffi / IPartOpt / cpu / Forward |
0.000024387 s |
0.000016493580014866895 s |
1.48 |
hlo_ffi / HLOOpt / cpu / Forward |
0.0000242 s |
0.000016304439968735094 s |
1.48 |
hlo_ffi / DefOpt / cpu / Forward |
0.000023876 s |
0.0000166749799700483 s |
1.43 |
hlo_ffi / IDefOpt / cpu / Forward |
0.000023949 s |
0.00001626992002456973 s |
1.47 |
hlo_ffi / Jax / cpu / BothRev |
0.000023982 s |
0.000016992420014503296 s |
1.41 |
hlo_ffi / JaXPipe / cpu / PreRev |
0.000023549 s |
0.000016673420032020658 s |
1.41 |
hlo_ffi / JaXPipe / cpu / PostRev |
0.000023876 s |
0.000014827939985480045 s |
1.61 |
hlo_ffi / JaXPipe / cpu / BothRev |
0.000023167 s |
0.00001554261997625872 s |
1.49 |
hlo_ffi / PartOpt / cpu / PreRev |
0.000023899 s |
0.000016054180032369914 s |
1.49 |
hlo_ffi / PartOpt / cpu / PostRev |
0.000024954 s |
0.000019289579959149703 s |
1.29 |
hlo_ffi / PartOpt / cpu / BothRev |
0.000023901 s |
0.00001536798000415729 s |
1.56 |
hlo_ffi / IPartOpt / cpu / PreRev |
0.000023737 s |
0.00001672369996413181 s |
1.42 |
hlo_ffi / IPartOpt / cpu / PostRev |
0.00002356 s |
0.0000154835399644071 s |
1.52 |
hlo_ffi / IPartOpt / cpu / BothRev |
0.000024438 s |
0.000016247380035565584 s |
1.50 |
hlo_ffi / HLOOpt / cpu / PreRev |
0.000023913 s |
0.000016757339963078267 s |
1.43 |
hlo_ffi / HLOOpt / cpu / PostRev |
0.000024415 s |
0.00001766755997778091 s |
1.38 |
hlo_ffi / HLOOpt / cpu / BothRev |
0.000024191 s |
0.000015197859993349991 s |
1.59 |
hlo_ffi / DefOpt / cpu / PreRev |
0.000024389 s |
0.00001578282000082254 s |
1.55 |
hlo_ffi / DefOpt / cpu / PostRev |
0.000024242 s |
0.000015375199964182685 s |
1.58 |
hlo_ffi / DefOpt / cpu / BothRev |
0.000024158 s |
0.000015243000007103548 s |
1.58 |
hlo_ffi / IDefOpt / cpu / PreRev |
0.000024016 s |
0.000016734960063331527 s |
1.44 |
hlo_ffi / IDefOpt / cpu / PostRev |
0.000024484 s |
0.00001536071995360544 s |
1.59 |
hlo_ffi / IDefOpt / cpu / BothRev |
0.00002474 s |
0.000015463039990208926 s |
1.60 |
hlo_ffi / Jax / cpu / Primal |
0.000013 s |
0.000011390040008336656 s |
1.14 |
hlo_ffi / JaXPipe / cpu / Primal |
0.000013 s |
0.000011769219991037972 s |
1.10 |
hlo_ffi / PartOpt / cpu / Primal |
0.000013 s |
0.000010834639997483464 s |
1.20 |
hlo_ffi / IPartOpt / cpu / Primal |
0.000013 s |
0.000011298039999019238 s |
1.15 |
hlo_ffi / HLOOpt / cpu / Primal |
0.000013 s |
0.00001107128002331592 s |
1.17 |
hlo_ffi / DefOpt / cpu / Primal |
0.000013 s |
0.000010621599985825014 s |
1.22 |
hlo_ffi / IDefOpt / cpu / Primal |
0.000012 s |
0.000010755800030892714 s |
1.12 |
hlo_ffi / Jax / cpu / Forward |
0.000017 s |
0.000016056699996624958 s |
1.06 |
hlo_ffi / JaXPipe / cpu / Forward |
0.000017 s |
0.000016757680014052313 s |
1.01 |
hlo_ffi / PartOpt / cpu / Forward |
0.000017999999999999997 s |
0.000015897820067038992 s |
1.13 |
hlo_ffi / IPartOpt / cpu / Forward |
0.000017999999999999997 s |
0.000016493580014866895 s |
1.09 |
hlo_ffi / HLOOpt / cpu / Forward |
0.000017 s |
0.000016304439968735094 s |
1.04 |
hlo_ffi / DefOpt / cpu / Forward |
0.000017999999999999997 s |
0.0000166749799700483 s |
1.08 |
hlo_ffi / IDefOpt / cpu / Forward |
0.000017999999999999997 s |
0.00001626992002456973 s |
1.11 |
hlo_ffi / Jax / cpu / BothRev |
0.000017 s |
0.000016992420014503296 s |
1.00 |
hlo_ffi / JaXPipe / cpu / PreRev |
0.000017 s |
0.000016673420032020658 s |
1.02 |
hlo_ffi / JaXPipe / cpu / PostRev |
0.000017999999999999997 s |
0.000014827939985480045 s |
1.21 |
hlo_ffi / JaXPipe / cpu / BothRev |
0.000019 s |
0.00001554261997625872 s |
1.22 |
hlo_ffi / PartOpt / cpu / PreRev |
0.000017999999999999997 s |
0.000016054180032369914 s |
1.12 |
hlo_ffi / PartOpt / cpu / PostRev |
0.000017 s |
0.000019289579959149703 s |
0.88 |
hlo_ffi / PartOpt / cpu / BothRev |
0.000017999999999999997 s |
0.00001536798000415729 s |
1.17 |
hlo_ffi / IPartOpt / cpu / PreRev |
0.000017 s |
0.00001672369996413181 s |
1.02 |
hlo_ffi / IPartOpt / cpu / PostRev |
0.000017999999999999997 s |
0.0000154835399644071 s |
1.16 |
hlo_ffi / IPartOpt / cpu / BothRev |
0.000017 s |
0.000016247380035565584 s |
1.05 |
hlo_ffi / HLOOpt / cpu / PreRev |
0.000017999999999999997 s |
0.000016757339963078267 s |
1.07 |
hlo_ffi / HLOOpt / cpu / PostRev |
0.000017999999999999997 s |
0.00001766755997778091 s |
1.02 |
hlo_ffi / HLOOpt / cpu / BothRev |
0.000017 s |
0.000015197859993349991 s |
1.12 |
hlo_ffi / DefOpt / cpu / PreRev |
0.000017 s |
0.00001578282000082254 s |
1.08 |
hlo_ffi / DefOpt / cpu / PostRev |
0.000017999999999999997 s |
0.000015375199964182685 s |
1.17 |
hlo_ffi / DefOpt / cpu / BothRev |
0.000017 s |
0.000015243000007103548 s |
1.12 |
hlo_ffi / IDefOpt / cpu / PreRev |
0.000017 s |
0.000016734960063331527 s |
1.02 |
hlo_ffi / IDefOpt / cpu / PostRev |
0.000017 s |
0.00001536071995360544 s |
1.11 |
hlo_ffi / IDefOpt / cpu / BothRev |
0.000017 s |
0.000015463039990208926 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 |
0.0008949580000262 s |
0.0009418846000698 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 / JaXPipe / cpu / Primal |
0.000893846999952 s |
0.0011267505998148 s |
0.79 |
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 |
0.0008984821998637 s |
0.0011027717998331 s |
0.81 |
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 |
0.0008737329999348 s |
0.0011475706000965 s |
0.76 |
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 |
0.00096198859992 s |
0.0010541087999627 s |
0.91 |
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 |
0.0009599488000276 s |
0.0011051118000068 s |
0.87 |
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 |
0.0009495911998783 s |
0.0011550227999578 s |
0.82 |
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 |
0.0022024286001396 s |
0.0029001091998907 s |
0.76 |
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 |
0.002176992600107 s |
0.0026810323999598 s |
0.81 |
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 |
0.0021062134000203 s |
0.0024966237999251 s |
0.84 |
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 |
0.0021166849999644 s |
0.0025083886000174 s |
0.84 |
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 |
0.0020862579999629 s |
0.0026212021999526 s |
0.80 |
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 |
0.0020943618000274 s |
0.0025393892000465 s |
0.82 |
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 |
0.0021580178000476 s |
0.0027567053999518 s |
0.78 |
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 |
0.0056533694000791 s |
0.0065450790000795 s |
0.86 |
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 |
0.0054500458000802 s |
0.0072784822001267 s |
0.75 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / PostRev |
0.0051895758000682 s |
0.0069289246000153 s |
0.75 |
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 |
0.00358839419996 s |
0.0065746002000196 s |
0.55 |
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 |
0.0053741677999823 s |
0.0061067225999067 s |
0.88 |
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 |
0.0033909232000041 s |
0.006158757600042 s |
0.55 |
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 |
0.0055491877999884 s |
0.0063330867998956 s |
0.88 |
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 |
0.0032990182000503 s |
0.0058289966001211 s |
0.57 |
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 |
0.0055657676000009 s |
0.0063528508000672 s |
0.88 |
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 |
0.0032082142000945 s |
0.0056682509999518 s |
0.57 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / PreRev |
0.0045261958000992 s |
0.0067159168001126 s |
0.67 |
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 |
0.0031025229999613 s |
0.0037599254001179 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 / HLOOpt / cpu / BothRev |
0.0055902780000906 s |
0.005835021599978 s |
0.96 |
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 |
0.00329169539973 s |
0.0062407683998571 s |
0.53 |
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 |
0.0043648945999848 s |
0.005692110000109 s |
0.77 |
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 |
0.0032054819999757 s |
0.0059548058000473 s |
0.54 |
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 |
0.0056596548000925 s |
0.005899918400064 s |
0.96 |
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 |
0.0032415286000286 s |
0.0052036910001334 s |
0.62 |
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 |
0.0045769203999952 s |
0.0063195202000315 s |
0.72 |
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 |
0.000283489 s |
0.000284094 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 / cuda / Primal |
0.000280385 s |
0.000284158 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 / PartOpt / cuda / Primal |
0.000284097 s |
0.000282494 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 / IPartOpt / cuda / Primal |
0.000281569 s |
0.000283006 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 / HLOOpt / cuda / Primal |
0.0002904959999999 s |
0.000290462 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 / cuda / Primal |
0.0002906889999999 s |
0.000289405 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 / cuda / Primal |
0.000289088 s |
0.00029075 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 / Jax / cuda / Forward |
0.00054093 s |
0.0005427149999999 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 / cuda / Forward |
0.000559233 s |
0.000560156 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 / cuda / Forward |
0.00055949 s |
0.000560283 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 / cuda / Forward |
0.000559265 s |
0.000560795 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 / cuda / Forward |
0.000560417 s |
0.000560763 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 / cuda / Forward |
0.000558881 s |
0.000560348 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 / cuda / Forward |
0.000559553 s |
0.000561148 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 / cuda / BothRev |
0.000991938 s |
0.000997399 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 / JaXPipe / cuda / PreRev |
0.001027874 s |
0.001034327 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 / JaXPipe / cuda / PostRev |
0.00099037 s |
0.000992599 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 / cuda / BothRev |
0.0010293779999999 s |
0.001026936 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 / cuda / PreRev |
0.0010273939999999 s |
0.001033015 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 / PartOpt / cuda / PostRev |
0.000981474 s |
0.000983607 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 / cuda / BothRev |
0.001025026 s |
0.00103452 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 / cuda / PreRev |
0.001031714 s |
0.0010326 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 / cuda / PostRev |
0.000980899 s |
0.000980727 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 / cuda / BothRev |
0.001030851 s |
0.001032823 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 / cuda / PreRev |
0.001018434 s |
0.001018808 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 / cuda / PostRev |
0.00104781 s |
0.001043767 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 / cuda / BothRev |
0.001016802 s |
0.001016216 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 / cuda / PreRev |
0.001026851 s |
0.001029592 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 / cuda / PostRev |
0.000964098 s |
0.0009675759999999 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 / cuda / BothRev |
0.001027106 s |
0.001031735 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 / cuda / PreRev |
0.001025314 s |
0.00102364 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 / cuda / PostRev |
0.001024418 s |
0.00102812 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 / cuda / BothRev |
0.0010258259999999 s |
0.0010308399999999 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 / Primal |
0.0001241025 s |
0.00012627875 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 / JaXPipe / tpu / Primal |
0.00012692025 s |
0.0001236115 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 |
0.00013136225 s |
0.00013420725 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 |
0.000134294 s |
0.0001311715 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 / tpu / Primal |
0.000152829 s |
0.0001527022499999 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 / Primal |
0.00014782425 s |
0.00014800375 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 / Primal |
0.000150752 s |
0.000150843 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 / Forward |
0.0002605185 s |
0.000261026 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 / Forward |
0.0002182354999999 s |
0.00021210625 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 / Forward |
0.0002120864999999 s |
0.0002183129999999 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 / IPartOpt / tpu / Forward |
0.000218071 s |
0.00021214525 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 / HLOOpt / tpu / Forward |
0.00021210975 s |
0.0002117882499999 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 / Forward |
0.000217937 s |
0.00021827375 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 |
0.00021215125 s |
0.00021204925 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 |
0.00025706725 s |
0.00025923775 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 / JaXPipe / tpu / PreRev |
0.000358622 s |
0.0003565605 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 / JaXPipe / tpu / PostRev |
0.00025749 s |
0.0002593045 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 / JaXPipe / tpu / BothRev |
0.00035797075 s |
0.00035667 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 |
0.0003574739999999 s |
0.00035846425 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 |
0.0002749275 s |
0.00027207375 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 / PartOpt / tpu / BothRev |
0.000357146 s |
0.0003585587499999 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 |
0.00035804 s |
0.0003570305 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 |
0.000272754 s |
0.00027476175 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 / tpu / BothRev |
0.00035767325 s |
0.00035703525 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 |
0.00035735175 s |
0.00035666175 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 |
0.0002918235 s |
0.0002918622499999 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 |
0.0003571935 s |
0.00035662875 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 |
0.00035971275 s |
0.0003595432499999 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 |
0.00028415875 s |
0.00028369525 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 |
0.0003592155 s |
0.00035994525 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 |
0.00035877725 s |
0.00035769625 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 |
0.00030213975 s |
0.00030205625 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 |
0.0003585317499999 s |
0.00035778875 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 / cpu / Primal |
0.002267592 s |
0.0009418846000698 s |
2.41 |
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 |
0.002124465 s |
0.0011267505998148 s |
1.89 |
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 |
0.002208796 s |
0.0011027717998331 s |
2.00 |
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 |
0.001987262 s |
0.0011475706000965 s |
1.73 |
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 |
0.002193624 s |
0.0010541087999627 s |
2.08 |
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 |
0.002222865 s |
0.0011051118000068 s |
2.01 |
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 |
0.001988659 s |
0.0011550227999578 s |
1.72 |
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 |
0.005898812 s |
0.0029001091998907 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 / Forward |
0.005220397 s |
0.0026810323999598 s |
1.95 |
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 |
0.0057575269999999 s |
0.0024966237999251 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 / IPartOpt / cpu / Forward |
0.004851133 s |
0.0025083886000174 s |
1.93 |
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 |
0.005821281 s |
0.0026212021999526 s |
2.22 |
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 |
0.00544065 s |
0.0025393892000465 s |
2.14 |
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 |
0.0052270469999999 s |
0.0027567053999518 s |
1.90 |
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 |
0.0095339539999999 s |
0.0065450790000795 s |
1.46 |
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 |
0.011146682 s |
0.0072784822001267 s |
1.53 |
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 |
0.0092357899999999 s |
0.0069289246000153 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 / cpu / BothRev |
0.009222717 s |
0.0065746002000196 s |
1.40 |
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 |
0.008551747 s |
0.0061067225999067 s |
1.40 |
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 |
0.009512306 s |
0.006158757600042 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 / BothRev |
0.01000552 s |
0.0063330867998956 s |
1.58 |
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 |
0.00730796 s |
0.0058289966001211 s |
1.25 |
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 |
0.008528508 s |
0.0063528508000672 s |
1.34 |
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 |
0.007909328 s |
0.0056682509999518 s |
1.40 |
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 |
0.008324985 s |
0.0067159168001126 s |
1.24 |
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 |
0.007889822 s |
0.0037599254001179 s |
2.10 |
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 |
0.007298245 s |
0.005835021599978 s |
1.25 |
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 |
0.009568419 s |
0.0062407683998571 s |
1.53 |
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 |
0.008053227 s |
0.005692110000109 s |
1.41 |
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 |
0.0081150699999999 s |
0.0059548058000473 s |
1.36 |
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 |
0.009523483 s |
0.005899918400064 s |
1.61 |
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 |
0.008017892 s |
0.0052036910001334 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 / IDefOpt / cpu / BothRev |
0.0085557149999999 s |
0.0063195202000315 s |
1.35 |
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 |
0.003487 s |
0.0009418846000698 s |
3.70 |
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 |
0.002232 s |
0.0011267505998148 s |
1.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / Primal |
0.002221 s |
0.0011027717998331 s |
2.01 |
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 |
0.0017729999999999 s |
0.0011475706000965 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 / HLOOpt / cpu / Primal |
0.0023039999999999 s |
0.0010541087999627 s |
2.19 |
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 |
0.0017749999999999 s |
0.0011051118000068 s |
1.61 |
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 |
0.0021 s |
0.0011550227999578 s |
1.82 |
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 |
0.0068319999999999 s |
0.0029001091998907 s |
2.36 |
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 |
0.010836 s |
0.0026810323999598 s |
4.04 |
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 |
0.005143 s |
0.0024966237999251 s |
2.06 |
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 |
0.005652 s |
0.0025083886000174 s |
2.25 |
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 |
0.006633 s |
0.0026212021999526 s |
2.53 |
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 |
0.004893 s |
0.0025393892000465 s |
1.93 |
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 |
0.005337 s |
0.0027567053999518 s |
1.94 |
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 |
0.01868 s |
0.0065450790000795 s |
2.85 |
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 |
0.014119 s |
0.0072784822001267 s |
1.94 |
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 |
0.027586 s |
0.0069289246000153 s |
3.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / BothRev |
0.017468 s |
0.0065746002000196 s |
2.66 |
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 |
0.008875 s |
0.0061067225999067 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 / PartOpt / cpu / PostRev |
0.033865 s |
0.006158757600042 s |
5.50 |
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 |
0.014343 s |
0.0063330867998956 s |
2.26 |
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 |
0.01149 s |
0.0058289966001211 s |
1.97 |
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 |
0.011244 s |
0.0063528508000672 s |
1.77 |
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 |
0.009076 s |
0.0056682509999518 s |
1.60 |
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 |
0.016031 s |
0.0067159168001126 s |
2.39 |
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 |
0.0151899999999999 s |
0.0037599254001179 s |
4.04 |
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 |
0.009192 s |
0.005835021599978 s |
1.58 |
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 |
0.0092249999999999 s |
0.0062407683998571 s |
1.48 |
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 |
0.01269 s |
0.005692110000109 s |
2.23 |
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 |
0.014163 s |
0.0059548058000473 s |
2.38 |
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 |
0.010485 s |
0.005899918400064 s |
1.78 |
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 |
0.01209 s |
0.0052036910001334 s |
2.32 |
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 |
0.0115749999999999 s |
0.0063195202000315 s |
1.83 |
scatter_sum / Jax / cpu / Primal |
0.000007595079950988292 s |
0.000009051719980561756 s |
0.84 |
scatter_sum / JaXPipe / cpu / Primal |
0.000007504279983550077 s |
0.000009541880017422954 s |
0.79 |
scatter_sum / PartOpt / cpu / Primal |
0.000007726240046395105 s |
0.000008413739942625398 s |
0.92 |
scatter_sum / IPartOpt / cpu / Primal |
0.000007662100024390384 s |
0.000008346000031451695 s |
0.92 |
scatter_sum / HLOOpt / cpu / Primal |
0.00000807451996479358 s |
0.000009232299989889725 s |
0.87 |
scatter_sum / DefOpt / cpu / Primal |
0.00000767068004279281 s |
0.000008606619967395091 s |
0.89 |
scatter_sum / IDefOpt / cpu / Primal |
0.000007812919975549448 s |
0.000008915020007407293 s |
0.88 |
scatter_sum / Jax / cpu / Forward |
0.000011173700013387132 s |
0.000013720980014113591 s |
0.81 |
scatter_sum / JaXPipe / cpu / Forward |
0.000010993260002578608 s |
0.000014127079957688693 s |
0.78 |
scatter_sum / PartOpt / cpu / Forward |
0.00001239324000380293 s |
0.00001362183998026012 s |
0.91 |
scatter_sum / IPartOpt / cpu / Forward |
0.000011610480014496717 s |
0.00001518636006039742 s |
0.76 |
scatter_sum / HLOOpt / cpu / Forward |
0.000011735500029317336 s |
0.000014498360051220517 s |
0.81 |
scatter_sum / DefOpt / cpu / Forward |
0.00001123053999435797 s |
0.000013790399952995358 s |
0.81 |
scatter_sum / IDefOpt / cpu / Forward |
0.000011164080033267963 s |
0.000013915299978179974 s |
0.80 |
scatter_sum / Jax / cpu / BothRev |
0.000011352319988873204 s |
0.000012925799992444807 s |
0.88 |
scatter_sum / JaXPipe / cpu / PreRev |
0.000011539919996721438 s |
0.000013283560037962162 s |
0.87 |
scatter_sum / JaXPipe / cpu / PostRev |
0.00001217481997628056 s |
0.000013325800000529852 s |
0.91 |
scatter_sum / JaXPipe / cpu / BothRev |
0.000011285700029475264 s |
0.00001360463998025807 s |
0.83 |
scatter_sum / PartOpt / cpu / PreRev |
0.000012052839965690507 s |
0.000013849779970769304 s |
0.87 |
scatter_sum / PartOpt / cpu / PostRev |
0.000013963760002297932 s |
0.000013569119992098424 s |
1.03 |
scatter_sum / PartOpt / cpu / BothRev |
0.000011667780026982655 s |
0.000013870199991288246 s |
0.84 |
scatter_sum / IPartOpt / cpu / PreRev |
0.000011268160051258748 s |
0.000013387979970502784 s |
0.84 |
scatter_sum / IPartOpt / cpu / PostRev |
0.000011868160017911575 s |
0.000013002060004509986 s |
0.91 |
scatter_sum / IPartOpt / cpu / BothRev |
0.00001225770002747595 s |
0.000012920400004077236 s |
0.95 |
scatter_sum / HLOOpt / cpu / PreRev |
0.00001146644000073138 s |
0.000014037100054338226 s |
0.82 |
scatter_sum / HLOOpt / cpu / PostRev |
0.000012101499996788337 s |
0.000015473340035896398 s |
0.78 |
scatter_sum / HLOOpt / cpu / BothRev |
0.000011643539992292062 s |
0.00001335435997134482 s |
0.87 |
scatter_sum / DefOpt / cpu / PreRev |
0.000011458960007075802 s |
0.000013036360005571623 s |
0.88 |
scatter_sum / DefOpt / cpu / PostRev |
0.000011810420019173762 s |
0.000013914739993197143 s |
0.85 |
scatter_sum / DefOpt / cpu / BothRev |
0.00001201727993247914 s |
0.000014243039995562869 s |
0.84 |
scatter_sum / IDefOpt / cpu / PreRev |
0.000011830339981315771 s |
0.00001324805996773648 s |
0.89 |
scatter_sum / IDefOpt / cpu / PostRev |
0.000011668299976008711 s |
0.000013406620037130778 s |
0.87 |
scatter_sum / IDefOpt / cpu / BothRev |
0.000012136980003560894 s |
0.000013913320008214216 s |
0.87 |
scatter_sum / Jax / cuda / Primal |
0.000009889 s |
0.000009664 s |
1.02 |
scatter_sum / JaXPipe / cuda / Primal |
0.000009793 s |
0.000009664 s |
1.01 |
scatter_sum / PartOpt / cuda / Primal |
0.000009793 s |
0.000009952 s |
0.98 |
scatter_sum / IPartOpt / cuda / Primal |
0.000009824 s |
0.000009889 s |
0.99 |
scatter_sum / HLOOpt / cuda / Primal |
0.000009632 s |
0.000009888 s |
0.97 |
scatter_sum / DefOpt / cuda / Primal |
0.000009824 s |
0.00000976 s |
1.01 |
scatter_sum / IDefOpt / cuda / Primal |
0.00001008 s |
0.000009184 s |
1.10 |
scatter_sum / Jax / cuda / Forward |
0.000016607 s |
0.000016767 s |
0.99 |
scatter_sum / JaXPipe / cuda / Forward |
0.000017633 s |
0.000016479 s |
1.07 |
scatter_sum / PartOpt / cuda / Forward |
0.00001712 s |
0.000016352 s |
1.05 |
scatter_sum / IPartOpt / cuda / Forward |
0.000016512 s |
0.000016704 s |
0.99 |
scatter_sum / HLOOpt / cuda / Forward |
0.000017152 s |
0.000016544 s |
1.04 |
scatter_sum / DefOpt / cuda / Forward |
0.000016704 s |
0.000018496 s |
0.90 |
scatter_sum / IDefOpt / cuda / Forward |
0.000016831 s |
0.000017919999999999998 s |
0.94 |
scatter_sum / Jax / cuda / BothRev |
0.000016927999999999998 s |
0.000016512 s |
1.03 |
scatter_sum / JaXPipe / cuda / PreRev |
0.000017056 s |
0.000016864 s |
1.01 |
scatter_sum / JaXPipe / cuda / PostRev |
0.000016704 s |
0.000016352 s |
1.02 |
scatter_sum / JaXPipe / cuda / BothRev |
0.000016896000000000002 s |
0.000016512 s |
1.02 |
scatter_sum / PartOpt / cuda / PreRev |
0.000017057 s |
0.00001712 s |
1.00 |
scatter_sum / PartOpt / cuda / PostRev |
0.000017313 s |
0.000016192 s |
1.07 |
scatter_sum / PartOpt / cuda / BothRev |
0.000016736 s |
0.00001664 s |
1.01 |
scatter_sum / IPartOpt / cuda / PreRev |
0.000017568000000000002 s |
0.000016703 s |
1.05 |
scatter_sum / IPartOpt / cuda / PostRev |
0.0000168 s |
0.000016192 s |
1.04 |
scatter_sum / IPartOpt / cuda / BothRev |
0.000016864 s |
0.000016832 s |
1.00 |
scatter_sum / HLOOpt / cuda / PreRev |
0.000017056 s |
0.000016672 s |
1.02 |
scatter_sum / HLOOpt / cuda / PostRev |
0.000016383999999999998 s |
0.0000168 s |
0.98 |
scatter_sum / HLOOpt / cuda / BothRev |
0.000017247999999999998 s |
0.000016544 s |
1.04 |
scatter_sum / DefOpt / cuda / PreRev |
0.00001696 s |
0.000016832 s |
1.01 |
scatter_sum / DefOpt / cuda / PostRev |
0.000016032 s |
0.000015872 s |
1.01 |
scatter_sum / DefOpt / cuda / BothRev |
0.000017184 s |
0.000017056 s |
1.01 |
scatter_sum / IDefOpt / cuda / PreRev |
0.000017216 s |
0.00001696 s |
1.02 |
scatter_sum / IDefOpt / cuda / PostRev |
0.0000168 s |
0.000017024 s |
0.99 |
scatter_sum / IDefOpt / cuda / BothRev |
0.000016927999999999998 s |
0.000016832 s |
1.01 |
scatter_sum / Jax / tpu / Primal |
0.000001344025 s |
0.0000014048 s |
0.96 |
scatter_sum / JaXPipe / tpu / Primal |
0.000001343725 s |
0.000001344 s |
1.00 |
scatter_sum / PartOpt / tpu / Primal |
0.000001343375 s |
0.0000014045750000000002 s |
0.96 |
scatter_sum / IPartOpt / tpu / Primal |
0.0000013437499999999998 s |
0.000001343725 s |
1.00 |
scatter_sum / HLOOpt / tpu / Primal |
0.0000013437499999999998 s |
0.000001343875 s |
1.00 |
scatter_sum / DefOpt / tpu / Primal |
0.000001344375 s |
0.000001404925 s |
0.96 |
scatter_sum / IDefOpt / tpu / Primal |
0.000001343725 s |
0.0000013436 s |
1.00 |
scatter_sum / Jax / tpu / Forward |
0.00000274075 s |
0.000002722675 s |
1.01 |
scatter_sum / JaXPipe / tpu / Forward |
0.000002744825 s |
0.00000270495 s |
1.01 |
scatter_sum / PartOpt / tpu / Forward |
0.0000027431 s |
0.00000268545 s |
1.02 |
scatter_sum / IPartOpt / tpu / Forward |
0.000002711675 s |
0.00000270835 s |
1.00 |
scatter_sum / HLOOpt / tpu / Forward |
0.00000274515 s |
0.0000027063 s |
1.01 |
scatter_sum / DefOpt / tpu / Forward |
0.0000027149 s |
0.000002685175 s |
1.01 |
scatter_sum / IDefOpt / tpu / Forward |
0.000002739125 s |
0.00000270065 s |
1.01 |
scatter_sum / Jax / tpu / BothRev |
0.0000027104250000000004 s |
0.0000027426 s |
0.99 |
scatter_sum / JaXPipe / tpu / PreRev |
0.0000027345750000000004 s |
0.000002686075 s |
1.02 |
scatter_sum / JaXPipe / tpu / PostRev |
0.0000027252500000000003 s |
0.00000269025 s |
1.01 |
scatter_sum / JaXPipe / tpu / BothRev |
0.00000279155 s |
0.000002700875 s |
1.03 |
scatter_sum / PartOpt / tpu / PreRev |
0.0000027377 s |
0.0000027438000000000003 s |
1.00 |
scatter_sum / PartOpt / tpu / PostRev |
0.000002792775 s |
0.0000026997 s |
1.03 |
scatter_sum / PartOpt / tpu / BothRev |
0.00000272645 s |
0.0000027439 s |
0.99 |
scatter_sum / IPartOpt / tpu / PreRev |
0.000002794075 s |
0.0000027068 s |
1.03 |
scatter_sum / IPartOpt / tpu / PostRev |
0.00000272015 s |
0.00000274555 s |
0.99 |
scatter_sum / IPartOpt / tpu / BothRev |
0.00000278955 s |
0.0000027067249999999995 s |
1.03 |
scatter_sum / HLOOpt / tpu / PreRev |
0.00000272265 s |
0.000002695875 s |
1.01 |
scatter_sum / HLOOpt / tpu / PostRev |
0.000002788675 s |
0.000002746125 s |
1.02 |
scatter_sum / HLOOpt / tpu / BothRev |
0.000002734 s |
0.000002700975 s |
1.01 |
scatter_sum / DefOpt / tpu / PreRev |
0.0000027952500000000005 s |
0.000002747 s |
1.02 |
scatter_sum / DefOpt / tpu / PostRev |
0.0000027208500000000004 s |
0.00000269455 s |
1.01 |
scatter_sum / DefOpt / tpu / BothRev |
0.00000278765 s |
0.000002745425 s |
1.02 |
scatter_sum / IDefOpt / tpu / PreRev |
0.0000027252749999999995 s |
0.0000027003 s |
1.01 |
scatter_sum / IDefOpt / tpu / PostRev |
0.000002785975 s |
0.000002745825 s |
1.01 |
scatter_sum / IDefOpt / tpu / BothRev |
0.000002725075 s |
0.000002696975 s |
1.01 |
scatter_sum / Jax / cpu / Primal |
0.000015813 s |
0.000009051719980561756 s |
1.75 |
scatter_sum / JaXPipe / cpu / Primal |
0.000015591 s |
0.000009541880017422954 s |
1.63 |
scatter_sum / PartOpt / cpu / Primal |
0.000015665 s |
0.000008413739942625398 s |
1.86 |
scatter_sum / IPartOpt / cpu / Primal |
0.000015716 s |
0.000008346000031451695 s |
1.88 |
scatter_sum / HLOOpt / cpu / Primal |
0.000015949999999999998 s |
0.000009232299989889725 s |
1.73 |
scatter_sum / DefOpt / cpu / Primal |
0.000015711 s |
0.000008606619967395091 s |
1.83 |
scatter_sum / IDefOpt / cpu / Primal |
0.000015887 s |
0.000008915020007407293 s |
1.78 |
scatter_sum / Jax / cpu / Forward |
0.000022957 s |
0.000013720980014113591 s |
1.67 |
scatter_sum / JaXPipe / cpu / Forward |
0.000022937 s |
0.000014127079957688693 s |
1.62 |
scatter_sum / PartOpt / cpu / Forward |
0.000022627 s |
0.00001362183998026012 s |
1.66 |
scatter_sum / IPartOpt / cpu / Forward |
0.0000232 s |
0.00001518636006039742 s |
1.53 |
scatter_sum / HLOOpt / cpu / Forward |
0.00002251 s |
0.000014498360051220517 s |
1.55 |
scatter_sum / DefOpt / cpu / Forward |
0.000022423 s |
0.000013790399952995358 s |
1.63 |
scatter_sum / IDefOpt / cpu / Forward |
0.000022518 s |
0.000013915299978179974 s |
1.62 |
scatter_sum / Jax / cpu / BothRev |
0.000023375 s |
0.000012925799992444807 s |
1.81 |
scatter_sum / JaXPipe / cpu / PreRev |
0.000022326 s |
0.000013283560037962162 s |
1.68 |
scatter_sum / JaXPipe / cpu / PostRev |
0.000022269 s |
0.000013325800000529852 s |
1.67 |
scatter_sum / JaXPipe / cpu / BothRev |
0.000022791 s |
0.00001360463998025807 s |
1.68 |
scatter_sum / PartOpt / cpu / PreRev |
0.000022569 s |
0.000013849779970769304 s |
1.63 |
scatter_sum / PartOpt / cpu / PostRev |
0.000022234 s |
0.000013569119992098424 s |
1.64 |
scatter_sum / PartOpt / cpu / BothRev |
0.000022284 s |
0.000013870199991288246 s |
1.61 |
scatter_sum / IPartOpt / cpu / PreRev |
0.000022564 s |
0.000013387979970502784 s |
1.69 |
scatter_sum / IPartOpt / cpu / PostRev |
0.000022556 s |
0.000013002060004509986 s |
1.73 |
scatter_sum / IPartOpt / cpu / BothRev |
0.000023143 s |
0.000012920400004077236 s |
1.79 |
scatter_sum / HLOOpt / cpu / PreRev |
0.000022870000000000003 s |
0.000014037100054338226 s |
1.63 |
scatter_sum / HLOOpt / cpu / PostRev |
0.000022696 s |
0.000015473340035896398 s |
1.47 |
scatter_sum / HLOOpt / cpu / BothRev |
0.000022836 s |
0.00001335435997134482 s |
1.71 |
scatter_sum / DefOpt / cpu / PreRev |
0.000022964 s |
0.000013036360005571623 s |
1.76 |
scatter_sum / DefOpt / cpu / PostRev |
0.000023092 s |
0.000013914739993197143 s |
1.66 |
scatter_sum / DefOpt / cpu / BothRev |
0.00002264 s |
0.000014243039995562869 s |
1.59 |
scatter_sum / IDefOpt / cpu / PreRev |
0.000022683 s |
0.00001324805996773648 s |
1.71 |
scatter_sum / IDefOpt / cpu / PostRev |
0.000023121 s |
0.000013406620037130778 s |
1.72 |
scatter_sum / IDefOpt / cpu / BothRev |
0.000023346 s |
0.000013913320008214216 s |
1.68 |
scatter_sum / Jax / cpu / Primal |
0.000011 s |
0.000009051719980561756 s |
1.22 |
scatter_sum / JaXPipe / cpu / Primal |
0.000011 s |
0.000009541880017422954 s |
1.15 |
scatter_sum / PartOpt / cpu / Primal |
0.000011 s |
0.000008413739942625398 s |
1.31 |
scatter_sum / IPartOpt / cpu / Primal |
0.00001 s |
0.000008346000031451695 s |
1.20 |
scatter_sum / HLOOpt / cpu / Primal |
0.000011 s |
0.000009232299989889725 s |
1.19 |
scatter_sum / DefOpt / cpu / Primal |
0.000011 s |
0.000008606619967395091 s |
1.28 |
scatter_sum / IDefOpt / cpu / Primal |
0.000011 s |
0.000008915020007407293 s |
1.23 |
scatter_sum / Jax / cpu / Forward |
0.000016 s |
0.000013720980014113591 s |
1.17 |
scatter_sum / JaXPipe / cpu / Forward |
0.000019 s |
0.000014127079957688693 s |
1.34 |
scatter_sum / PartOpt / cpu / Forward |
0.000016 s |
0.00001362183998026012 s |
1.17 |
scatter_sum / IPartOpt / cpu / Forward |
0.000016 s |
0.00001518636006039742 s |
1.05 |
scatter_sum / HLOOpt / cpu / Forward |
0.000015 s |
0.000014498360051220517 s |
1.03 |
scatter_sum / DefOpt / cpu / Forward |
0.000015 s |
0.000013790399952995358 s |
1.09 |
scatter_sum / IDefOpt / cpu / Forward |
0.000016 s |
0.000013915299978179974 s |
1.15 |
scatter_sum / Jax / cpu / BothRev |
0.000016 s |
0.000012925799992444807 s |
1.24 |
scatter_sum / JaXPipe / cpu / PreRev |
0.000017 s |
0.000013283560037962162 s |
1.28 |
scatter_sum / JaXPipe / cpu / PostRev |
0.000017 s |
0.000013325800000529852 s |
1.28 |
scatter_sum / JaXPipe / cpu / BothRev |
0.000016 s |
0.00001360463998025807 s |
1.18 |
scatter_sum / PartOpt / cpu / PreRev |
0.000016 s |
0.000013849779970769304 s |
1.16 |
scatter_sum / PartOpt / cpu / PostRev |
0.000016 s |
0.000013569119992098424 s |
1.18 |
scatter_sum / PartOpt / cpu / BothRev |
0.000016 s |
0.000013870199991288246 s |
1.15 |
scatter_sum / IPartOpt / cpu / PreRev |
0.000016 s |
0.000013387979970502784 s |
1.20 |
scatter_sum / IPartOpt / cpu / PostRev |
0.000016 s |
0.000013002060004509986 s |
1.23 |
scatter_sum / IPartOpt / cpu / BothRev |
0.000016 s |
0.000012920400004077236 s |
1.24 |
scatter_sum / HLOOpt / cpu / PreRev |
0.000017 s |
0.000014037100054338226 s |
1.21 |
scatter_sum / HLOOpt / cpu / PostRev |
0.000017 s |
0.000015473340035896398 s |
1.10 |
scatter_sum / HLOOpt / cpu / BothRev |
0.000017 s |
0.00001335435997134482 s |
1.27 |
scatter_sum / DefOpt / cpu / PreRev |
0.000016 s |
0.000013036360005571623 s |
1.23 |
scatter_sum / DefOpt / cpu / PostRev |
0.000016 s |
0.000013914739993197143 s |
1.15 |
scatter_sum / DefOpt / cpu / BothRev |
0.000017 s |
0.000014243039995562869 s |
1.19 |
scatter_sum / IDefOpt / cpu / PreRev |
0.000016 s |
0.00001324805996773648 s |
1.21 |
scatter_sum / IDefOpt / cpu / PostRev |
0.000016 s |
0.000013406620037130778 s |
1.19 |
scatter_sum / IDefOpt / cpu / BothRev |
0.000016 s |
0.000013913320008214216 s |
1.15 |
slicing / Jax / cpu / Primal |
0.00000623084003564145 s |
0.000007417620008709491 s |
0.84 |
slicing / JaXPipe / cpu / Primal |
0.000006202480035426561 s |
0.000007281100033651456 s |
0.85 |
slicing / PartOpt / cpu / Primal |
0.000006345920046442188 s |
0.00000741012001526542 s |
0.86 |
slicing / IPartOpt / cpu / Primal |
0.000006179700021675672 s |
0.000006921139993210091 s |
0.89 |
slicing / HLOOpt / cpu / Primal |
0.000006455499997173319 s |
0.000006967280014578136 s |
0.93 |
slicing / DefOpt / cpu / Primal |
0.0000066374000198266 s |
0.000007031080021988601 s |
0.94 |
slicing / IDefOpt / cpu / Primal |
0.000006305600018094992 s |
0.000006688900002700393 s |
0.94 |
slicing / Jax / cpu / Forward |
0.00000939471997298824 s |
0.000011345779976181802 s |
0.83 |
slicing / JaXPipe / cpu / Forward |
0.00000896269995791954 s |
0.00001028114003020164 s |
0.87 |
slicing / PartOpt / cpu / Forward |
0.000009470179984418792 s |
0.00001100200001928897 s |
0.86 |
slicing / IPartOpt / cpu / Forward |
0.000009097959982682368 s |
0.000011208740024812867 s |
0.81 |
slicing / HLOOpt / cpu / Forward |
0.000009298860031776713 s |
0.000011428660027377193 s |
0.81 |
slicing / DefOpt / cpu / Forward |
0.000009405059990967855 s |
0.000010430400025143173 s |
0.90 |
slicing / IDefOpt / cpu / Forward |
0.00000918101998649945 s |
0.000010656319973350036 s |
0.86 |
slicing / Jax / cpu / BothRev |
0.000010069620029753424 s |
0.00001135638000050676 s |
0.89 |
slicing / JaXPipe / cpu / PreRev |
0.00000987648002592323 s |
0.000011447760016380926 s |
0.86 |
slicing / JaXPipe / cpu / PostRev |
0.000010204179998254404 s |
0.000011277679996055666 s |
0.90 |
slicing / JaXPipe / cpu / BothRev |
0.000009484959991823415 s |
0.000011822359983852948 s |
0.80 |
slicing / PartOpt / cpu / PreRev |
0.0000100743600523856 s |
0.000011041359948649188 s |
0.91 |
slicing / PartOpt / cpu / PostRev |
0.000012159320031059906 s |
0.000011046320032619406 s |
1.10 |
slicing / PartOpt / cpu / BothRev |
0.000009991519964387408 s |
0.00001108768004087324 s |
0.90 |
slicing / IPartOpt / cpu / PreRev |
0.000009573759998602326 s |
0.000011140319975311284 s |
0.86 |
slicing / IPartOpt / cpu / PostRev |
0.000010001839973483584 s |
0.000011385600000721752 s |
0.88 |
slicing / IPartOpt / cpu / BothRev |
0.000009894699969663634 s |
0.00001075728005162091 s |
0.92 |
slicing / HLOOpt / cpu / PreRev |
0.000010006500015151686 s |
0.000011924040018129743 s |
0.84 |
slicing / HLOOpt / cpu / PostRev |
0.000009925759977704729 s |
0.000013196680001783532 s |
0.75 |
slicing / HLOOpt / cpu / BothRev |
0.000009799359977478162 s |
0.00001109399996494176 s |
0.88 |
slicing / DefOpt / cpu / PreRev |
0.000009805579929889064 s |
0.00001135841998802789 s |
0.86 |
slicing / DefOpt / cpu / PostRev |
0.000010054240001409196 s |
0.000011674980032694294 s |
0.86 |
slicing / DefOpt / cpu / BothRev |
0.000009771260010893457 s |
0.00001120979999541305 s |
0.87 |
slicing / IDefOpt / cpu / PreRev |
0.000009670859990364988 s |
0.000011482079980851268 s |
0.84 |
slicing / IDefOpt / cpu / PostRev |
0.000009733300021252945 s |
0.000011328559985486208 s |
0.86 |
slicing / IDefOpt / cpu / BothRev |
0.000010113119969901165 s |
0.000011219779962630129 s |
0.90 |
slicing / Jax / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
slicing / JaXPipe / cuda / Primal |
0.000001888 s |
0.000001887 s |
1.00 |
slicing / PartOpt / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
slicing / IPartOpt / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
slicing / HLOOpt / cuda / Primal |
0.000001887 s |
0.000001888 s |
1.00 |
slicing / DefOpt / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
slicing / IDefOpt / cuda / Primal |
0.000001887 s |
0.000001887 s |
1 |
slicing / Jax / cuda / Forward |
0.000009824 s |
0.000009824 s |
1 |
slicing / JaXPipe / cuda / Forward |
0.000009728 s |
0.000009632 s |
1.01 |
slicing / PartOpt / cuda / Forward |
0.000009984 s |
0.000009792 s |
1.02 |
slicing / IPartOpt / cuda / Forward |
0.00001008 s |
0.00000976 s |
1.03 |
slicing / HLOOpt / cuda / Forward |
0.000009696 s |
0.00000944 s |
1.03 |
slicing / DefOpt / cuda / Forward |
0.00001008 s |
0.00000976 s |
1.03 |
slicing / IDefOpt / cuda / Forward |
0.000010145 s |
0.000009951 s |
1.02 |
slicing / Jax / cuda / BothRev |
0.000009504 s |
0.000009824 s |
0.97 |
slicing / JaXPipe / cuda / PreRev |
0.000009153 s |
0.000009344 s |
0.98 |
slicing / JaXPipe / cuda / PostRev |
0.000010272 s |
0.000010016 s |
1.03 |
slicing / JaXPipe / cuda / BothRev |
0.000009824 s |
0.000009504 s |
1.03 |
slicing / PartOpt / cuda / PreRev |
0.0000096 s |
0.000009824 s |
0.98 |
slicing / PartOpt / cuda / PostRev |
0.000009024 s |
0.000009664 s |
0.93 |
slicing / PartOpt / cuda / BothRev |
0.000009728 s |
0.000009248 s |
1.05 |
slicing / IPartOpt / cuda / PreRev |
0.000009696 s |
0.000009856 s |
0.98 |
slicing / IPartOpt / cuda / PostRev |
0.000009568 s |
0.000009344 s |
1.02 |
slicing / IPartOpt / cuda / BothRev |
0.000009951 s |
0.000010368 s |
0.96 |
slicing / HLOOpt / cuda / PreRev |
0.000009792 s |
0.000009536 s |
1.03 |
slicing / HLOOpt / cuda / PostRev |
0.000010016 s |
0.000009504 s |
1.05 |
slicing / HLOOpt / cuda / BothRev |
0.000009887 s |
0.000009471 s |
1.04 |
slicing / DefOpt / cuda / PreRev |
0.000009984 s |
0.000009728 s |
1.03 |
slicing / DefOpt / cuda / PostRev |
0.000009856 s |
0.0000096 s |
1.03 |
slicing / DefOpt / cuda / BothRev |
0.0000096 s |
0.000009696 s |
0.99 |
slicing / IDefOpt / cuda / PreRev |
0.000009855 s |
0.00000992 s |
0.99 |
slicing / IDefOpt / cuda / PostRev |
0.00000976 s |
0.000009439 s |
1.03 |
slicing / IDefOpt / cuda / BothRev |
0.00000992 s |
0.000009888 s |
1.00 |
slicing / Jax / tpu / Primal |
9.65425e-7 s |
9.66075e-7 s |
1.00 |
slicing / JaXPipe / tpu / Primal |
9.73425e-7 s |
0.000001017725 s |
0.96 |
slicing / PartOpt / tpu / Primal |
9.64175e-7 s |
9.635e-7 s |
1.00 |
slicing / IPartOpt / tpu / Primal |
9.732e-7 s |
0.00000102175 s |
0.95 |
slicing / HLOOpt / tpu / Primal |
9.619e-7 s |
0.000001019725 s |
0.94 |
slicing / DefOpt / tpu / Primal |
9.8335e-7 s |
9.69275e-7 s |
1.01 |
slicing / IDefOpt / tpu / Primal |
9.62125e-7 s |
0.000001017375 s |
0.95 |
slicing / Jax / tpu / Forward |
0.00000141205 s |
0.0000014684249999999998 s |
0.96 |
slicing / JaXPipe / tpu / Forward |
0.000001417475 s |
0.000001402875 s |
1.01 |
slicing / PartOpt / tpu / Forward |
0.000001525525 s |
0.000001492375 s |
1.02 |
slicing / IPartOpt / tpu / Forward |
0.000001435525 s |
0.0000015116 s |
0.95 |
slicing / HLOOpt / tpu / Forward |
0.00000151645 s |
0.000001511325 s |
1.00 |
slicing / DefOpt / tpu / Forward |
0.00000143185 s |
0.000001490025 s |
0.96 |
slicing / IDefOpt / tpu / Forward |
0.00000152795 s |
0.000001513325 s |
1.01 |
slicing / Jax / tpu / BothRev |
0.0000023279 s |
0.00000253535 s |
0.92 |
slicing / JaXPipe / tpu / PreRev |
0.00000251465 s |
0.000002577125 s |
0.98 |
slicing / JaXPipe / tpu / PostRev |
0.000002354925 s |
0.0000025213249999999995 s |
0.93 |
slicing / JaXPipe / tpu / BothRev |
0.00000252455 s |
0.000002582525 s |
0.98 |
slicing / PartOpt / tpu / PreRev |
0.00000235035 s |
0.0000025458750000000004 s |
0.92 |
slicing / PartOpt / tpu / PostRev |
0.00000252195 s |
0.000002588825 s |
0.97 |
slicing / PartOpt / tpu / BothRev |
0.00000234695 s |
0.00000253965 s |
0.92 |
slicing / IPartOpt / tpu / PreRev |
0.0000025211250000000004 s |
0.0000025968000000000003 s |
0.97 |
slicing / IPartOpt / tpu / PostRev |
0.000002344675 s |
0.0000025466 s |
0.92 |
slicing / IPartOpt / tpu / BothRev |
0.0000025324 s |
0.000002589625 s |
0.98 |
slicing / HLOOpt / tpu / PreRev |
0.00000235845 s |
0.0000025862249999999995 s |
0.91 |
slicing / HLOOpt / tpu / PostRev |
0.000002525825 s |
0.0000025417 s |
0.99 |
slicing / HLOOpt / tpu / BothRev |
0.0000023596 s |
0.000002583125 s |
0.91 |
slicing / DefOpt / tpu / PreRev |
0.000002525675 s |
0.00000253795 s |
1.00 |
slicing / DefOpt / tpu / PostRev |
0.00000235075 s |
0.00000258885 s |
0.91 |
slicing / DefOpt / tpu / BothRev |
0.0000025242249999999995 s |
0.0000025395 s |
0.99 |
slicing / IDefOpt / tpu / PreRev |
0.00000235195 s |
0.0000025814500000000005 s |
0.91 |
slicing / IDefOpt / tpu / PostRev |
0.000002534525 s |
0.0000025348 s |
1.00 |
slicing / IDefOpt / tpu / BothRev |
0.0000023576 s |
0.000002584975 s |
0.91 |
slicing / Jax / cpu / Primal |
0.000012826 s |
0.000007417620008709491 s |
1.73 |
slicing / JaXPipe / cpu / Primal |
0.000012562 s |
0.000007281100033651456 s |
1.73 |
slicing / PartOpt / cpu / Primal |
0.000013062 s |
0.00000741012001526542 s |
1.76 |
slicing / IPartOpt / cpu / Primal |
0.00001311 s |
0.000006921139993210091 s |
1.89 |
slicing / HLOOpt / cpu / Primal |
0.000012688 s |
0.000006967280014578136 s |
1.82 |
slicing / DefOpt / cpu / Primal |
0.000012523 s |
0.000007031080021988601 s |
1.78 |
slicing / IDefOpt / cpu / Primal |
0.000012436 s |
0.000006688900002700393 s |
1.86 |
slicing / Jax / cpu / Forward |
0.000017124 s |
0.000011345779976181802 s |
1.51 |
slicing / JaXPipe / cpu / Forward |
0.000016798 s |
0.00001028114003020164 s |
1.63 |
slicing / PartOpt / cpu / Forward |
0.00001649 s |
0.00001100200001928897 s |
1.50 |
slicing / IPartOpt / cpu / Forward |
0.000016695000000000002 s |
0.000011208740024812867 s |
1.49 |
slicing / HLOOpt / cpu / Forward |
0.000016751999999999998 s |
0.000011428660027377193 s |
1.47 |
slicing / DefOpt / cpu / Forward |
0.000016969000000000003 s |
0.000010430400025143173 s |
1.63 |
slicing / IDefOpt / cpu / Forward |
0.000016547 s |
0.000010656319973350036 s |
1.55 |
slicing / Jax / cpu / BothRev |
0.000017681 s |
0.00001135638000050676 s |
1.56 |
slicing / JaXPipe / cpu / PreRev |
0.000017283 s |
0.000011447760016380926 s |
1.51 |
slicing / JaXPipe / cpu / PostRev |
0.000017698 s |
0.000011277679996055666 s |
1.57 |
slicing / JaXPipe / cpu / BothRev |
0.000017428 s |
0.000011822359983852948 s |
1.47 |
slicing / PartOpt / cpu / PreRev |
0.000017545000000000002 s |
0.000011041359948649188 s |
1.59 |
slicing / PartOpt / cpu / PostRev |
0.000017316 s |
0.000011046320032619406 s |
1.57 |
slicing / PartOpt / cpu / BothRev |
0.000017168 s |
0.00001108768004087324 s |
1.55 |
slicing / IPartOpt / cpu / PreRev |
0.000017703 s |
0.000011140319975311284 s |
1.59 |
slicing / IPartOpt / cpu / PostRev |
0.000017613 s |
0.000011385600000721752 s |
1.55 |
slicing / IPartOpt / cpu / BothRev |
0.000017621000000000003 s |
0.00001075728005162091 s |
1.64 |
slicing / HLOOpt / cpu / PreRev |
0.000018099 s |
0.000011924040018129743 s |
1.52 |
slicing / HLOOpt / cpu / PostRev |
0.000017408 s |
0.000013196680001783532 s |
1.32 |
slicing / HLOOpt / cpu / BothRev |
0.000017437999999999998 s |
0.00001109399996494176 s |
1.57 |
slicing / DefOpt / cpu / PreRev |
0.000017109 s |
0.00001135841998802789 s |
1.51 |
slicing / DefOpt / cpu / PostRev |
0.000017077 s |
0.000011674980032694294 s |
1.46 |
slicing / DefOpt / cpu / BothRev |
0.000017412000000000002 s |
0.00001120979999541305 s |
1.55 |
slicing / IDefOpt / cpu / PreRev |
0.000017355 s |
0.000011482079980851268 s |
1.51 |
slicing / IDefOpt / cpu / PostRev |
0.000017643 s |
0.000011328559985486208 s |
1.56 |
slicing / IDefOpt / cpu / BothRev |
0.000017802 s |
0.000011219779962630129 s |
1.59 |
slicing / Jax / cpu / Primal |
0.000008 s |
0.000007417620008709491 s |
1.08 |
slicing / JaXPipe / cpu / Primal |
0.000008 s |
0.000007281100033651456 s |
1.10 |
slicing / PartOpt / cpu / Primal |
0.000008999999999999999 s |
0.00000741012001526542 s |
1.21 |
slicing / IPartOpt / cpu / Primal |
0.000008 s |
0.000006921139993210091 s |
1.16 |
slicing / HLOOpt / cpu / Primal |
0.000008 s |
0.000006967280014578136 s |
1.15 |
slicing / DefOpt / cpu / Primal |
0.000008 s |
0.000007031080021988601 s |
1.14 |
slicing / IDefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000006688900002700393 s |
1.35 |
slicing / Jax / cpu / Forward |
0.000012 s |
0.000011345779976181802 s |
1.06 |
slicing / JaXPipe / cpu / Forward |
0.000011 s |
0.00001028114003020164 s |
1.07 |
slicing / PartOpt / cpu / Forward |
0.000012 s |
0.00001100200001928897 s |
1.09 |
slicing / IPartOpt / cpu / Forward |
0.000012 s |
0.000011208740024812867 s |
1.07 |
slicing / HLOOpt / cpu / Forward |
0.000012 s |
0.000011428660027377193 s |
1.05 |
slicing / DefOpt / cpu / Forward |
0.000012 s |
0.000010430400025143173 s |
1.15 |
slicing / IDefOpt / cpu / Forward |
0.000011 s |
0.000010656319973350036 s |
1.03 |
slicing / Jax / cpu / BothRev |
0.000012 s |
0.00001135638000050676 s |
1.06 |
slicing / JaXPipe / cpu / PreRev |
0.000012 s |
0.000011447760016380926 s |
1.05 |
slicing / JaXPipe / cpu / PostRev |
0.000012 s |
0.000011277679996055666 s |
1.06 |
slicing / JaXPipe / cpu / BothRev |
0.000012 s |
0.000011822359983852948 s |
1.02 |
slicing / PartOpt / cpu / PreRev |
0.000012 s |
0.000011041359948649188 s |
1.09 |
slicing / PartOpt / cpu / PostRev |
0.000012 s |
0.000011046320032619406 s |
1.09 |
slicing / PartOpt / cpu / BothRev |
0.000012 s |
0.00001108768004087324 s |
1.08 |
slicing / IPartOpt / cpu / PreRev |
0.000011 s |
0.000011140319975311284 s |
0.99 |
slicing / IPartOpt / cpu / PostRev |
0.000012 s |
0.000011385600000721752 s |
1.05 |
slicing / IPartOpt / cpu / BothRev |
0.000012 s |
0.00001075728005162091 s |
1.12 |
slicing / HLOOpt / cpu / PreRev |
0.000012 s |
0.000011924040018129743 s |
1.01 |
slicing / HLOOpt / cpu / PostRev |
0.000013 s |
0.000013196680001783532 s |
0.99 |
slicing / HLOOpt / cpu / BothRev |
0.000012 s |
0.00001109399996494176 s |
1.08 |
slicing / DefOpt / cpu / PreRev |
0.000012 s |
0.00001135841998802789 s |
1.06 |
slicing / DefOpt / cpu / PostRev |
0.000012 s |
0.000011674980032694294 s |
1.03 |
slicing / DefOpt / cpu / BothRev |
0.000012 s |
0.00001120979999541305 s |
1.07 |
slicing / IDefOpt / cpu / PreRev |
0.000012 s |
0.000011482079980851268 s |
1.05 |
slicing / IDefOpt / cpu / PostRev |
0.000012 s |
0.000011328559985486208 s |
1.06 |
slicing / IDefOpt / cpu / BothRev |
0.000012 s |
0.000011219779962630129 s |
1.07 |
sum / Jax / cpu / Primal |
0.000007844060000934405 s |
0.000008546899998691515 s |
0.92 |
sum / JaXPipe / cpu / Primal |
0.00000792218001151923 s |
0.000008694479984114878 s |
0.91 |
sum / PartOpt / cpu / Primal |
0.00000822441999844159 s |
0.000008412260031036568 s |
0.98 |
sum / IPartOpt / cpu / Primal |
0.000007326939921767916 s |
0.00000878825994732324 s |
0.83 |
sum / HLOOpt / cpu / Primal |
0.00000747927998418163 s |
0.000008662599948365823 s |
0.86 |
sum / DefOpt / cpu / Primal |
0.000007839520021661883 s |
0.000008437960023002233 s |
0.93 |
sum / IDefOpt / cpu / Primal |
0.000008016060037334683 s |
0.000008664920005685418 s |
0.93 |
sum / Jax / cpu / Forward |
0.000011395079982321476 s |
0.00001288352003939508 s |
0.88 |
sum / JaXPipe / cpu / Forward |
0.000010687760013752268 s |
0.0000127289999727509 s |
0.84 |
sum / PartOpt / cpu / Forward |
0.000011098959994342296 s |
0.00001233078003679111 s |
0.90 |
sum / IPartOpt / cpu / Forward |
0.000011429139995016158 s |
0.000012780420038325246 s |
0.89 |
sum / HLOOpt / cpu / Forward |
0.000011722519975592147 s |
0.000012899100038339384 s |
0.91 |
sum / DefOpt / cpu / Forward |
0.000011027780019503552 s |
0.00001248081999619899 s |
0.88 |
sum / IDefOpt / cpu / Forward |
0.00001133386000219616 s |
0.000012676520000241 s |
0.89 |
sum / Jax / cpu / BothRev |
0.00001085068000065803 s |
0.00001194789999317436 s |
0.91 |
sum / JaXPipe / cpu / PreRev |
0.000011334119981256664 s |
0.000012363699952402384 s |
0.92 |
sum / JaXPipe / cpu / PostRev |
0.000010848120027731056 s |
0.00001218069995957194 s |
0.89 |
sum / JaXPipe / cpu / BothRev |
0.000010666480047802906 s |
0.000012381719943732606 s |
0.86 |
sum / PartOpt / cpu / PreRev |
0.00001109199998609256 s |
0.00001217521999933524 s |
0.91 |
sum / PartOpt / cpu / PostRev |
0.000012469899993448052 s |
0.000012258639990250232 s |
1.02 |
sum / PartOpt / cpu / BothRev |
0.00001062449993696646 s |
0.00001247643996066472 s |
0.85 |
sum / IPartOpt / cpu / PreRev |
0.000010665500012692063 s |
0.000012240759997439454 s |
0.87 |
sum / IPartOpt / cpu / PostRev |
0.000010412040037408587 s |
0.000011836020021291916 s |
0.88 |
sum / IPartOpt / cpu / BothRev |
0.000010836100027518114 s |
0.000011904080001841069 s |
0.91 |
sum / HLOOpt / cpu / PreRev |
0.000010459880031703506 s |
0.000012409460023263818 s |
0.84 |
sum / HLOOpt / cpu / PostRev |
0.000010863099996640812 s |
0.000014344759974846966 s |
0.76 |
sum / HLOOpt / cpu / BothRev |
0.000010622259987940196 s |
0.000012370700023893732 s |
0.86 |
sum / DefOpt / cpu / PreRev |
0.000011061980003432835 s |
0.000011943660019824163 s |
0.93 |
sum / DefOpt / cpu / PostRev |
0.00001035970003613329 s |
0.000012389420035106014 s |
0.84 |
sum / DefOpt / cpu / BothRev |
0.000010276300035911846 s |
0.000011991000019406784 s |
0.86 |
sum / IDefOpt / cpu / PreRev |
0.000010844959933820063 s |
0.000011959200001001592 s |
0.91 |
sum / IDefOpt / cpu / PostRev |
0.000010679220022211666 s |
0.000011911360052181409 s |
0.90 |
sum / IDefOpt / cpu / BothRev |
0.000010560920045463718 s |
0.000012511519989857336 s |
0.84 |
sum / Jax / cuda / Primal |
0.00000208 s |
0.000002047 s |
1.02 |
sum / JaXPipe / cuda / Primal |
0.00000208 s |
0.000002047 s |
1.02 |
sum / PartOpt / cuda / Primal |
0.000002048 s |
0.000002047 s |
1.00 |
sum / IPartOpt / cuda / Primal |
0.00000208 s |
0.000002047 s |
1.02 |
sum / HLOOpt / cuda / Primal |
0.000002049 s |
0.000002047 s |
1.00 |
sum / DefOpt / cuda / Primal |
0.00000208 s |
0.000002047 s |
1.02 |
sum / IDefOpt / cuda / Primal |
0.00000208 s |
0.000002047 s |
1.02 |
sum / Jax / cuda / Forward |
0.000011616 s |
0.00001008 s |
1.15 |
sum / JaXPipe / cuda / Forward |
0.000010016 s |
0.000009952 s |
1.01 |
sum / PartOpt / cuda / Forward |
0.000010112 s |
0.000010144 s |
1.00 |
sum / IPartOpt / cuda / Forward |
0.000009952 s |
0.000009952 s |
1 |
sum / HLOOpt / cuda / Forward |
0.00001008 s |
0.000009952 s |
1.01 |
sum / DefOpt / cuda / Forward |
0.000010592 s |
0.00000992 s |
1.07 |
sum / IDefOpt / cuda / Forward |
0.000010336 s |
0.00001024 s |
1.01 |
sum / Jax / cuda / BothRev |
0.000009889 s |
0.00000992 s |
1.00 |
sum / JaXPipe / cuda / PreRev |
0.000009632 s |
0.000009345 s |
1.03 |
sum / JaXPipe / cuda / PostRev |
0.000009504 s |
0.00000928 s |
1.02 |
sum / JaXPipe / cuda / BothRev |
0.000009823 s |
0.00000944 s |
1.04 |
sum / PartOpt / cuda / PreRev |
0.000010144 s |
0.00000992 s |
1.02 |
sum / PartOpt / cuda / PostRev |
0.00000992 s |
0.000009696 s |
1.02 |
sum / PartOpt / cuda / BothRev |
0.0000096 s |
0.000009536 s |
1.01 |
sum / IPartOpt / cuda / PreRev |
0.000009888 s |
0.000009408 s |
1.05 |
sum / IPartOpt / cuda / PostRev |
0.000011072 s |
0.000009536 s |
1.16 |
sum / IPartOpt / cuda / BothRev |
0.00001008 s |
0.000009568 s |
1.05 |
sum / HLOOpt / cuda / PreRev |
0.00000976 s |
0.000009984 s |
0.98 |
sum / HLOOpt / cuda / PostRev |
0.00000976 s |
0.000009632 s |
1.01 |
sum / HLOOpt / cuda / BothRev |
0.000011295 s |
0.000009472 s |
1.19 |
sum / DefOpt / cuda / PreRev |
0.00000976 s |
0.000009856 s |
0.99 |
sum / DefOpt / cuda / PostRev |
0.000009856 s |
0.000009376 s |
1.05 |
sum / DefOpt / cuda / BothRev |
0.000009312000000000002 s |
0.0000096 s |
0.97 |
sum / IDefOpt / cuda / PreRev |
0.000009984 s |
0.00000992 s |
1.01 |
sum / IDefOpt / cuda / PostRev |
0.000010016 s |
0.000009728 s |
1.03 |
sum / IDefOpt / cuda / BothRev |
0.000009856 s |
0.000009856 s |
1 |
sum / Jax / tpu / Primal |
5.1745e-7 s |
5.4685e-7 s |
0.95 |
sum / JaXPipe / tpu / Primal |
5.475e-7 s |
5.1075e-7 s |
1.07 |
sum / PartOpt / tpu / Primal |
5.170249999999999e-7 s |
5.46625e-7 s |
0.95 |
sum / IPartOpt / tpu / Primal |
5.477000000000001e-7 s |
5.10425e-7 s |
1.07 |
sum / HLOOpt / tpu / Primal |
5.17275e-7 s |
5.104499999999999e-7 s |
1.01 |
sum / DefOpt / tpu / Primal |
5.475e-7 s |
5.473499999999999e-7 s |
1.00 |
sum / IDefOpt / tpu / Primal |
5.172999999999999e-7 s |
5.1025e-7 s |
1.01 |
sum / Jax / tpu / Forward |
0.00000155415 s |
0.000001508825 s |
1.03 |
sum / JaXPipe / tpu / Forward |
0.00000150445 s |
0.000001551575 s |
0.97 |
sum / PartOpt / tpu / Forward |
0.000001531325 s |
0.000001493275 s |
1.03 |
sum / IPartOpt / tpu / Forward |
0.000001510125 s |
0.00000152845 s |
0.99 |
sum / HLOOpt / tpu / Forward |
0.00000152995 s |
0.000001528575 s |
1.00 |
sum / DefOpt / tpu / Forward |
0.000001504125 s |
0.000001493475 s |
1.01 |
sum / IDefOpt / tpu / Forward |
0.000001530375 s |
0.0000015284 s |
1.00 |
sum / Jax / tpu / BothRev |
0.000001 s |
0.000001090075 s |
0.92 |
sum / JaXPipe / tpu / PreRev |
0.00000103495 s |
0.0000010533 s |
0.98 |
sum / JaXPipe / tpu / PostRev |
0.000001004 s |
0.00000108595 s |
0.92 |
sum / JaXPipe / tpu / BothRev |
0.00000103125 s |
0.0000010503 s |
0.98 |
sum / PartOpt / tpu / PreRev |
0.00000100525 s |
0.000001084425 s |
0.93 |
sum / PartOpt / tpu / PostRev |
0.000001030725 s |
0.000001054 s |
0.98 |
sum / PartOpt / tpu / BothRev |
0.000001004825 s |
0.0000010963000000000002 s |
0.92 |
sum / IPartOpt / tpu / PreRev |
0.00000103815 s |
0.00000105545 s |
0.98 |
sum / IPartOpt / tpu / PostRev |
0.0000010021 s |
0.000001087275 s |
0.92 |
sum / IPartOpt / tpu / BothRev |
0.0000010341999999999998 s |
0.00000105555 s |
0.98 |
sum / HLOOpt / tpu / PreRev |
0.00000100555 s |
0.000001049675 s |
0.96 |
sum / HLOOpt / tpu / PostRev |
0.000001036375 s |
0.0000010878000000000002 s |
0.95 |
sum / HLOOpt / tpu / BothRev |
0.000001009075 s |
0.0000010470500000000002 s |
0.96 |
sum / DefOpt / tpu / PreRev |
0.0000010426 s |
0.000001088475 s |
0.96 |
sum / DefOpt / tpu / PostRev |
0.000001003475 s |
0.00000105905 s |
0.95 |
sum / DefOpt / tpu / BothRev |
0.000001031925 s |
0.000001083975 s |
0.95 |
sum / IDefOpt / tpu / PreRev |
9.9975e-7 s |
0.0000010464 s |
0.96 |
sum / IDefOpt / tpu / PostRev |
0.000001038 s |
0.000001092975 s |
0.95 |
sum / IDefOpt / tpu / BothRev |
0.000001001175 s |
0.0000010563500000000005 s |
0.95 |
sum / Jax / cpu / Primal |
0.000014644 s |
0.000008546899998691515 s |
1.71 |
sum / JaXPipe / cpu / Primal |
0.000016533 s |
0.000008694479984114878 s |
1.90 |
sum / PartOpt / cpu / Primal |
0.000019811 s |
0.000008412260031036568 s |
2.36 |
sum / IPartOpt / cpu / Primal |
0.000014397 s |
0.00000878825994732324 s |
1.64 |
sum / HLOOpt / cpu / Primal |
0.00001457 s |
0.000008662599948365823 s |
1.68 |
sum / DefOpt / cpu / Primal |
0.000014681 s |
0.000008437960023002233 s |
1.74 |
sum / IDefOpt / cpu / Primal |
0.000014684 s |
0.000008664920005685418 s |
1.69 |
sum / Jax / cpu / Forward |
0.000019999 s |
0.00001288352003939508 s |
1.55 |
sum / JaXPipe / cpu / Forward |
0.000019406 s |
0.0000127289999727509 s |
1.52 |
sum / PartOpt / cpu / Forward |
0.000020281 s |
0.00001233078003679111 s |
1.64 |
sum / IPartOpt / cpu / Forward |
0.000020127 s |
0.000012780420038325246 s |
1.57 |
sum / HLOOpt / cpu / Forward |
0.000020631 s |
0.000012899100038339384 s |
1.60 |
sum / DefOpt / cpu / Forward |
0.000019654 s |
0.00001248081999619899 s |
1.57 |
sum / IDefOpt / cpu / Forward |
0.000020119 s |
0.000012676520000241 s |
1.59 |
sum / Jax / cpu / BothRev |
0.000018973 s |
0.00001194789999317436 s |
1.59 |
sum / JaXPipe / cpu / PreRev |
0.000018682 s |
0.000012363699952402384 s |
1.51 |
sum / JaXPipe / cpu / PostRev |
0.000019024 s |
0.00001218069995957194 s |
1.56 |
sum / JaXPipe / cpu / BothRev |
0.000018431 s |
0.000012381719943732606 s |
1.49 |
sum / PartOpt / cpu / PreRev |
0.00001893 s |
0.00001217521999933524 s |
1.55 |
sum / PartOpt / cpu / PostRev |
0.000018762 s |
0.000012258639990250232 s |
1.53 |
sum / PartOpt / cpu / BothRev |
0.000019137 s |
0.00001247643996066472 s |
1.53 |
sum / IPartOpt / cpu / PreRev |
0.000018609 s |
0.000012240759997439454 s |
1.52 |
sum / IPartOpt / cpu / PostRev |
0.000018889 s |
0.000011836020021291916 s |
1.60 |
sum / IPartOpt / cpu / BothRev |
0.000019085 s |
0.000011904080001841069 s |
1.60 |
sum / HLOOpt / cpu / PreRev |
0.000019152 s |
0.000012409460023263818 s |
1.54 |
sum / HLOOpt / cpu / PostRev |
0.000019456 s |
0.000014344759974846966 s |
1.36 |
sum / HLOOpt / cpu / BothRev |
0.000018954 s |
0.000012370700023893732 s |
1.53 |
sum / DefOpt / cpu / PreRev |
0.000019027 s |
0.000011943660019824163 s |
1.59 |
sum / DefOpt / cpu / PostRev |
0.000019347 s |
0.000012389420035106014 s |
1.56 |
sum / DefOpt / cpu / BothRev |
0.000019173 s |
0.000011991000019406784 s |
1.60 |
sum / IDefOpt / cpu / PreRev |
0.000019029 s |
0.000011959200001001592 s |
1.59 |
sum / IDefOpt / cpu / PostRev |
0.000018878 s |
0.000011911360052181409 s |
1.58 |
sum / IDefOpt / cpu / BothRev |
0.000018813 s |
0.000012511519989857336 s |
1.50 |
sum / Jax / cpu / Primal |
0.000033 s |
0.000008546899998691515 s |
3.86 |
sum / JaXPipe / cpu / Primal |
0.00001 s |
0.000008694479984114878 s |
1.15 |
sum / PartOpt / cpu / Primal |
0.00001 s |
0.000008412260031036568 s |
1.19 |
sum / IPartOpt / cpu / Primal |
0.00001 s |
0.00000878825994732324 s |
1.14 |
sum / HLOOpt / cpu / Primal |
0.00001 s |
0.000008662599948365823 s |
1.15 |
sum / DefOpt / cpu / Primal |
0.00001 s |
0.000008437960023002233 s |
1.19 |
sum / IDefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000008664920005685418 s |
1.04 |
sum / Jax / cpu / Forward |
0.000014 s |
0.00001288352003939508 s |
1.09 |
sum / JaXPipe / cpu / Forward |
0.000014 s |
0.0000127289999727509 s |
1.10 |
sum / PartOpt / cpu / Forward |
0.000014 s |
0.00001233078003679111 s |
1.14 |
sum / IPartOpt / cpu / Forward |
0.000014 s |
0.000012780420038325246 s |
1.10 |
sum / HLOOpt / cpu / Forward |
0.000014 s |
0.000012899100038339384 s |
1.09 |
sum / DefOpt / cpu / Forward |
0.000014 s |
0.00001248081999619899 s |
1.12 |
sum / IDefOpt / cpu / Forward |
0.000014 s |
0.000012676520000241 s |
1.10 |
sum / Jax / cpu / BothRev |
0.000013 s |
0.00001194789999317436 s |
1.09 |
sum / JaXPipe / cpu / PreRev |
0.000013 s |
0.000012363699952402384 s |
1.05 |
sum / JaXPipe / cpu / PostRev |
0.000013 s |
0.00001218069995957194 s |
1.07 |
sum / JaXPipe / cpu / BothRev |
0.000014 s |
0.000012381719943732606 s |
1.13 |
sum / PartOpt / cpu / PreRev |
0.000014 s |
0.00001217521999933524 s |
1.15 |
sum / PartOpt / cpu / PostRev |
0.000013 s |
0.000012258639990250232 s |
1.06 |
sum / PartOpt / cpu / BothRev |
0.000014 s |
0.00001247643996066472 s |
1.12 |
sum / IPartOpt / cpu / PreRev |
0.000013 s |
0.000012240759997439454 s |
1.06 |
sum / IPartOpt / cpu / PostRev |
0.000014 s |
0.000011836020021291916 s |
1.18 |
sum / IPartOpt / cpu / BothRev |
0.000013 s |
0.000011904080001841069 s |
1.09 |
sum / HLOOpt / cpu / PreRev |
0.000013 s |
0.000012409460023263818 s |
1.05 |
sum / HLOOpt / cpu / PostRev |
0.000013 s |
0.000014344759974846966 s |
0.91 |
sum / HLOOpt / cpu / BothRev |
0.000014 s |
0.000012370700023893732 s |
1.13 |
sum / DefOpt / cpu / PreRev |
0.000013 s |
0.000011943660019824163 s |
1.09 |
sum / DefOpt / cpu / PostRev |
0.000013 s |
0.000012389420035106014 s |
1.05 |
sum / DefOpt / cpu / BothRev |
0.000013 s |
0.000011991000019406784 s |
1.08 |
sum / IDefOpt / cpu / PreRev |
0.000014 s |
0.000011959200001001592 s |
1.17 |
sum / IDefOpt / cpu / PostRev |
0.000013 s |
0.000011911360052181409 s |
1.09 |
sum / IDefOpt / cpu / BothRev |
0.000014 s |
0.000012511519989857336 s |
1.12 |
value_and_grad / Jax / cpu / Primal |
0.000013980399980937363 s |
0.000015932120040815788 s |
0.88 |
value_and_grad / JaXPipe / cpu / Primal |
0.000014040859960005036 s |
0.00001542877999781922 s |
0.91 |
value_and_grad / PartOpt / cpu / Primal |
0.000013734500007558382 s |
0.000015459419983017143 s |
0.89 |
value_and_grad / IPartOpt / cpu / Primal |
0.000013085560030958732 s |
0.000016022300014810755 s |
0.82 |
value_and_grad / HLOOpt / cpu / Primal |
0.000014029479971213731 s |
0.00001495937996878638 s |
0.94 |
value_and_grad / DefOpt / cpu / Primal |
0.00001298357998166466 s |
0.000015086439989318025 s |
0.86 |
value_and_grad / IDefOpt / cpu / Primal |
0.000013514260017473134 s |
0.000015966919945640257 s |
0.85 |
value_and_grad / Jax / cuda / Primal |
0.000033345 s |
0.000032832 s |
1.02 |
value_and_grad / JaXPipe / cuda / Primal |
0.000032543 s |
0.000032192 s |
1.01 |
value_and_grad / PartOpt / cuda / Primal |
0.000032767999999999995 s |
0.000032959 s |
0.99 |
value_and_grad / IPartOpt / cuda / Primal |
0.000032577 s |
0.000032543 s |
1.00 |
value_and_grad / HLOOpt / cuda / Primal |
0.000033184 s |
0.000033119999999999995 s |
1.00 |
value_and_grad / DefOpt / cuda / Primal |
0.00003344 s |
0.000032288 s |
1.04 |
value_and_grad / IDefOpt / cuda / Primal |
0.000033344 s |
0.00003184 s |
1.05 |
value_and_grad / Jax / tpu / Primal |
0 s |
0 s |
1 |
value_and_grad / JaXPipe / 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 / HLOOpt / 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 / Jax / cpu / Primal |
0.000022699 s |
0.000015932120040815788 s |
1.42 |
value_and_grad / JaXPipe / cpu / Primal |
0.000023062 s |
0.00001542877999781922 s |
1.49 |
value_and_grad / PartOpt / cpu / Primal |
0.000023007 s |
0.000015459419983017143 s |
1.49 |
value_and_grad / IPartOpt / cpu / Primal |
0.00002326 s |
0.000016022300014810755 s |
1.45 |
value_and_grad / HLOOpt / cpu / Primal |
0.000023085 s |
0.00001495937996878638 s |
1.54 |
value_and_grad / DefOpt / cpu / Primal |
0.000023074 s |
0.000015086439989318025 s |
1.53 |
value_and_grad / IDefOpt / cpu / Primal |
0.000023086 s |
0.000015966919945640257 s |
1.45 |
value_and_grad / Jax / cpu / Primal |
0.000016 s |
0.000015932120040815788 s |
1.00 |
value_and_grad / JaXPipe / cpu / Primal |
0.000017 s |
0.00001542877999781922 s |
1.10 |
value_and_grad / PartOpt / cpu / Primal |
0.000017 s |
0.000015459419983017143 s |
1.10 |
value_and_grad / IPartOpt / cpu / Primal |
0.000017999999999999997 s |
0.000016022300014810755 s |
1.12 |
value_and_grad / HLOOpt / cpu / Primal |
0.000017 s |
0.00001495937996878638 s |
1.14 |
value_and_grad / DefOpt / cpu / Primal |
0.000016 s |
0.000015086439989318025 s |
1.06 |
value_and_grad / IDefOpt / cpu / Primal |
0.000015 s |
0.000015966919945640257 s |
0.94 |
jaxmd20 / Jax / cuda / Primal |
0.001463458 s |
0.001515699 s |
0.97 |
jaxmd20 / JaXPipe / cuda / Primal |
0.001449667 s |
0.001502068 s |
0.97 |
jaxmd20 / PartOpt / cuda / Primal |
0.001337955 s |
0.001303734 s |
1.03 |
jaxmd20 / IPartOpt / cuda / Primal |
0.00130653 s |
0.001324502 s |
0.99 |
jaxmd20 / HLOOpt / cuda / Primal |
0.001338979 s |
0.001316338 s |
1.02 |
jaxmd20 / DefOpt / cuda / Primal |
0.000920289 s |
0.000916986 s |
1.00 |
jaxmd20 / IDefOpt / cuda / Primal |
0.000950977 s |
0.000950392 s |
1.00 |
jaxmd20 / Jax / cuda / Forward |
0.001857987 s |
0.00180357 s |
1.03 |
jaxmd20 / JaXPipe / cuda / Forward |
0.001573539 s |
0.001554066 s |
1.01 |
jaxmd20 / PartOpt / cuda / Forward |
0.001633028 s |
0.001636595 s |
1.00 |
jaxmd20 / IPartOpt / cuda / Forward |
0.001645667 s |
0.001628435 s |
1.01 |
jaxmd20 / HLOOpt / cuda / Forward |
0.001629763 s |
0.001628338 s |
1.00 |
jaxmd20 / DefOpt / cuda / Forward |
0.001632163 s |
0.001648402 s |
0.99 |
jaxmd20 / IDefOpt / cuda / Forward |
0.001622915 s |
0.001610963 s |
1.01 |
jaxmd20 / Jax / cuda / BothRev |
0.00529262 s |
0.005374405 s |
0.98 |
jaxmd20 / JaXPipe / cuda / PreRev |
0.002670213 s |
0.00267236 s |
1.00 |
jaxmd20 / JaXPipe / cuda / PostRev |
0.005298665 s |
0.005362591 s |
0.99 |
jaxmd20 / JaXPipe / cuda / BothRev |
0.0026909169999999 s |
0.0027405529999999 s |
0.98 |
jaxmd20 / PartOpt / cuda / PreRev |
0.002808649 s |
0.002867273 s |
0.98 |
jaxmd20 / PartOpt / cuda / PostRev |
0.005364811 s |
0.005403988 s |
0.99 |
jaxmd20 / PartOpt / cuda / BothRev |
0.002748806 s |
0.002758153 s |
1.00 |
jaxmd20 / IPartOpt / cuda / PreRev |
0.002811846 s |
0.002793064 s |
1.01 |
jaxmd20 / IPartOpt / cuda / PostRev |
0.005369643 s |
0.005419859 s |
0.99 |
jaxmd20 / IPartOpt / cuda / BothRev |
0.002771301 s |
0.002777959 s |
1.00 |
jaxmd20 / HLOOpt / cuda / PreRev |
0.002758149 s |
0.002730279 s |
1.01 |
jaxmd20 / HLOOpt / cuda / PostRev |
0.005329676 s |
0.005283831 s |
1.01 |
jaxmd20 / HLOOpt / cuda / BothRev |
0.00271194 s |
0.00273217 s |
0.99 |
jaxmd20 / DefOpt / cuda / PreRev |
0.0028165499999999 s |
0.002815432 s |
1.00 |
jaxmd20 / DefOpt / cuda / PostRev |
0.002711141 s |
0.002721953 s |
1.00 |
jaxmd20 / DefOpt / cuda / BothRev |
0.002775237 s |
0.0027546 s |
1.01 |
jaxmd20 / IDefOpt / cuda / PreRev |
0.00282679 s |
0.002798055 s |
1.01 |
jaxmd20 / IDefOpt / cuda / PostRev |
0.0023269799999999 s |
0.00230251 s |
1.01 |
jaxmd20 / IDefOpt / cuda / BothRev |
0.002752039 s |
0.002761108 s |
1.00 |
jaxmd20 / Jax / tpu / Primal |
0.009287263125 s |
0.009278386875 s |
1.00 |
jaxmd20 / JaXPipe / tpu / Primal |
0.0092772468749999 s |
0.009287865 s |
1.00 |
jaxmd20 / PartOpt / tpu / Primal |
0.0092005775 s |
0.009197413125 s |
1.00 |
jaxmd20 / IPartOpt / tpu / Primal |
0.00919791375 s |
0.009201908125 s |
1.00 |
jaxmd20 / HLOOpt / tpu / Primal |
0.0091782368749999 s |
0.00917926125 s |
1.00 |
jaxmd20 / DefOpt / tpu / Primal |
0.008796813125 s |
0.00879857125 s |
1.00 |
jaxmd20 / IDefOpt / tpu / Primal |
0.0087020725 s |
0.008701575 s |
1.00 |
jaxmd20 / Jax / tpu / Forward |
0.01873506125 s |
0.018750668125 s |
1.00 |
jaxmd20 / JaXPipe / tpu / Forward |
0.017417691875 s |
0.017421941875 s |
1.00 |
jaxmd20 / PartOpt / tpu / Forward |
0.0174260275 s |
0.017423065 s |
1.00 |
jaxmd20 / IPartOpt / tpu / Forward |
0.017423526875 s |
0.01741626125 s |
1.00 |
jaxmd20 / HLOOpt / tpu / Forward |
0.01739882625 s |
0.01740896375 s |
1.00 |
jaxmd20 / DefOpt / tpu / Forward |
0.01742464875 s |
0.0174240481249999 s |
1.00 |
jaxmd20 / IDefOpt / tpu / Forward |
0.017411576875 s |
0.0174109625 s |
1.00 |
jaxmd20 / Jax / tpu / BothRev |
0.021874050625 s |
0.02187549375 s |
1.00 |
jaxmd20 / JaXPipe / tpu / PreRev |
0.025495241875 s |
0.0254711174999999 s |
1.00 |
jaxmd20 / JaXPipe / tpu / PostRev |
0.021555738125 s |
0.02187455375 s |
0.99 |
jaxmd20 / JaXPipe / tpu / BothRev |
0.0254920318749999 s |
0.025454668125 s |
1.00 |
jaxmd20 / PartOpt / tpu / PreRev |
0.0254645225 s |
0.025500503125 s |
1.00 |
jaxmd20 / PartOpt / tpu / PostRev |
0.02152711625 s |
0.021509539375 s |
1.00 |
jaxmd20 / PartOpt / tpu / BothRev |
0.0255534312499999 s |
0.025581229375 s |
1.00 |
jaxmd20 / IPartOpt / tpu / PreRev |
0.025499565 s |
0.02546226125 s |
1.00 |
jaxmd20 / IPartOpt / tpu / PostRev |
0.021509524375 s |
0.021520011875 s |
1.00 |
jaxmd20 / IPartOpt / tpu / BothRev |
0.025577014375 s |
0.02555030875 s |
1.00 |
jaxmd20 / HLOOpt / tpu / PreRev |
0.0255715174999999 s |
0.025571803125 s |
1.00 |
jaxmd20 / HLOOpt / tpu / PostRev |
0.020810156875 s |
0.0208195193749999 s |
1.00 |
jaxmd20 / HLOOpt / tpu / BothRev |
0.025675656875 s |
0.025676069375 s |
1.00 |
jaxmd20 / DefOpt / tpu / PreRev |
0.0254987368749999 s |
0.025501114375 s |
1.00 |
jaxmd20 / DefOpt / tpu / PostRev |
0.01880938 s |
0.01881101125 s |
1.00 |
jaxmd20 / DefOpt / tpu / BothRev |
0.0255854375 s |
0.02558739625 s |
1.00 |
jaxmd20 / IDefOpt / tpu / PreRev |
0.025458410625 s |
0.02546454875 s |
1.00 |
jaxmd20 / IDefOpt / tpu / PostRev |
0.018320804375 s |
0.0183198049999999 s |
1.00 |
jaxmd20 / IDefOpt / tpu / BothRev |
0.02555742 s |
0.025556130625 s |
1.00 |
jaxmd40 / Jax / cpu / Primal |
0.071632347 s |
0.064726397 s |
1.11 |
jaxmd40 / JaXPipe / cpu / Primal |
0.071921591 s |
0.0710995 s |
1.01 |
jaxmd40 / PartOpt / cpu / Primal |
0.067216103 s |
0.0735390809999999 s |
0.91 |
jaxmd40 / IPartOpt / cpu / Primal |
0.072087491 s |
0.074325466 s |
0.97 |
jaxmd40 / HLOOpt / cpu / Primal |
0.091305056 s |
0.091431759 s |
1.00 |
jaxmd40 / DefOpt / cpu / Primal |
0.088296598 s |
0.092193808 s |
0.96 |
jaxmd40 / IDefOpt / cpu / Primal |
0.0843185 s |
0.0868588709999999 s |
0.97 |
jaxmd40 / Jax / cpu / Forward |
0.091231036 s |
0.096498974 s |
0.95 |
jaxmd40 / JaXPipe / cpu / Forward |
0.176169474 s |
0.169716206 s |
1.04 |
jaxmd40 / PartOpt / cpu / Forward |
0.173537474 s |
0.171666692 s |
1.01 |
jaxmd40 / IPartOpt / cpu / Forward |
0.166528625 s |
0.166021188 s |
1.00 |
jaxmd40 / HLOOpt / cpu / Forward |
0.165825902 s |
0.173637867 s |
0.96 |
jaxmd40 / DefOpt / cpu / Forward |
0.169339371 s |
0.163862997 s |
1.03 |
jaxmd40 / IDefOpt / cpu / Forward |
0.166254004 s |
0.164408476 s |
1.01 |
jaxmd40 / Jax / cpu / BothRev |
0.1338236139999999 s |
0.14647163 s |
0.91 |
jaxmd40 / JaXPipe / cpu / PreRev |
0.234649766 s |
0.246420341 s |
0.95 |
jaxmd40 / JaXPipe / cpu / PostRev |
0.136609496 s |
0.142790002 s |
0.96 |
jaxmd40 / JaXPipe / cpu / BothRev |
0.22955504 s |
0.235643853 s |
0.97 |
jaxmd40 / PartOpt / cpu / PreRev |
0.217366972 s |
0.238793437 s |
0.91 |
jaxmd40 / PartOpt / cpu / PostRev |
0.126653321 s |
0.130844221 s |
0.97 |
jaxmd40 / PartOpt / cpu / BothRev |
0.251363437 s |
0.234667297 s |
1.07 |
jaxmd40 / IPartOpt / cpu / PreRev |
0.213504054 s |
0.2315206159999999 s |
0.92 |
jaxmd40 / IPartOpt / cpu / PostRev |
0.129869859 s |
0.139821482 s |
0.93 |
jaxmd40 / IPartOpt / cpu / BothRev |
0.235701106 s |
0.25754629 s |
0.92 |
jaxmd40 / HLOOpt / cpu / PreRev |
0.241935043 s |
0.242932352 s |
1.00 |
jaxmd40 / HLOOpt / cpu / PostRev |
0.173478582 s |
0.179192015 s |
0.97 |
jaxmd40 / HLOOpt / cpu / BothRev |
0.260457222 s |
0.257848239 s |
1.01 |
jaxmd40 / DefOpt / cpu / PreRev |
0.225233193 s |
0.229896429 s |
0.98 |
jaxmd40 / DefOpt / cpu / PostRev |
0.17958246 s |
0.1780652939999999 s |
1.01 |
jaxmd40 / DefOpt / cpu / BothRev |
0.260420689 s |
0.232200429 s |
1.12 |
jaxmd40 / IDefOpt / cpu / PreRev |
0.239266497 s |
0.227594538 s |
1.05 |
jaxmd40 / IDefOpt / cpu / PostRev |
0.190419116 s |
0.179249319 s |
1.06 |
jaxmd40 / IDefOpt / cpu / BothRev |
0.252163502 s |
0.238341839 s |
1.06 |
This comment was automatically generated by workflow using github-action-benchmark.
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.