-
Notifications
You must be signed in to change notification settings - Fork 25
Update jax-ml/jax to commit 816e644cc4eb1a4353894ba52d5e0d92716936e5 #1791
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
Open
enzymead-bot
wants to merge
3
commits into
main
Choose a base branch
from
update-jax-ml-jax
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and old review comments may become outdated.
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
EnzymeJAX Benchmarks
Details
| Benchmark suite | Current: 4471232 | Previous: 139149a | Ratio |
|---|---|---|---|
actmtch / JaXPipe / cpu / Primal |
0.000007681120005145203 s |
0.000007320119966607308 s |
1.05 |
actmtch / Jax / cpu / Primal |
0.000006886820028739749 s |
0.000006830180000179098 s |
1.01 |
actmtch / HLOOpt / cpu / Primal |
0.000007867759986766032 s |
0.000007744339964119717 s |
1.02 |
actmtch / PartOpt / cpu / Primal |
0.0000069038799938425655 s |
0.0000063939800020307306 s |
1.08 |
actmtch / IPartOpt / cpu / Primal |
0.000007453219996023108 s |
0.000006602240009669913 s |
1.13 |
actmtch / DefOpt / cpu / Primal |
0.000008223839995480375 s |
0.00000696203999723366 s |
1.18 |
actmtch / IDefOpt / cpu / Primal |
0.000007849800003896235 s |
0.000007290520006790757 s |
1.08 |
actmtch / JaXPipe / cpu / Forward |
0.000011404339975342737 s |
0.000010564379999777885 s |
1.08 |
actmtch / Jax / cpu / Forward |
0.00001080464002370718 s |
0.000009786259952306863 s |
1.10 |
actmtch / HLOOpt / cpu / Forward |
0.000011954980063819676 s |
0.00001134779996391444 s |
1.05 |
actmtch / PartOpt / cpu / Forward |
0.000011230119980609745 s |
0.00001038470002640679 s |
1.08 |
actmtch / IPartOpt / cpu / Forward |
0.000012238420022185893 s |
0.000010790480018840752 s |
1.13 |
actmtch / DefOpt / cpu / Forward |
0.00001183699995635834 s |
0.000010597319960652385 s |
1.12 |
actmtch / IDefOpt / cpu / Forward |
0.00001188043996990018 s |
0.000010714560012274888 s |
1.11 |
actmtch / JaXPipe / cpu / PreRev |
0.000011973579976256588 s |
0.000011346840001351664 s |
1.06 |
actmtch / JaXPipe / cpu / PostRev |
0.000011732480006685364 s |
0.000010035259974756628 s |
1.17 |
actmtch / JaXPipe / cpu / BothRev |
0.000013013779989705654 s |
0.000011080100039180252 s |
1.17 |
actmtch / Jax / cpu / BothRev |
0.000010751739982879372 s |
0.000009212080003635492 s |
1.17 |
actmtch / HLOOpt / cpu / PreRev |
0.000012261379979463526 s |
0.000011040720009987124 s |
1.11 |
actmtch / HLOOpt / cpu / PostRev |
0.000014395579992196872 s |
0.00001305266002418648 s |
1.10 |
actmtch / HLOOpt / cpu / BothRev |
0.00001209116000609356 s |
0.000010760040013337857 s |
1.12 |
actmtch / PartOpt / cpu / PreRev |
0.000011862300007123849 s |
0.00001040318003106222 s |
1.14 |
actmtch / PartOpt / cpu / PostRev |
0.000010773859949040342 s |
0.000010260040016873971 s |
1.05 |
actmtch / PartOpt / cpu / BothRev |
0.00001352908003354969 s |
0.00001096735995815834 s |
1.23 |
actmtch / IPartOpt / cpu / PreRev |
0.000011685780009429436 s |
0.000010797939985423 s |
1.08 |
actmtch / IPartOpt / cpu / PostRev |
0.000011332359999869368 s |
0.000009893180049402872 s |
1.15 |
actmtch / IPartOpt / cpu / BothRev |
0.000012909960014440003 s |
0.00001106279998566606 s |
1.17 |
actmtch / DefOpt / cpu / PreRev |
0.000011700900004143475 s |
0.000010808880033437162 s |
1.08 |
actmtch / DefOpt / cpu / PostRev |
0.000012323520040808944 s |
0.00001125027999478334 s |
1.10 |
actmtch / DefOpt / cpu / BothRev |
0.000012437539999154978 s |
0.000010869620036828564 s |
1.14 |
actmtch / IDefOpt / cpu / PreRev |
0.00001175655998849834 s |
0.000011085179985457216 s |
1.06 |
actmtch / IDefOpt / cpu / PostRev |
0.000012077140036126366 s |
0.000011287999977867005 s |
1.07 |
actmtch / IDefOpt / cpu / BothRev |
0.00001261412002349971 s |
0.000010600419991533271 s |
1.19 |
actmtch / JaXPipe / cuda / Primal |
0.000002016 s |
0.0000024 s |
0.84 |
actmtch / Jax / cuda / Primal |
0.000002016 s |
0.0000024 s |
0.84 |
actmtch / HLOOpt / cuda / Primal |
0.000002047 s |
0.000002399 s |
0.85 |
actmtch / PartOpt / cuda / Primal |
0.000002016 s |
0.000002399 s |
0.84 |
actmtch / IPartOpt / cuda / Primal |
0.000002016 s |
0.000002369 s |
0.85 |
actmtch / DefOpt / cuda / Primal |
0.000002016 s |
0.000002399 s |
0.84 |
actmtch / IDefOpt / cuda / Primal |
0.000002015 s |
0.000002368 s |
0.85 |
actmtch / JaXPipe / cuda / Forward |
0.00001008 s |
0.000010689 s |
0.94 |
actmtch / Jax / cuda / Forward |
0.000009951 s |
0.000010623 s |
0.94 |
actmtch / HLOOpt / cuda / Forward |
0.000010273 s |
0.000010336 s |
0.99 |
actmtch / PartOpt / cuda / Forward |
0.00001008 s |
0.000010591 s |
0.95 |
actmtch / IPartOpt / cuda / Forward |
0.000010272 s |
0.000010528 s |
0.98 |
actmtch / DefOpt / cuda / Forward |
0.00001056 s |
0.000010368 s |
1.02 |
actmtch / IDefOpt / cuda / Forward |
0.00001136 s |
0.000010432 s |
1.09 |
actmtch / JaXPipe / cuda / PreRev |
0.000012224 s |
0.000010783 s |
1.13 |
actmtch / JaXPipe / cuda / PostRev |
0.000011936 s |
0.000015712 s |
0.76 |
actmtch / JaXPipe / cuda / BothRev |
0.000010368 s |
0.000010367 s |
1.00 |
actmtch / Jax / cuda / BothRev |
0.00001024 s |
0.000010751 s |
0.95 |
actmtch / HLOOpt / cuda / PreRev |
0.000010176 s |
0.000010752 s |
0.95 |
actmtch / HLOOpt / cuda / PostRev |
0.00001008 s |
0.000010336 s |
0.98 |
actmtch / HLOOpt / cuda / BothRev |
0.00001168 s |
0.000010688 s |
1.09 |
actmtch / PartOpt / cuda / PreRev |
0.000010432 s |
0.000010976 s |
0.95 |
actmtch / PartOpt / cuda / PostRev |
0.000010176 s |
0.00001072 s |
0.95 |
actmtch / PartOpt / cuda / BothRev |
0.000010016 s |
0.000011008 s |
0.91 |
actmtch / IPartOpt / cuda / PreRev |
0.000012 s |
0.000010656 s |
1.13 |
actmtch / IPartOpt / cuda / PostRev |
0.000011904 s |
0.000010784 s |
1.10 |
actmtch / IPartOpt / cuda / BothRev |
0.000010592 s |
0.000010272 s |
1.03 |
actmtch / DefOpt / cuda / PreRev |
0.000011423 s |
0.000011008 s |
1.04 |
actmtch / DefOpt / cuda / PostRev |
0.000011617 s |
0.000010848 s |
1.07 |
actmtch / DefOpt / cuda / BothRev |
0.00001104 s |
0.000010464 s |
1.06 |
actmtch / IDefOpt / cuda / PreRev |
0.000011904 s |
0.000010624 s |
1.12 |
actmtch / IDefOpt / cuda / PostRev |
0.000009665 s |
0.000010688 s |
0.90 |
actmtch / IDefOpt / cuda / BothRev |
0.000010207 s |
0.000010848 s |
0.94 |
actmtch / JaXPipe / cpu / Primal |
0.000016698000000000002 s |
0.000007320119966607308 s |
2.28 |
actmtch / Jax / cpu / Primal |
0.000016692 s |
0.000006830180000179098 s |
2.44 |
actmtch / HLOOpt / cpu / Primal |
0.000017334 s |
0.000007744339964119717 s |
2.24 |
actmtch / PartOpt / cpu / Primal |
0.000016578 s |
0.0000063939800020307306 s |
2.59 |
actmtch / IPartOpt / cpu / Primal |
0.000016597 s |
0.000006602240009669913 s |
2.51 |
actmtch / DefOpt / cpu / Primal |
0.000017437999999999998 s |
0.00000696203999723366 s |
2.50 |
actmtch / IDefOpt / cpu / Primal |
0.000017892 s |
0.000007290520006790757 s |
2.45 |
actmtch / JaXPipe / cpu / Forward |
0.000024098 s |
0.000010564379999777885 s |
2.28 |
actmtch / Jax / cpu / Forward |
0.000022374000000000003 s |
0.000009786259952306863 s |
2.29 |
actmtch / HLOOpt / cpu / Forward |
0.000023772 s |
0.00001134779996391444 s |
2.09 |
actmtch / PartOpt / cpu / Forward |
0.000023618 s |
0.00001038470002640679 s |
2.27 |
actmtch / IPartOpt / cpu / Forward |
0.0000236 s |
0.000010790480018840752 s |
2.19 |
actmtch / DefOpt / cpu / Forward |
0.000023645 s |
0.000010597319960652385 s |
2.23 |
actmtch / IDefOpt / cpu / Forward |
0.000023807 s |
0.000010714560012274888 s |
2.22 |
actmtch / JaXPipe / cpu / PreRev |
0.000025087 s |
0.000011346840001351664 s |
2.21 |
actmtch / JaXPipe / cpu / PostRev |
0.000021998 s |
0.000010035259974756628 s |
2.19 |
actmtch / JaXPipe / cpu / BothRev |
0.000023997 s |
0.000011080100039180252 s |
2.17 |
actmtch / Jax / cpu / BothRev |
0.000022362 s |
0.000009212080003635492 s |
2.43 |
actmtch / HLOOpt / cpu / PreRev |
0.00002407 s |
0.000011040720009987124 s |
2.18 |
actmtch / HLOOpt / cpu / PostRev |
0.0000242 s |
0.00001305266002418648 s |
1.85 |
actmtch / HLOOpt / cpu / BothRev |
0.000023554 s |
0.000010760040013337857 s |
2.19 |
actmtch / PartOpt / cpu / PreRev |
0.00002377 s |
0.00001040318003106222 s |
2.28 |
actmtch / PartOpt / cpu / PostRev |
0.000036265 s |
0.000010260040016873971 s |
3.53 |
actmtch / PartOpt / cpu / BothRev |
0.000024062 s |
0.00001096735995815834 s |
2.19 |
actmtch / IPartOpt / cpu / PreRev |
0.000024517 s |
0.000010797939985423 s |
2.27 |
actmtch / IPartOpt / cpu / PostRev |
0.000022367 s |
0.000009893180049402872 s |
2.26 |
actmtch / IPartOpt / cpu / BothRev |
0.000024642 s |
0.00001106279998566606 s |
2.23 |
actmtch / DefOpt / cpu / PreRev |
0.00002417 s |
0.000010808880033437162 s |
2.24 |
actmtch / DefOpt / cpu / PostRev |
0.000024029 s |
0.00001125027999478334 s |
2.14 |
actmtch / DefOpt / cpu / BothRev |
0.000023885 s |
0.000010869620036828564 s |
2.20 |
actmtch / IDefOpt / cpu / PreRev |
0.000023641 s |
0.000011085179985457216 s |
2.13 |
actmtch / IDefOpt / cpu / PostRev |
0.000023805 s |
0.000011287999977867005 s |
2.11 |
actmtch / IDefOpt / cpu / BothRev |
0.000024575 s |
0.000010600419991533271 s |
2.32 |
actmtch / JaXPipe / cpu / Primal |
0.000008999999999999999 s |
0.000007320119966607308 s |
1.23 |
actmtch / Jax / cpu / Primal |
0.000008999999999999999 s |
0.000006830180000179098 s |
1.32 |
actmtch / HLOOpt / cpu / Primal |
0.00001 s |
0.000007744339964119717 s |
1.29 |
actmtch / PartOpt / cpu / Primal |
0.000008999999999999999 s |
0.0000063939800020307306 s |
1.41 |
actmtch / IPartOpt / cpu / Primal |
0.000008999999999999999 s |
0.000006602240009669913 s |
1.36 |
actmtch / DefOpt / cpu / Primal |
0.000008 s |
0.00000696203999723366 s |
1.15 |
actmtch / IDefOpt / cpu / Primal |
0.000008 s |
0.000007290520006790757 s |
1.10 |
actmtch / JaXPipe / cpu / Forward |
0.000013 s |
0.000010564379999777885 s |
1.23 |
actmtch / Jax / cpu / Forward |
0.000012 s |
0.000009786259952306863 s |
1.23 |
actmtch / HLOOpt / cpu / Forward |
0.000013 s |
0.00001134779996391444 s |
1.15 |
actmtch / PartOpt / cpu / Forward |
0.000013 s |
0.00001038470002640679 s |
1.25 |
actmtch / IPartOpt / cpu / Forward |
0.000012 s |
0.000010790480018840752 s |
1.11 |
actmtch / DefOpt / cpu / Forward |
0.000014 s |
0.000010597319960652385 s |
1.32 |
actmtch / IDefOpt / cpu / Forward |
0.000012 s |
0.000010714560012274888 s |
1.12 |
actmtch / JaXPipe / cpu / PreRev |
0.000012 s |
0.000011346840001351664 s |
1.06 |
actmtch / JaXPipe / cpu / PostRev |
0.000011 s |
0.000010035259974756628 s |
1.10 |
actmtch / JaXPipe / cpu / BothRev |
0.000012 s |
0.000011080100039180252 s |
1.08 |
actmtch / Jax / cpu / BothRev |
0.000011 s |
0.000009212080003635492 s |
1.19 |
actmtch / HLOOpt / cpu / PreRev |
0.000012 s |
0.000011040720009987124 s |
1.09 |
actmtch / HLOOpt / cpu / PostRev |
0.000013 s |
0.00001305266002418648 s |
1.00 |
actmtch / HLOOpt / cpu / BothRev |
0.000013 s |
0.000010760040013337857 s |
1.21 |
actmtch / PartOpt / cpu / PreRev |
0.000013 s |
0.00001040318003106222 s |
1.25 |
actmtch / PartOpt / cpu / PostRev |
0.000011 s |
0.000010260040016873971 s |
1.07 |
actmtch / PartOpt / cpu / BothRev |
0.000013 s |
0.00001096735995815834 s |
1.19 |
actmtch / IPartOpt / cpu / PreRev |
0.000013 s |
0.000010797939985423 s |
1.20 |
actmtch / IPartOpt / cpu / PostRev |
0.000011 s |
0.000009893180049402872 s |
1.11 |
actmtch / IPartOpt / cpu / BothRev |
0.000014 s |
0.00001106279998566606 s |
1.27 |
actmtch / DefOpt / cpu / PreRev |
0.000012 s |
0.000010808880033437162 s |
1.11 |
actmtch / DefOpt / cpu / PostRev |
0.000013 s |
0.00001125027999478334 s |
1.16 |
actmtch / DefOpt / cpu / BothRev |
0.000013 s |
0.000010869620036828564 s |
1.20 |
actmtch / IDefOpt / cpu / PreRev |
0.000013 s |
0.000011085179985457216 s |
1.17 |
actmtch / IDefOpt / cpu / PostRev |
0.000014 s |
0.000011287999977867005 s |
1.24 |
actmtch / IDefOpt / cpu / BothRev |
0.000013 s |
0.000010600419991533271 s |
1.23 |
add_one / JaXPipe / cpu / Primal |
0.000007306760044230032 s |
0.000006907579991093371 s |
1.06 |
add_one / Jax / cpu / Primal |
0.000007426339961966732 s |
0.00000676276001286169 s |
1.10 |
add_one / HLOOpt / cpu / Primal |
0.000007707540007686475 s |
0.000006887820009069401 s |
1.12 |
add_one / PartOpt / cpu / Primal |
0.000007051379952827119 s |
0.000006576520008820807 s |
1.07 |
add_one / IPartOpt / cpu / Primal |
0.000007697539995206171 s |
0.000006939099985174835 s |
1.11 |
add_one / DefOpt / cpu / Primal |
0.000006997220052653574 s |
0.000006486319989562617 s |
1.08 |
add_one / IDefOpt / cpu / Primal |
0.000007345739986703848 s |
0.000006594699962079176 s |
1.11 |
add_one / JaXPipe / cpu / Forward |
0.000011883060060426945 s |
0.00000948447996051982 s |
1.25 |
add_one / Jax / cpu / Forward |
0.000011302680013614008 s |
0.000009536679981465567 s |
1.19 |
add_one / HLOOpt / cpu / Forward |
0.000011574059963095353 s |
0.00000980943999820738 s |
1.18 |
add_one / PartOpt / cpu / Forward |
0.000011403499984226072 s |
0.000009570080001140014 s |
1.19 |
add_one / IPartOpt / cpu / Forward |
0.00001151891997324128 s |
0.00000947989996348042 s |
1.22 |
add_one / DefOpt / cpu / Forward |
0.000011350479971952157 s |
0.000010185959999944315 s |
1.11 |
add_one / IDefOpt / cpu / Forward |
0.00001146134000919119 s |
0.000009939120009221367 s |
1.15 |
add_one / JaXPipe / cpu / PreRev |
0.000012806220001948532 s |
0.000011204479988009552 s |
1.14 |
add_one / JaXPipe / cpu / PostRev |
0.000012454760035325308 s |
0.000011416899978939907 s |
1.09 |
add_one / JaXPipe / cpu / BothRev |
0.000013123519993314403 s |
0.00001207060000524507 s |
1.09 |
add_one / Jax / cpu / BothRev |
0.000013286879984661936 s |
0.00001128492000134429 s |
1.18 |
add_one / HLOOpt / cpu / PreRev |
0.000012875300026280456 s |
0.000011100679985247551 s |
1.16 |
add_one / HLOOpt / cpu / PostRev |
0.0000146485399636731 s |
0.00001353964001282293 s |
1.08 |
add_one / HLOOpt / cpu / BothRev |
0.000013005619948671665 s |
0.000011486960011097837 s |
1.13 |
add_one / PartOpt / cpu / PreRev |
0.000012344940014372696 s |
0.00001130043999182817 s |
1.09 |
add_one / PartOpt / cpu / PostRev |
0.000012744119985654831 s |
0.000011905940000360716 s |
1.07 |
add_one / PartOpt / cpu / BothRev |
0.000013116319996697711 s |
0.00001155997996647784 s |
1.13 |
add_one / IPartOpt / cpu / PreRev |
0.00001292728002226795 s |
0.00001138500001616194 s |
1.14 |
add_one / IPartOpt / cpu / PostRev |
0.00001266238001335296 s |
0.00001133304001086799 s |
1.12 |
add_one / IPartOpt / cpu / BothRev |
0.000012672480015680777 s |
0.000011015079962817254 s |
1.15 |
add_one / DefOpt / cpu / PreRev |
0.000012927600009788877 s |
0.000011270639961367123 s |
1.15 |
add_one / DefOpt / cpu / PostRev |
0.000012950840009580132 s |
0.000011101200007033184 s |
1.17 |
add_one / DefOpt / cpu / BothRev |
0.000013042600021435649 s |
0.000011353939953551162 s |
1.15 |
add_one / IDefOpt / cpu / PreRev |
0.000013026640017415048 s |
0.00001115835999371484 s |
1.17 |
add_one / IDefOpt / cpu / PostRev |
0.000012973559969395864 s |
0.00001128357997913554 s |
1.15 |
add_one / IDefOpt / cpu / BothRev |
0.000012988320022486731 s |
0.000011233480008741026 s |
1.16 |
add_one / JaXPipe / cuda / Primal |
0.0000019200000000000003 s |
0.000002303 s |
0.83 |
add_one / Jax / cuda / Primal |
0.0000019200000000000003 s |
0.000002303 s |
0.83 |
add_one / HLOOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000002303 s |
0.83 |
add_one / PartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000002303 s |
0.83 |
add_one / IPartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000002303 s |
0.83 |
add_one / DefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000002304 s |
0.83 |
add_one / IDefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000002303 s |
0.83 |
add_one / JaXPipe / cuda / Forward |
0.00001024 s |
0.000010463 s |
0.98 |
add_one / Jax / cuda / Forward |
0.000010207 s |
0.000010624 s |
0.96 |
add_one / HLOOpt / cuda / Forward |
0.000010272 s |
0.000010624 s |
0.97 |
add_one / PartOpt / cuda / Forward |
0.000010432 s |
0.00001088 s |
0.96 |
add_one / IPartOpt / cuda / Forward |
0.00001008 s |
0.000010624 s |
0.95 |
add_one / DefOpt / cuda / Forward |
0.00001024 s |
0.000010816 s |
0.95 |
add_one / IDefOpt / cuda / Forward |
0.000012672 s |
0.000010816 s |
1.17 |
add_one / JaXPipe / cuda / PreRev |
0.000025664 s |
0.000026208 s |
0.98 |
add_one / JaXPipe / cuda / PostRev |
0.000025088 s |
0.000026464000000000003 s |
0.95 |
add_one / JaXPipe / cuda / BothRev |
0.000025376 s |
0.000025535 s |
0.99 |
add_one / Jax / cuda / BothRev |
0.000025504 s |
0.000025664 s |
0.99 |
add_one / HLOOpt / cuda / PreRev |
0.000025376 s |
0.000026432 s |
0.96 |
add_one / HLOOpt / cuda / PostRev |
0.000025055 s |
0.000025792 s |
0.97 |
add_one / HLOOpt / cuda / BothRev |
0.00002544 s |
0.000025727 s |
0.99 |
add_one / PartOpt / cuda / PreRev |
0.00002544 s |
0.000026144 s |
0.97 |
add_one / PartOpt / cuda / PostRev |
0.000030943 s |
0.000032415 s |
0.95 |
add_one / PartOpt / cuda / BothRev |
0.000025248 s |
0.000026016 s |
0.97 |
add_one / IPartOpt / cuda / PreRev |
0.000026368 s |
0.000026528 s |
0.99 |
add_one / IPartOpt / cuda / PostRev |
0.00003104 s |
0.0000264 s |
1.18 |
add_one / IPartOpt / cuda / BothRev |
0.000025216 s |
0.000026144 s |
0.96 |
add_one / DefOpt / cuda / PreRev |
0.000025056 s |
0.000025984 s |
0.96 |
add_one / DefOpt / cuda / PostRev |
0.00002512 s |
0.000027487 s |
0.91 |
add_one / DefOpt / cuda / BothRev |
0.000025985000000000003 s |
0.000026079 s |
1.00 |
add_one / IDefOpt / cuda / PreRev |
0.000025152 s |
0.000026592 s |
0.95 |
add_one / IDefOpt / cuda / PostRev |
0.000024736 s |
0.000026432 s |
0.94 |
add_one / IDefOpt / cuda / BothRev |
0.000025792 s |
0.00002656 s |
0.97 |
add_one / JaXPipe / cpu / Primal |
0.000016511 s |
0.000006907579991093371 s |
2.39 |
add_one / Jax / cpu / Primal |
0.000016269 s |
0.00000676276001286169 s |
2.41 |
add_one / HLOOpt / cpu / Primal |
0.000015999 s |
0.000006887820009069401 s |
2.32 |
add_one / PartOpt / cpu / Primal |
0.000016225 s |
0.000006576520008820807 s |
2.47 |
add_one / IPartOpt / cpu / Primal |
0.000016051 s |
0.000006939099985174835 s |
2.31 |
add_one / DefOpt / cpu / Primal |
0.000016288 s |
0.000006486319989562617 s |
2.51 |
add_one / IDefOpt / cpu / Primal |
0.000015959 s |
0.000006594699962079176 s |
2.42 |
add_one / JaXPipe / cpu / Forward |
0.000022217 s |
0.00000948447996051982 s |
2.34 |
add_one / Jax / cpu / Forward |
0.000021734 s |
0.000009536679981465567 s |
2.28 |
add_one / HLOOpt / cpu / Forward |
0.000021803 s |
0.00000980943999820738 s |
2.22 |
add_one / PartOpt / cpu / Forward |
0.000022141 s |
0.000009570080001140014 s |
2.31 |
add_one / IPartOpt / cpu / Forward |
0.000022106 s |
0.00000947989996348042 s |
2.33 |
add_one / DefOpt / cpu / Forward |
0.000021953 s |
0.000010185959999944315 s |
2.16 |
add_one / IDefOpt / cpu / Forward |
0.00002213 s |
0.000009939120009221367 s |
2.23 |
add_one / JaXPipe / cpu / PreRev |
0.000024552 s |
0.000011204479988009552 s |
2.19 |
add_one / JaXPipe / cpu / PostRev |
0.00002425 s |
0.000011416899978939907 s |
2.12 |
add_one / JaXPipe / cpu / BothRev |
0.000024483000000000003 s |
0.00001207060000524507 s |
2.03 |
add_one / Jax / cpu / BothRev |
0.000024106 s |
0.00001128492000134429 s |
2.14 |
add_one / HLOOpt / cpu / PreRev |
0.00002401 s |
0.000011100679985247551 s |
2.16 |
add_one / HLOOpt / cpu / PostRev |
0.000024192 s |
0.00001353964001282293 s |
1.79 |
add_one / HLOOpt / cpu / BothRev |
0.000023792 s |
0.000011486960011097837 s |
2.07 |
add_one / PartOpt / cpu / PreRev |
0.000032933 s |
0.00001130043999182817 s |
2.91 |
add_one / PartOpt / cpu / PostRev |
0.000024178 s |
0.000011905940000360716 s |
2.03 |
add_one / PartOpt / cpu / BothRev |
0.000024073 s |
0.00001155997996647784 s |
2.08 |
add_one / IPartOpt / cpu / PreRev |
0.000024322 s |
0.00001138500001616194 s |
2.14 |
add_one / IPartOpt / cpu / PostRev |
0.000024038 s |
0.00001133304001086799 s |
2.12 |
add_one / IPartOpt / cpu / BothRev |
0.000023793 s |
0.000011015079962817254 s |
2.16 |
add_one / DefOpt / cpu / PreRev |
0.000023972 s |
0.000011270639961367123 s |
2.13 |
add_one / DefOpt / cpu / PostRev |
0.000024265 s |
0.000011101200007033184 s |
2.19 |
add_one / DefOpt / cpu / BothRev |
0.000023962 s |
0.000011353939953551162 s |
2.11 |
add_one / IDefOpt / cpu / PreRev |
0.000024334 s |
0.00001115835999371484 s |
2.18 |
add_one / IDefOpt / cpu / PostRev |
0.000024203 s |
0.00001128357997913554 s |
2.14 |
add_one / IDefOpt / cpu / BothRev |
0.000024144 s |
0.000011233480008741026 s |
2.15 |
add_one / JaXPipe / cpu / Primal |
0.000008 s |
0.000006907579991093371 s |
1.16 |
add_one / Jax / cpu / Primal |
0.000008 s |
0.00000676276001286169 s |
1.18 |
add_one / HLOOpt / cpu / Primal |
0.000008 s |
0.000006887820009069401 s |
1.16 |
add_one / PartOpt / cpu / Primal |
0.000008 s |
0.000006576520008820807 s |
1.22 |
add_one / IPartOpt / cpu / Primal |
0.000008 s |
0.000006939099985174835 s |
1.15 |
add_one / DefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000006486319989562617 s |
1.39 |
add_one / IDefOpt / cpu / Primal |
0.000008 s |
0.000006594699962079176 s |
1.21 |
add_one / JaXPipe / cpu / Forward |
0.000011 s |
0.00000948447996051982 s |
1.16 |
add_one / Jax / cpu / Forward |
0.000012 s |
0.000009536679981465567 s |
1.26 |
add_one / HLOOpt / cpu / Forward |
0.000011 s |
0.00000980943999820738 s |
1.12 |
add_one / PartOpt / cpu / Forward |
0.000011 s |
0.000009570080001140014 s |
1.15 |
add_one / IPartOpt / cpu / Forward |
0.000012 s |
0.00000947989996348042 s |
1.27 |
add_one / DefOpt / cpu / Forward |
0.000011 s |
0.000010185959999944315 s |
1.08 |
add_one / IDefOpt / cpu / Forward |
0.000011 s |
0.000009939120009221367 s |
1.11 |
add_one / JaXPipe / cpu / PreRev |
0.000012 s |
0.000011204479988009552 s |
1.07 |
add_one / JaXPipe / cpu / PostRev |
0.000013 s |
0.000011416899978939907 s |
1.14 |
add_one / JaXPipe / cpu / BothRev |
0.000014 s |
0.00001207060000524507 s |
1.16 |
add_one / Jax / cpu / BothRev |
0.000013 s |
0.00001128492000134429 s |
1.15 |
add_one / HLOOpt / cpu / PreRev |
0.000014 s |
0.000011100679985247551 s |
1.26 |
add_one / HLOOpt / cpu / PostRev |
0.000012 s |
0.00001353964001282293 s |
0.89 |
add_one / HLOOpt / cpu / BothRev |
0.000014 s |
0.000011486960011097837 s |
1.22 |
add_one / PartOpt / cpu / PreRev |
0.000012 s |
0.00001130043999182817 s |
1.06 |
add_one / PartOpt / cpu / PostRev |
0.000013 s |
0.000011905940000360716 s |
1.09 |
add_one / PartOpt / cpu / BothRev |
0.000013 s |
0.00001155997996647784 s |
1.12 |
add_one / IPartOpt / cpu / PreRev |
0.000013 s |
0.00001138500001616194 s |
1.14 |
add_one / IPartOpt / cpu / PostRev |
0.000013 s |
0.00001133304001086799 s |
1.15 |
add_one / IPartOpt / cpu / BothRev |
0.000013 s |
0.000011015079962817254 s |
1.18 |
add_one / DefOpt / cpu / PreRev |
0.000014 s |
0.000011270639961367123 s |
1.24 |
add_one / DefOpt / cpu / PostRev |
0.000012 s |
0.000011101200007033184 s |
1.08 |
add_one / DefOpt / cpu / BothRev |
0.000013 s |
0.000011353939953551162 s |
1.14 |
add_one / IDefOpt / cpu / PreRev |
0.000013 s |
0.00001115835999371484 s |
1.17 |
add_one / IDefOpt / cpu / PostRev |
0.000014 s |
0.00001128357997913554 s |
1.24 |
add_one / IDefOpt / cpu / BothRev |
0.000013 s |
0.000011233480008741026 s |
1.16 |
add_two / JaXPipe / cpu / Primal |
0.000007858720009608077 s |
0.000007173779968070449 s |
1.10 |
add_two / Jax / cpu / Primal |
0.000007874859966250369 s |
0.000006748499972673017 s |
1.17 |
add_two / HLOOpt / cpu / Primal |
0.000007677599987800932 s |
0.0000069464000353036684 s |
1.11 |
add_two / PartOpt / cpu / Primal |
0.000007567640004708664 s |
0.000006672779982181964 s |
1.13 |
add_two / IPartOpt / cpu / Primal |
0.000008091639974736609 s |
0.000006682439998257906 s |
1.21 |
add_two / DefOpt / cpu / Primal |
0.000007916300000943011 s |
0.000006676440007140627 s |
1.19 |
add_two / IDefOpt / cpu / Primal |
0.000007622739976795856 s |
0.000006850760009911028 s |
1.11 |
add_two / JaXPipe / cpu / Forward |
0.000011561519995666458 s |
0.000010133979994861876 s |
1.14 |
add_two / Jax / cpu / Forward |
0.00001129776000198035 s |
0.000010257700005240622 s |
1.10 |
add_two / HLOOpt / cpu / Forward |
0.00001152874004219484 s |
0.00001020202002109727 s |
1.13 |
add_two / PartOpt / cpu / Forward |
0.000011271360008322518 s |
0.000009991320002882275 s |
1.13 |
add_two / IPartOpt / cpu / Forward |
0.000011623979971773224 s |
0.000009990719972847727 s |
1.16 |
add_two / DefOpt / cpu / Forward |
0.000011454999994384706 s |
0.000010176940022574856 s |
1.13 |
add_two / IDefOpt / cpu / Forward |
0.000011690659939631586 s |
0.000009701360004328308 s |
1.21 |
add_two / JaXPipe / cpu / PreRev |
0.00001563976004945289 s |
0.000014047679997020168 s |
1.11 |
add_two / JaXPipe / cpu / PostRev |
0.000014908400016793166 s |
0.000014034899968464743 s |
1.06 |
add_two / JaXPipe / cpu / BothRev |
0.000015213700016829536 s |
0.000013643299989780644 s |
1.12 |
add_two / Jax / cpu / BothRev |
0.000015059060006024083 s |
0.000013720739998461797 s |
1.10 |
add_two / HLOOpt / cpu / PreRev |
0.000015181039989329293 s |
0.000013685779958905186 s |
1.11 |
add_two / HLOOpt / cpu / PostRev |
0.000017317559950242868 s |
0.000015608399999109678 s |
1.11 |
add_two / HLOOpt / cpu / BothRev |
0.00001556219996018626 s |
0.000014502559979518992 s |
1.07 |
add_two / PartOpt / cpu / PreRev |
0.000015517539977736306 s |
0.000013529180014302256 s |
1.15 |
add_two / PartOpt / cpu / PostRev |
0.000014764539992029312 s |
0.00001394477997564536 s |
1.06 |
add_two / PartOpt / cpu / BothRev |
0.000015683260025980418 s |
0.000013888859994040104 s |
1.13 |
add_two / IPartOpt / cpu / PreRev |
0.000015033500003482914 s |
0.000013996460029375158 s |
1.07 |
add_two / IPartOpt / cpu / PostRev |
0.000015193899989753846 s |
0.000013922960006311769 s |
1.09 |
add_two / IPartOpt / cpu / BothRev |
0.000015201559981505851 s |
0.000013716940011363476 s |
1.11 |
add_two / DefOpt / cpu / PreRev |
0.00001556588001221826 s |
0.000014143979969958309 s |
1.10 |
add_two / DefOpt / cpu / PostRev |
0.000014922660002412158 s |
0.000013327520018719952 s |
1.12 |
add_two / DefOpt / cpu / BothRev |
0.00001578532002895372 s |
0.000013483859975167434 s |
1.17 |
add_two / IDefOpt / cpu / PreRev |
0.000014900280020810895 s |
0.00001424845998371893 s |
1.05 |
add_two / IDefOpt / cpu / PostRev |
0.000015253360015776706 s |
0.000014205700035745394 s |
1.07 |
add_two / IDefOpt / cpu / BothRev |
0.000014632160018663852 s |
0.00001421470003151626 s |
1.03 |
add_two / JaXPipe / cuda / Primal |
0.0000019200000000000003 s |
0.0000024 s |
0.80 |
add_two / Jax / cuda / Primal |
0.0000019200000000000003 s |
0.0000024 s |
0.80 |
add_two / HLOOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000024 s |
0.80 |
add_two / PartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000002399 s |
0.80 |
add_two / IPartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000024 s |
0.80 |
add_two / DefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000024 s |
0.80 |
add_two / IDefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000002399 s |
0.80 |
add_two / JaXPipe / cuda / Forward |
0.00001024 s |
0.000010305 s |
0.99 |
add_two / Jax / cuda / Forward |
0.000009632 s |
0.00001024 s |
0.94 |
add_two / HLOOpt / cuda / Forward |
0.000010016 s |
0.000010271 s |
0.98 |
add_two / PartOpt / cuda / Forward |
0.000010689 s |
0.000010496 s |
1.02 |
add_two / IPartOpt / cuda / Forward |
0.000010271 s |
0.0000104 s |
0.99 |
add_two / DefOpt / cuda / Forward |
0.000009984 s |
0.000010176 s |
0.98 |
add_two / IDefOpt / cuda / Forward |
0.000010112 s |
0.000010751 s |
0.94 |
add_two / JaXPipe / cuda / PreRev |
0.000032704 s |
0.000032864 s |
1.00 |
add_two / JaXPipe / cuda / PostRev |
0.000033407 s |
0.000037983000000000005 s |
0.88 |
add_two / JaXPipe / cuda / BothRev |
0.000032544 s |
0.000037696 s |
0.86 |
add_two / Jax / cuda / BothRev |
0.000032992 s |
0.00003808 s |
0.87 |
add_two / HLOOpt / cuda / PreRev |
0.00003264 s |
0.000038368 s |
0.85 |
add_two / HLOOpt / cuda / PostRev |
0.000032929 s |
0.000037951 s |
0.87 |
add_two / HLOOpt / cuda / BothRev |
0.000032606999999999995 s |
0.000033983 s |
0.96 |
add_two / PartOpt / cuda / PreRev |
0.00003232 s |
0.000033855 s |
0.95 |
add_two / PartOpt / cuda / PostRev |
0.00003296 s |
0.000033056 s |
1.00 |
add_two / PartOpt / cuda / BothRev |
0.000033248 s |
0.000033312 s |
1.00 |
add_two / IPartOpt / cuda / PreRev |
0.000033344 s |
0.000033408 s |
1.00 |
add_two / IPartOpt / cuda / PostRev |
0.000033696 s |
0.000033312 s |
1.01 |
add_two / IPartOpt / cuda / BothRev |
0.000033119999999999995 s |
0.000034272 s |
0.97 |
add_two / DefOpt / cuda / PreRev |
0.000032864 s |
0.000033824 s |
0.97 |
add_two / DefOpt / cuda / PostRev |
0.000032767999999999995 s |
0.000032991 s |
0.99 |
add_two / DefOpt / cuda / BothRev |
0.000033184 s |
0.000033312 s |
1.00 |
add_two / IDefOpt / cuda / PreRev |
0.000032928 s |
0.000033024 s |
1.00 |
add_two / IDefOpt / cuda / PostRev |
0.000033312 s |
0.000033119999999999995 s |
1.01 |
add_two / IDefOpt / cuda / BothRev |
0.0000336 s |
0.000033408 s |
1.01 |
add_two / JaXPipe / cpu / Primal |
0.000017054 s |
0.000007173779968070449 s |
2.38 |
add_two / Jax / cpu / Primal |
0.000016512 s |
0.000006748499972673017 s |
2.45 |
add_two / HLOOpt / cpu / Primal |
0.000016846 s |
0.0000069464000353036684 s |
2.43 |
add_two / PartOpt / cpu / Primal |
0.000016466 s |
0.000006672779982181964 s |
2.47 |
add_two / IPartOpt / cpu / Primal |
0.000016734 s |
0.000006682439998257906 s |
2.50 |
add_two / DefOpt / cpu / Primal |
0.000016734 s |
0.000006676440007140627 s |
2.51 |
add_two / IDefOpt / cpu / Primal |
0.000016785999999999998 s |
0.000006850760009911028 s |
2.45 |
add_two / JaXPipe / cpu / Forward |
0.00002249 s |
0.000010133979994861876 s |
2.22 |
add_two / Jax / cpu / Forward |
0.00002245 s |
0.000010257700005240622 s |
2.19 |
add_two / HLOOpt / cpu / Forward |
0.000022411 s |
0.00001020202002109727 s |
2.20 |
add_two / PartOpt / cpu / Forward |
0.000022429 s |
0.000009991320002882275 s |
2.24 |
add_two / IPartOpt / cpu / Forward |
0.000021844 s |
0.000009990719972847727 s |
2.19 |
add_two / DefOpt / cpu / Forward |
0.000021978 s |
0.000010176940022574856 s |
2.16 |
add_two / IDefOpt / cpu / Forward |
0.000022553 s |
0.000009701360004328308 s |
2.32 |
add_two / JaXPipe / cpu / PreRev |
0.000028973 s |
0.000014047679997020168 s |
2.06 |
add_two / JaXPipe / cpu / PostRev |
0.000028179 s |
0.000014034899968464743 s |
2.01 |
add_two / JaXPipe / cpu / BothRev |
0.000028074000000000003 s |
0.000013643299989780644 s |
2.06 |
add_two / Jax / cpu / BothRev |
0.000028221 s |
0.000013720739998461797 s |
2.06 |
add_two / HLOOpt / cpu / PreRev |
0.000028233 s |
0.000013685779958905186 s |
2.06 |
add_two / HLOOpt / cpu / PostRev |
0.00002831 s |
0.000015608399999109678 s |
1.81 |
add_two / HLOOpt / cpu / BothRev |
0.000028164 s |
0.000014502559979518992 s |
1.94 |
add_two / PartOpt / cpu / PreRev |
0.000028427 s |
0.000013529180014302256 s |
2.10 |
add_two / PartOpt / cpu / PostRev |
0.000028433 s |
0.00001394477997564536 s |
2.04 |
add_two / PartOpt / cpu / BothRev |
0.000028813 s |
0.000013888859994040104 s |
2.07 |
add_two / IPartOpt / cpu / PreRev |
0.000028528 s |
0.000013996460029375158 s |
2.04 |
add_two / IPartOpt / cpu / PostRev |
0.00002768 s |
0.000013922960006311769 s |
1.99 |
add_two / IPartOpt / cpu / BothRev |
0.000028618 s |
0.000013716940011363476 s |
2.09 |
add_two / DefOpt / cpu / PreRev |
0.000028236 s |
0.000014143979969958309 s |
2.00 |
add_two / DefOpt / cpu / PostRev |
0.000028236 s |
0.000013327520018719952 s |
2.12 |
add_two / DefOpt / cpu / BothRev |
0.000028564 s |
0.000013483859975167434 s |
2.12 |
add_two / IDefOpt / cpu / PreRev |
0.00002838 s |
0.00001424845998371893 s |
1.99 |
add_two / IDefOpt / cpu / PostRev |
0.000028162 s |
0.000014205700035745394 s |
1.98 |
add_two / IDefOpt / cpu / BothRev |
0.00002833 s |
0.00001421470003151626 s |
1.99 |
add_two / JaXPipe / cpu / Primal |
0.000008999999999999999 s |
0.000007173779968070449 s |
1.25 |
add_two / Jax / cpu / Primal |
0.000008 s |
0.000006748499972673017 s |
1.19 |
add_two / HLOOpt / cpu / Primal |
0.000008 s |
0.0000069464000353036684 s |
1.15 |
add_two / PartOpt / cpu / Primal |
0.000008999999999999999 s |
0.000006672779982181964 s |
1.35 |
add_two / IPartOpt / cpu / Primal |
0.000008 s |
0.000006682439998257906 s |
1.20 |
add_two / DefOpt / cpu / Primal |
0.000008 s |
0.000006676440007140627 s |
1.20 |
add_two / IDefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000006850760009911028 s |
1.31 |
add_two / JaXPipe / cpu / Forward |
0.000011 s |
0.000010133979994861876 s |
1.09 |
add_two / Jax / cpu / Forward |
0.000011 s |
0.000010257700005240622 s |
1.07 |
add_two / HLOOpt / cpu / Forward |
0.000012 s |
0.00001020202002109727 s |
1.18 |
add_two / PartOpt / cpu / Forward |
0.000012 s |
0.000009991320002882275 s |
1.20 |
add_two / IPartOpt / cpu / Forward |
0.000012 s |
0.000009990719972847727 s |
1.20 |
add_two / DefOpt / cpu / Forward |
0.000012 s |
0.000010176940022574856 s |
1.18 |
add_two / IDefOpt / cpu / Forward |
0.000012 s |
0.000009701360004328308 s |
1.24 |
add_two / JaXPipe / cpu / PreRev |
0.000016 s |
0.000014047679997020168 s |
1.14 |
add_two / JaXPipe / cpu / PostRev |
0.000016 s |
0.000014034899968464743 s |
1.14 |
add_two / JaXPipe / cpu / BothRev |
0.000016 s |
0.000013643299989780644 s |
1.17 |
add_two / Jax / cpu / BothRev |
0.000015 s |
0.000013720739998461797 s |
1.09 |
add_two / HLOOpt / cpu / PreRev |
0.000016 s |
0.000013685779958905186 s |
1.17 |
add_two / HLOOpt / cpu / PostRev |
0.000016 s |
0.000015608399999109678 s |
1.03 |
add_two / HLOOpt / cpu / BothRev |
0.000016 s |
0.000014502559979518992 s |
1.10 |
add_two / PartOpt / cpu / PreRev |
0.000016 s |
0.000013529180014302256 s |
1.18 |
add_two / PartOpt / cpu / PostRev |
0.000016 s |
0.00001394477997564536 s |
1.15 |
add_two / PartOpt / cpu / BothRev |
0.000017 s |
0.000013888859994040104 s |
1.22 |
add_two / IPartOpt / cpu / PreRev |
0.000016 s |
0.000013996460029375158 s |
1.14 |
add_two / IPartOpt / cpu / PostRev |
0.000016 s |
0.000013922960006311769 s |
1.15 |
add_two / IPartOpt / cpu / BothRev |
0.000016 s |
0.000013716940011363476 s |
1.17 |
add_two / DefOpt / cpu / PreRev |
0.000016 s |
0.000014143979969958309 s |
1.13 |
add_two / DefOpt / cpu / PostRev |
0.000016 s |
0.000013327520018719952 s |
1.20 |
add_two / DefOpt / cpu / BothRev |
0.000016 s |
0.000013483859975167434 s |
1.19 |
add_two / IDefOpt / cpu / PreRev |
0.000016 s |
0.00001424845998371893 s |
1.12 |
add_two / IDefOpt / cpu / PostRev |
0.000016 s |
0.000014205700035745394 s |
1.13 |
add_two / IDefOpt / cpu / BothRev |
0.000015 s |
0.00001421470003151626 s |
1.06 |
cache / JaXPipe / cpu / Primal |
0.000006903140028953203 s |
0.000006223720010893885 s |
1.11 |
cache / Jax / cpu / Primal |
0.000006924700046511134 s |
0.00000673749997986306 s |
1.03 |
cache / HLOOpt / cpu / Primal |
0.000006636819998675492 s |
0.000006718279983033426 s |
0.99 |
cache / PartOpt / cpu / Primal |
0.000007032000012259232 s |
0.000006046339995009475 s |
1.16 |
cache / IPartOpt / cpu / Primal |
0.000006629720028286101 s |
0.000006025160018907627 s |
1.10 |
cache / DefOpt / cpu / Primal |
0.000006811260018366738 s |
0.00000653982000585529 s |
1.04 |
cache / IDefOpt / cpu / Primal |
0.000007073939968904597 s |
0.000006367899986798875 s |
1.11 |
cache / JaXPipe / cpu / Forward |
0.000015911700056676637 s |
0.00001533326003482216 s |
1.04 |
cache / Jax / cpu / Forward |
0.00001561342002787569 s |
0.00001484798000092269 s |
1.05 |
cache / HLOOpt / cpu / Forward |
0.000016250280004896922 s |
0.000015632519980499636 s |
1.04 |
cache / PartOpt / cpu / Forward |
0.000015229840000756669 s |
0.000014201479962139274 s |
1.07 |
cache / IPartOpt / cpu / Forward |
0.000015891540024313144 s |
0.000014842179962215595 s |
1.07 |
cache / DefOpt / cpu / Forward |
0.000015931939997244627 s |
0.000014357419986481546 s |
1.11 |
cache / IDefOpt / cpu / Forward |
0.000016191360055017866 s |
0.00001422434003870876 s |
1.14 |
cache / JaXPipe / cpu / PreRev |
0.000018368959999861544 s |
0.00001581281996550388 s |
1.16 |
cache / JaXPipe / cpu / PostRev |
0.00002176102003431879 s |
0.00002159693999601586 s |
1.01 |
cache / JaXPipe / cpu / BothRev |
0.00001730410000163829 s |
0.00001498288003858761 s |
1.15 |
cache / Jax / cpu / BothRev |
0.000022358480000548296 s |
0.00002013373999034229 s |
1.11 |
cache / HLOOpt / cpu / PreRev |
0.000017650239997237804 s |
0.00001587113995810796 s |
1.11 |
cache / HLOOpt / cpu / PostRev |
0.00002310014000613592 s |
0.000017650000017965795 s |
1.31 |
cache / HLOOpt / cpu / BothRev |
0.000017511539945189724 s |
0.000015484780042243075 s |
1.13 |
cache / PartOpt / cpu / PreRev |
0.00001649936000831076 s |
0.000015225280012600706 s |
1.08 |
cache / PartOpt / cpu / PostRev |
0.000020373400020616823 s |
0.00002088918004119478 s |
0.98 |
cache / PartOpt / cpu / BothRev |
0.000017299920018558622 s |
0.000016181779974431264 s |
1.07 |
cache / IPartOpt / cpu / PreRev |
0.000016916660006245364 s |
0.000015798420054125018 s |
1.07 |
cache / IPartOpt / cpu / PostRev |
0.000021537619932132657 s |
0.000020258740023564317 s |
1.06 |
cache / IPartOpt / cpu / BothRev |
0.000015971459961292568 s |
0.000015281639998647735 s |
1.05 |
cache / DefOpt / cpu / PreRev |
0.00001620027996978024 s |
0.000016079200004242012 s |
1.01 |
cache / DefOpt / cpu / PostRev |
0.000016124719986692072 s |
0.000015468399951714673 s |
1.04 |
cache / DefOpt / cpu / BothRev |
0.00001661909996983013 s |
0.00001569140002175118 s |
1.06 |
cache / IDefOpt / cpu / PreRev |
0.00001693617999990238 s |
0.000016558580036871716 s |
1.02 |
cache / IDefOpt / cpu / PostRev |
0.000017308999977103666 s |
0.00001607710006283014 s |
1.08 |
cache / IDefOpt / cpu / BothRev |
0.000017206320035256794 s |
0.000015474859983442 s |
1.11 |
cache / JaXPipe / cuda / Primal |
0.000002304 s |
0.000002335 s |
0.99 |
cache / Jax / cuda / Primal |
0.000002335 s |
0.000002336 s |
1.00 |
cache / HLOOpt / cuda / Primal |
0.00000224 s |
0.000002304 s |
0.97 |
cache / PartOpt / cuda / Primal |
0.000002272 s |
0.000002335 s |
0.97 |
cache / IPartOpt / cuda / Primal |
0.000002304 s |
0.000002304 s |
1 |
cache / DefOpt / cuda / Primal |
0.00000224 s |
0.000002336 s |
0.96 |
cache / IDefOpt / cuda / Primal |
0.00000224 s |
0.000002304 s |
0.97 |
cache / JaXPipe / cuda / Forward |
0.000002335 s |
0.000002335 s |
1 |
cache / Jax / cuda / Forward |
0.000002335 s |
0.000002335 s |
1 |
cache / HLOOpt / cuda / Forward |
0.000002335 s |
0.000002336 s |
1.00 |
cache / PartOpt / cuda / Forward |
0.000002336 s |
0.000002336 s |
1 |
cache / IPartOpt / cuda / Forward |
0.000002335 s |
0.000002335 s |
1 |
cache / DefOpt / cuda / Forward |
0.000002304 s |
0.000002336 s |
0.99 |
cache / IDefOpt / cuda / Forward |
0.000002335 s |
0.000002336 s |
1.00 |
cache / JaXPipe / cuda / PreRev |
0.000011168 s |
0.00001056 s |
1.06 |
cache / JaXPipe / cuda / PostRev |
0.000011455999999999998 s |
0.000010559 s |
1.08 |
cache / JaXPipe / cuda / BothRev |
0.000010944 s |
0.000010944 s |
1 |
cache / Jax / cuda / BothRev |
0.000011328 s |
0.000010688 s |
1.06 |
cache / HLOOpt / cuda / PreRev |
0.00001344 s |
0.000013504 s |
1.00 |
cache / HLOOpt / cuda / PostRev |
0.000013408 s |
0.000013472 s |
1.00 |
cache / HLOOpt / cuda / BothRev |
0.000013472 s |
0.000013504 s |
1.00 |
cache / PartOpt / cuda / PreRev |
0.000010816 s |
0.000010976 s |
0.99 |
cache / PartOpt / cuda / PostRev |
0.000011232 s |
0.00001056 s |
1.06 |
cache / PartOpt / cuda / BothRev |
0.000010624 s |
0.000011007 s |
0.97 |
cache / IPartOpt / cuda / PreRev |
0.000011168 s |
0.000010656 s |
1.05 |
cache / IPartOpt / cuda / PostRev |
0.000011104 s |
0.000010784 s |
1.03 |
cache / IPartOpt / cuda / BothRev |
0.000011008 s |
0.000010815 s |
1.02 |
cache / DefOpt / cuda / PreRev |
0.000011136 s |
0.000010816 s |
1.03 |
cache / DefOpt / cuda / PostRev |
0.000010944 s |
0.000010688 s |
1.02 |
cache / DefOpt / cuda / BothRev |
0.000010783 s |
0.000010783 s |
1 |
cache / IDefOpt / cuda / PreRev |
0.000010976 s |
0.000011328 s |
0.97 |
cache / IDefOpt / cuda / PostRev |
0.000010848 s |
0.00001072 s |
1.01 |
cache / IDefOpt / cuda / BothRev |
0.000010784 s |
0.000010816 s |
1.00 |
cache / JaXPipe / cpu / Primal |
0.000018692 s |
0.000006223720010893885 s |
3.00 |
cache / Jax / cpu / Primal |
0.000018643 s |
0.00000673749997986306 s |
2.77 |
cache / HLOOpt / cpu / Primal |
0.000019026 s |
0.000006718279983033426 s |
2.83 |
cache / PartOpt / cpu / Primal |
0.000018299 s |
0.000006046339995009475 s |
3.03 |
cache / IPartOpt / cpu / Primal |
0.000018413 s |
0.000006025160018907627 s |
3.06 |
cache / DefOpt / cpu / Primal |
0.000018587 s |
0.00000653982000585529 s |
2.84 |
cache / IDefOpt / cpu / Primal |
0.000018823 s |
0.000006367899986798875 s |
2.96 |
cache / JaXPipe / cpu / Forward |
0.000028954 s |
0.00001533326003482216 s |
1.89 |
cache / Jax / cpu / Forward |
0.000021615 s |
0.00001484798000092269 s |
1.46 |
cache / HLOOpt / cpu / Forward |
0.000021179 s |
0.000015632519980499636 s |
1.35 |
cache / PartOpt / cpu / Forward |
0.000021158 s |
0.000014201479962139274 s |
1.49 |
cache / IPartOpt / cpu / Forward |
0.000021635 s |
0.000014842179962215595 s |
1.46 |
cache / DefOpt / cpu / Forward |
0.000021247 s |
0.000014357419986481546 s |
1.48 |
cache / IDefOpt / cpu / Forward |
0.000021295 s |
0.00001422434003870876 s |
1.50 |
cache / JaXPipe / cpu / PreRev |
0.000022256 s |
0.00001581281996550388 s |
1.41 |
cache / JaXPipe / cpu / PostRev |
0.000025287 s |
0.00002159693999601586 s |
1.17 |
cache / JaXPipe / cpu / BothRev |
0.000032685 s |
0.00001498288003858761 s |
2.18 |
cache / Jax / cpu / BothRev |
0.000037423 s |
0.00002013373999034229 s |
1.86 |
cache / HLOOpt / cpu / PreRev |
0.000030098 s |
0.00001587113995810796 s |
1.90 |
cache / HLOOpt / cpu / PostRev |
0.000033737000000000006 s |
0.000017650000017965795 s |
1.91 |
cache / HLOOpt / cpu / BothRev |
0.000029051 s |
0.000015484780042243075 s |
1.88 |
cache / PartOpt / cpu / PreRev |
0.000030987 s |
0.000015225280012600706 s |
2.04 |
cache / PartOpt / cpu / PostRev |
0.000025799 s |
0.00002088918004119478 s |
1.24 |
cache / PartOpt / cpu / BothRev |
0.000021851 s |
0.000016181779974431264 s |
1.35 |
cache / IPartOpt / cpu / PreRev |
0.000022255 s |
0.000015798420054125018 s |
1.41 |
cache / IPartOpt / cpu / PostRev |
0.000025351 s |
0.000020258740023564317 s |
1.25 |
cache / IPartOpt / cpu / BothRev |
0.000032791 s |
0.000015281639998647735 s |
2.15 |
cache / DefOpt / cpu / PreRev |
0.000033043 s |
0.000016079200004242012 s |
2.06 |
cache / DefOpt / cpu / PostRev |
0.000032317 s |
0.000015468399951714673 s |
2.09 |
cache / DefOpt / cpu / BothRev |
0.000022356 s |
0.00001569140002175118 s |
1.42 |
cache / IDefOpt / cpu / PreRev |
0.000021675 s |
0.000016558580036871716 s |
1.31 |
cache / IDefOpt / cpu / PostRev |
0.000022077 s |
0.00001607710006283014 s |
1.37 |
cache / IDefOpt / cpu / BothRev |
0.000021592 s |
0.000015474859983442 s |
1.40 |
cache / JaXPipe / cpu / Primal |
0.000008 s |
0.000006223720010893885 s |
1.29 |
cache / Jax / cpu / Primal |
0.000008 s |
0.00000673749997986306 s |
1.19 |
cache / HLOOpt / cpu / Primal |
0.000008 s |
0.000006718279983033426 s |
1.19 |
cache / PartOpt / cpu / Primal |
0.000008 s |
0.000006046339995009475 s |
1.32 |
cache / IPartOpt / cpu / Primal |
0.000008999999999999999 s |
0.000006025160018907627 s |
1.49 |
cache / DefOpt / cpu / Primal |
0.000008999999999999999 s |
0.00000653982000585529 s |
1.38 |
cache / IDefOpt / cpu / Primal |
0.000008 s |
0.000006367899986798875 s |
1.26 |
cache / JaXPipe / cpu / Forward |
0.000034 s |
0.00001533326003482216 s |
2.22 |
cache / Jax / cpu / Forward |
0.00004 s |
0.00001484798000092269 s |
2.69 |
cache / HLOOpt / cpu / Forward |
0.00001 s |
0.000015632519980499636 s |
0.64 |
cache / PartOpt / cpu / Forward |
0.00001 s |
0.000014201479962139274 s |
0.70 |
cache / IPartOpt / cpu / Forward |
0.000011 s |
0.000014842179962215595 s |
0.74 |
cache / DefOpt / cpu / Forward |
0.00001 s |
0.000014357419986481546 s |
0.70 |
cache / IDefOpt / cpu / Forward |
0.00001 s |
0.00001422434003870876 s |
0.70 |
cache / JaXPipe / cpu / PreRev |
0.00001 s |
0.00001581281996550388 s |
0.63 |
cache / JaXPipe / cpu / PostRev |
0.000011 s |
0.00002159693999601586 s |
0.51 |
cache / JaXPipe / cpu / BothRev |
0.000038 s |
0.00001498288003858761 s |
2.54 |
cache / Jax / cpu / BothRev |
0.000011 s |
0.00002013373999034229 s |
0.55 |
cache / HLOOpt / cpu / PreRev |
0.00001 s |
0.00001587113995810796 s |
0.63 |
cache / HLOOpt / cpu / PostRev |
0.000011 s |
0.000017650000017965795 s |
0.62 |
cache / HLOOpt / cpu / BothRev |
0.000011 s |
0.000015484780042243075 s |
0.71 |
cache / PartOpt / cpu / PreRev |
0.00001 s |
0.000015225280012600706 s |
0.66 |
cache / PartOpt / cpu / PostRev |
0.000011 s |
0.00002088918004119478 s |
0.53 |
cache / PartOpt / cpu / BothRev |
0.000011 s |
0.000016181779974431264 s |
0.68 |
cache / IPartOpt / cpu / PreRev |
0.00001 s |
0.000015798420054125018 s |
0.63 |
cache / IPartOpt / cpu / PostRev |
0.000011 s |
0.000020258740023564317 s |
0.54 |
cache / IPartOpt / cpu / BothRev |
0.00001 s |
0.000015281639998647735 s |
0.65 |
cache / DefOpt / cpu / PreRev |
0.00001 s |
0.000016079200004242012 s |
0.62 |
cache / DefOpt / cpu / PostRev |
0.00001 s |
0.000015468399951714673 s |
0.65 |
cache / DefOpt / cpu / BothRev |
0.00001 s |
0.00001569140002175118 s |
0.64 |
cache / IDefOpt / cpu / PreRev |
0.00001 s |
0.000016558580036871716 s |
0.60 |
cache / IDefOpt / cpu / PostRev |
0.00001 s |
0.00001607710006283014 s |
0.62 |
cache / IDefOpt / cpu / BothRev |
0.00001 s |
0.000015474859983442 s |
0.65 |
Concat / JaXPipe / cpu / Primal |
0.000007521979987359373 s |
0.00000695150002684386 s |
1.08 |
Concat / Jax / cpu / Primal |
0.000007211159982034587 s |
0.000006699839996144874 s |
1.08 |
Concat / HLOOpt / cpu / Primal |
0.000007532179997724597 s |
0.00000690004001626221 s |
1.09 |
Concat / PartOpt / cpu / Primal |
0.000007391760018435889 s |
0.000006815699980506906 s |
1.08 |
Concat / IPartOpt / cpu / Primal |
0.000007498660006604041 s |
0.00000636850002592837 s |
1.18 |
Concat / DefOpt / cpu / Primal |
0.000007421879990943125 s |
0.00000703946003341116 s |
1.05 |
Concat / IDefOpt / cpu / Primal |
0.000007198839975899318 s |
0.000006285279978328617 s |
1.15 |
Concat / JaXPipe / cpu / Forward |
0.000010680240020519704 s |
0.000010241199997835791 s |
1.04 |
Concat / Jax / cpu / Forward |
0.000011074900003222863 s |
0.000009703319965410627 s |
1.14 |
Concat / HLOOpt / cpu / Forward |
0.000011201200004506971 s |
0.000009559300006003468 s |
1.17 |
Concat / PartOpt / cpu / Forward |
0.0000111081199702312 s |
0.00000958276003075298 s |
1.16 |
Concat / IPartOpt / cpu / Forward |
0.000011177280011906989 s |
0.000009982539986594929 s |
1.12 |
Concat / DefOpt / cpu / Forward |
0.000010866220018215244 s |
0.000010138779989574689 s |
1.07 |
Concat / IDefOpt / cpu / Forward |
0.000011281980005151126 s |
0.000010196479997830466 s |
1.11 |
Concat / JaXPipe / cpu / PreRev |
0.000012812380027753534 s |
0.00001103807999243145 s |
1.16 |
Concat / JaXPipe / cpu / PostRev |
0.000012519080037236563 s |
0.00001128766000874748 s |
1.11 |
Concat / JaXPipe / cpu / BothRev |
0.000012634600025194232 s |
0.00001132115998188965 s |
1.12 |
Concat / Jax / cpu / BothRev |
0.00001256969996575208 s |
0.000011009319978256826 s |
1.14 |
Concat / HLOOpt / cpu / PreRev |
0.000013062200023341575 s |
0.000011954099991271505 s |
1.09 |
Concat / HLOOpt / cpu / PostRev |
0.000014825219996055238 s |
0.000012993360014661448 s |
1.14 |
Concat / HLOOpt / cpu / BothRev |
0.00001248426002348424 s |
0.000011485780032671756 s |
1.09 |
Concat / PartOpt / cpu / PreRev |
0.000012883360031992195 s |
0.000011618539983828667 s |
1.11 |
Concat / PartOpt / cpu / PostRev |
0.000012723880008707055 s |
0.000011824160028481856 s |
1.08 |
Concat / PartOpt / cpu / BothRev |
0.000013071179964754264 s |
0.000011799639996752376 s |
1.11 |
Concat / IPartOpt / cpu / PreRev |
0.000012031859987473582 s |
0.000011507359986353549 s |
1.05 |
Concat / IPartOpt / cpu / PostRev |
0.000012376279983072893 s |
0.000011454079976829234 s |
1.08 |
Concat / IPartOpt / cpu / BothRev |
0.000012655500022447086 s |
0.000011326639987601085 s |
1.12 |
Concat / DefOpt / cpu / PreRev |
0.000012696920020971448 s |
0.00001092202000108955 s |
1.16 |
Concat / DefOpt / cpu / PostRev |
0.00001250893998076208 s |
0.0000106550000327843 s |
1.17 |
Concat / DefOpt / cpu / BothRev |
0.000012303120029173442 s |
0.000011423699970691812 s |
1.08 |
Concat / IDefOpt / cpu / PreRev |
0.000012277319920031004 s |
0.000010758380012703128 s |
1.14 |
Concat / IDefOpt / cpu / PostRev |
0.000012740639995172387 s |
0.000011344799977450748 s |
1.12 |
Concat / IDefOpt / cpu / BothRev |
0.000012994039989280282 s |
0.00001162687997748435 s |
1.12 |
Concat / JaXPipe / cuda / Primal |
0.0000019200000000000003 s |
0.0000024 s |
0.80 |
Concat / Jax / cuda / Primal |
0.0000019200000000000003 s |
0.0000024 s |
0.80 |
Concat / HLOOpt / cuda / Primal |
0.000001919 s |
0.0000024 s |
0.80 |
Concat / PartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000024 s |
0.80 |
Concat / IPartOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000024 s |
0.80 |
Concat / DefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.000002431 s |
0.79 |
Concat / IDefOpt / cuda / Primal |
0.0000019200000000000003 s |
0.0000024 s |
0.80 |
Concat / JaXPipe / cuda / Forward |
0.000010112 s |
0.000010656 s |
0.95 |
Concat / Jax / cuda / Forward |
0.000010144 s |
0.000010912 s |
0.93 |
Concat / HLOOpt / cuda / Forward |
0.000010112 s |
0.000011712 s |
0.86 |
Concat / PartOpt / cuda / Forward |
0.000010304 s |
0.000011904 s |
0.87 |
Concat / IPartOpt / cuda / Forward |
0.000012672 s |
0.000011616 s |
1.09 |
Concat / DefOpt / cuda / Forward |
0.000010048 s |
0.000011551 s |
0.87 |
Concat / IDefOpt / cuda / Forward |
0.00000992 s |
0.000012032 s |
0.82 |
Concat / JaXPipe / cuda / PreRev |
0.00001728 s |
0.000018752000000000003 s |
0.92 |
Concat / JaXPipe / cuda / PostRev |
0.000016512 s |
0.000018656 s |
0.89 |
Concat / JaXPipe / cuda / BothRev |
0.000017184 s |
0.000024736 s |
0.69 |
Concat / Jax / cuda / BothRev |
0.0000168 s |
0.000016865000000000002 s |
1.00 |
Concat / HLOOpt / cuda / PreRev |
0.000017375999999999998 s |
0.000017312 s |
1.00 |
Concat / HLOOpt / cuda / PostRev |
0.000016576000000000002 s |
0.000017216 s |
0.96 |
Concat / HLOOpt / cuda / BothRev |
0.000016768000000000003 s |
0.000016864 s |
0.99 |
Concat / PartOpt / cuda / PreRev |
0.000016864 s |
0.000018848 s |
0.89 |
Concat / PartOpt / cuda / PostRev |
0.000017152 s |
0.00001904 s |
0.90 |
Concat / PartOpt / cuda / BothRev |
0.000016863 s |
0.00001696 s |
0.99 |
Concat / IPartOpt / cuda / PreRev |
0.00001744 s |
0.000017056 s |
1.02 |
Concat / IPartOpt / cuda / PostRev |
0.000016576000000000002 s |
0.000016992 s |
0.98 |
Concat / IPartOpt / cuda / BothRev |
0.000016896000000000002 s |
0.000017375999999999998 s |
0.97 |
Concat / DefOpt / cuda / PreRev |
0.000017056 s |
0.000017536 s |
0.97 |
Concat / DefOpt / cuda / PostRev |
0.000016896000000000002 s |
0.000017119 s |
0.99 |
Concat / DefOpt / cuda / BothRev |
0.000017184 s |
0.00001568 s |
1.10 |
Concat / IDefOpt / cuda / PreRev |
0.000016576000000000002 s |
0.000017056 s |
0.97 |
Concat / IDefOpt / cuda / PostRev |
0.00001696 s |
0.000016927999999999998 s |
1.00 |
Concat / IDefOpt / cuda / BothRev |
0.00001696 s |
0.000018016 s |
0.94 |
Concat / JaXPipe / cpu / Primal |
0.000015853 s |
0.00000695150002684386 s |
2.28 |
Concat / Jax / cpu / Primal |
0.000015941 s |
0.000006699839996144874 s |
2.38 |
Concat / HLOOpt / cpu / Primal |
0.000016080000000000002 s |
0.00000690004001626221 s |
2.33 |
Concat / PartOpt / cpu / Primal |
0.000016261000000000002 s |
0.000006815699980506906 s |
2.39 |
Concat / IPartOpt / cpu / Primal |
0.000015963999999999998 s |
0.00000636850002592837 s |
2.51 |
Concat / DefOpt / cpu / Primal |
0.000016119000000000003 s |
0.00000703946003341116 s |
2.29 |
Concat / IDefOpt / cpu / Primal |
0.000016192 s |
0.000006285279978328617 s |
2.58 |
Concat / JaXPipe / cpu / Forward |
0.000022171 s |
0.000010241199997835791 s |
2.16 |
Concat / Jax / cpu / Forward |
0.000021393 s |
0.000009703319965410627 s |
2.20 |
Concat / HLOOpt / cpu / Forward |
0.000021663 s |
0.000009559300006003468 s |
2.27 |
Concat / PartOpt / cpu / Forward |
0.000021556 s |
0.00000958276003075298 s |
2.25 |
Concat / IPartOpt / cpu / Forward |
0.00002144 s |
0.000009982539986594929 s |
2.15 |
Concat / DefOpt / cpu / Forward |
0.000021762 s |
0.000010138779989574689 s |
2.15 |
Concat / IDefOpt / cpu / Forward |
0.000021725000000000003 s |
0.000010196479997830466 s |
2.13 |
Concat / JaXPipe / cpu / PreRev |
0.000024477 s |
0.00001103807999243145 s |
2.22 |
Concat / JaXPipe / cpu / PostRev |
0.000023971 s |
0.00001128766000874748 s |
2.12 |
Concat / JaXPipe / cpu / BothRev |
0.000029336 s |
0.00001132115998188965 s |
2.59 |
Concat / Jax / cpu / BothRev |
0.000024451 s |
0.000011009319978256826 s |
2.22 |
Concat / HLOOpt / cpu / PreRev |
0.000024533 s |
0.000011954099991271505 s |
2.05 |
Concat / HLOOpt / cpu / PostRev |
0.000023892 s |
0.000012993360014661448 s |
1.84 |
Concat / HLOOpt / cpu / BothRev |
0.000024073 s |
0.000011485780032671756 s |
2.10 |
Concat / PartOpt / cpu / PreRev |
0.000024852 s |
0.000011618539983828667 s |
2.14 |
Concat / PartOpt / cpu / PostRev |
0.000024452 s |
0.000011824160028481856 s |
2.07 |
Concat / PartOpt / cpu / BothRev |
0.000024149 s |
0.000011799639996752376 s |
2.05 |
Concat / IPartOpt / cpu / PreRev |
0.000024484 s |
0.000011507359986353549 s |
2.13 |
Concat / IPartOpt / cpu / PostRev |
0.000024787 s |
0.000011454079976829234 s |
2.16 |
Concat / IPartOpt / cpu / BothRev |
0.000024119 s |
0.000011326639987601085 s |
2.13 |
Concat / DefOpt / cpu / PreRev |
0.000024647 s |
0.00001092202000108955 s |
2.26 |
Concat / DefOpt / cpu / PostRev |
0.000024646 s |
0.0000106550000327843 s |
2.31 |
Concat / DefOpt / cpu / BothRev |
0.000024237 s |
0.000011423699970691812 s |
2.12 |
Concat / IDefOpt / cpu / PreRev |
0.000024472 s |
0.000010758380012703128 s |
2.27 |
Concat / IDefOpt / cpu / PostRev |
0.000024432 s |
0.000011344799977450748 s |
2.15 |
Concat / IDefOpt / cpu / BothRev |
0.000024042 s |
0.00001162687997748435 s |
2.07 |
Concat / JaXPipe / cpu / Primal |
0.000008 s |
0.00000695150002684386 s |
1.15 |
Concat / Jax / cpu / Primal |
0.000008 s |
0.000006699839996144874 s |
1.19 |
Concat / HLOOpt / cpu / Primal |
0.000008 s |
0.00000690004001626221 s |
1.16 |
Concat / PartOpt / cpu / Primal |
0.000008 s |
0.000006815699980506906 s |
1.17 |
Concat / IPartOpt / cpu / Primal |
0.000008 s |
0.00000636850002592837 s |
1.26 |
Concat / DefOpt / cpu / Primal |
0.000008 s |
0.00000703946003341116 s |
1.14 |
Concat / IDefOpt / cpu / Primal |
0.000008 s |
0.000006285279978328617 s |
1.27 |
Concat / JaXPipe / cpu / Forward |
0.000011 s |
0.000010241199997835791 s |
1.07 |
Concat / Jax / cpu / Forward |
0.000012 s |
0.000009703319965410627 s |
1.24 |
Concat / HLOOpt / cpu / Forward |
0.000012 s |
0.000009559300006003468 s |
1.26 |
Concat / PartOpt / cpu / Forward |
0.000012 s |
0.00000958276003075298 s |
1.25 |
Concat / IPartOpt / cpu / Forward |
0.000012 s |
0.000009982539986594929 s |
1.20 |
Concat / DefOpt / cpu / Forward |
0.000011 s |
0.000010138779989574689 s |
1.08 |
Concat / IDefOpt / cpu / Forward |
0.000012 s |
0.000010196479997830466 s |
1.18 |
Concat / JaXPipe / cpu / PreRev |
0.000013 s |
0.00001103807999243145 s |
1.18 |
Concat / JaXPipe / cpu / PostRev |
0.000014 s |
0.00001128766000874748 s |
1.24 |
Concat / JaXPipe / cpu / BothRev |
0.000014 s |
0.00001132115998188965 s |
1.24 |
Concat / Jax / cpu / BothRev |
0.000013 s |
0.000011009319978256826 s |
1.18 |
Concat / HLOOpt / cpu / PreRev |
0.000013 s |
0.000011954099991271505 s |
1.09 |
Concat / HLOOpt / cpu / PostRev |
0.000014 s |
0.000012993360014661448 s |
1.08 |
Concat / HLOOpt / cpu / BothRev |
0.000014 s |
0.000011485780032671756 s |
1.22 |
Concat / PartOpt / cpu / PreRev |
0.000013 s |
0.000011618539983828667 s |
1.12 |
Concat / PartOpt / cpu / PostRev |
0.000013 s |
0.000011824160028481856 s |
1.10 |
Concat / PartOpt / cpu / BothRev |
0.000013 s |
0.000011799639996752376 s |
1.10 |
Concat / IPartOpt / cpu / PreRev |
0.000014 s |
0.000011507359986353549 s |
1.22 |
Concat / IPartOpt / cpu / PostRev |
0.000014 s |
0.000011454079976829234 s |
1.22 |
Concat / IPartOpt / cpu / BothRev |
0.000014 s |
0.000011326639987601085 s |
1.24 |
Concat / DefOpt / cpu / PreRev |
0.000014 s |
0.00001092202000108955 s |
1.28 |
Concat / DefOpt / cpu / PostRev |
0.000014 s |
0.0000106550000327843 s |
1.31 |
Concat / DefOpt / cpu / BothRev |
0.000012 s |
0.000011423699970691812 s |
1.05 |
Concat / IDefOpt / cpu / PreRev |
0.000013 s |
0.000010758380012703128 s |
1.21 |
Concat / IDefOpt / cpu / PostRev |
0.000014 s |
0.000011344799977450748 s |
1.23 |
Concat / IDefOpt / cpu / BothRev |
0.000013 s |
0.00001162687997748435 s |
1.12 |
const_scatter / JaXPipe / cpu / Primal |
0.000007026700031929067 s |
0.000006484459991042968 s |
1.08 |
const_scatter / Jax / cpu / Primal |
0.000007550460004495108 s |
0.000006152880005174666 s |
1.23 |
const_scatter / HLOOpt / cpu / Primal |
0.000007093239955793251 s |
0.000006791900013922714 s |
1.04 |
const_scatter / PartOpt / cpu / Primal |
0.00000688708000780025 s |
0.00000655729999380128 s |
1.05 |
const_scatter / IPartOpt / cpu / Primal |
0.000007286179998118314 s |
0.000007222479980555363 s |
1.01 |
const_scatter / DefOpt / cpu / Primal |
0.000007622979965162813 s |
0.000007224400014820276 s |
1.06 |
const_scatter / IDefOpt / cpu / Primal |
0.000007493059983971762 s |
0.000006710400039082742 s |
1.12 |
const_scatter / JaXPipe / cpu / Forward |
0.000011500419986987254 s |
0.000010482079960638658 s |
1.10 |
const_scatter / Jax / cpu / Forward |
0.000010357580013078405 s |
0.0000089807199765346 s |
1.15 |
const_scatter / HLOOpt / cpu / Forward |
0.000012187540032755353 s |
0.000011184680015503546 s |
1.09 |
const_scatter / PartOpt / cpu / Forward |
0.000011786259992732084 s |
0.000010262339983455604 s |
1.15 |
const_scatter / IPartOpt / cpu / Forward |
0.000011769039992941544 s |
0.000011011039996446923 s |
1.07 |
const_scatter / DefOpt / cpu / Forward |
0.0000114010799825337 s |
0.000010111440014952677 s |
1.13 |
const_scatter / IDefOpt / cpu / Forward |
0.000012188540040369844 s |
0.000010444079953231266 s |
1.17 |
const_scatter / JaXPipe / cpu / PreRev |
0.0002881356199941 s |
0.0002865162400303 s |
1.01 |
const_scatter / JaXPipe / cpu / PostRev |
0.0002823180399536 s |
0.0002814156199929 s |
1.00 |
const_scatter / JaXPipe / cpu / BothRev |
0.0002859497599911 s |
0.0002842942999632 s |
1.01 |
const_scatter / Jax / cpu / BothRev |
0.0002859110999816 s |
0.0002827953999803 s |
1.01 |
const_scatter / HLOOpt / cpu / PreRev |
0.000285404340002 s |
0.0002827894400161 s |
1.01 |
const_scatter / HLOOpt / cpu / PostRev |
0.0002854601400031 s |
0.0002853909399709 s |
1.00 |
const_scatter / HLOOpt / cpu / BothRev |
0.0002832564599884 s |
0.0002819706999434 s |
1.00 |
const_scatter / PartOpt / cpu / PreRev |
0.0002846478999526 s |
0.0002821833399957 s |
1.01 |
const_scatter / PartOpt / cpu / PostRev |
0.0002828901799966 s |
0.0002816280799561 s |
1.00 |
const_scatter / PartOpt / cpu / BothRev |
0.000285806799975 s |
0.000282013979986 s |
1.01 |
const_scatter / IPartOpt / cpu / PreRev |
0.0002850937600305 s |
0.0002821123599824 s |
1.01 |
const_scatter / IPartOpt / cpu / PostRev |
0.0002841724799509 s |
0.0002832193599897 s |
1.00 |
const_scatter / IPartOpt / cpu / BothRev |
0.0002839576000224 s |
0.0002784233399688 s |
1.02 |
const_scatter / DefOpt / cpu / PreRev |
0.0002857492999646 s |
0.0002812062400516 s |
1.02 |
const_scatter / DefOpt / cpu / PostRev |
0.0002839961999961 s |
0.0002820629599955 s |
1.01 |
const_scatter / DefOpt / cpu / BothRev |
0.000286169619967 s |
0.0002900112800307 s |
0.99 |
const_scatter / IDefOpt / cpu / PreRev |
0.0002852966000682 s |
0.0002818730000035 s |
1.01 |
const_scatter / IDefOpt / cpu / PostRev |
0.000285924180016 s |
0.0002818949799802 s |
1.01 |
const_scatter / IDefOpt / cpu / BothRev |
0.0002857016399502 s |
0.0002822107000065 s |
1.01 |
const_scatter / JaXPipe / cuda / Primal |
0.000001887 s |
0.0000024 s |
0.79 |
const_scatter / Jax / cuda / Primal |
0.000001887 s |
0.0000024 s |
0.79 |
const_scatter / HLOOpt / cuda / Primal |
0.000001887 s |
0.000002399 s |
0.79 |
const_scatter / PartOpt / cuda / Primal |
0.000001887 s |
0.0000024 s |
0.79 |
const_scatter / IPartOpt / cuda / Primal |
0.000001887 s |
0.0000024 s |
0.79 |
const_scatter / DefOpt / cuda / Primal |
0.000001887 s |
0.0000024 s |
0.79 |
const_scatter / IDefOpt / cuda / Primal |
0.000001887 s |
0.0000024 s |
0.79 |
const_scatter / JaXPipe / cuda / Forward |
0.000010367 s |
0.000010624 s |
0.98 |
const_scatter / Jax / cuda / Forward |
0.000009952 s |
0.000010655 s |
0.93 |
const_scatter / HLOOpt / cuda / Forward |
0.000010433 s |
0.00001088 s |
0.96 |
const_scatter / PartOpt / cuda / Forward |
0.000010655 s |
0.000010943 s |
0.97 |
const_scatter / IPartOpt / cuda / Forward |
0.000010432 s |
0.000010689 s |
0.98 |
const_scatter / DefOpt / cuda / Forward |
0.000010111 s |
0.000010656 s |
0.95 |
const_scatter / IDefOpt / cuda / Forward |
0.000009984 s |
0.000010944 s |
0.91 |
const_scatter / JaXPipe / cuda / PreRev |
0.000017056 s |
0.000016608 s |
1.03 |
const_scatter / JaXPipe / cuda / PostRev |
0.000016992 s |
0.000017375999999999998 s |
0.98 |
const_scatter / JaXPipe / cuda / BothRev |
0.000016736 s |
0.000017024 s |
0.98 |
const_scatter / Jax / cuda / BothRev |
0.000016927999999999998 s |
0.000017503 s |
0.97 |
const_scatter / HLOOpt / cuda / PreRev |
0.000016864 s |
0.00001824 s |
0.92 |
const_scatter / HLOOpt / cuda / PostRev |
0.00001696 s |
0.000017505 s |
0.97 |
const_scatter / HLOOpt / cuda / BothRev |
0.000016864 s |
0.000016992 s |
0.99 |
const_scatter / PartOpt / cuda / PreRev |
0.00001696 s |
0.0000176 s |
0.96 |
const_scatter / PartOpt / cuda / PostRev |
0.000016736 s |
0.000017088 s |
0.98 |
const_scatter / PartOpt / cuda / BothRev |
0.000016544 s |
0.000016768000000000003 s |
0.99 |
const_scatter / IPartOpt / cuda / PreRev |
0.000016383999999999998 s |
0.000016864 s |
0.97 |
const_scatter / IPartOpt / cuda / PostRev |
0.000016992 s |
0.000016736 s |
1.02 |
const_scatter / IPartOpt / cuda / BothRev |
0.00001632 s |
0.000016736 s |
0.98 |
const_scatter / DefOpt / cuda / PreRev |
0.000017088 s |
0.000017375999999999998 s |
0.98 |
const_scatter / DefOpt / cuda / PostRev |
0.00001696 s |
0.000017216 s |
0.99 |
const_scatter / DefOpt / cuda / BothRev |
0.00001648 s |
0.000017056 s |
0.97 |
const_scatter / IDefOpt / cuda / PreRev |
0.000016865000000000002 s |
0.000017024 s |
0.99 |
const_scatter / IDefOpt / cuda / PostRev |
0.000016512 s |
0.0000168 s |
0.98 |
const_scatter / IDefOpt / cuda / BothRev |
0.000017247999999999998 s |
0.000016448000000000002 s |
1.05 |
const_scatter / JaXPipe / cpu / Primal |
0.000016055 s |
0.000006484459991042968 s |
2.48 |
const_scatter / Jax / cpu / Primal |
0.000015703000000000002 s |
0.000006152880005174666 s |
2.55 |
const_scatter / HLOOpt / cpu / Primal |
0.000016879000000000002 s |
0.000006791900013922714 s |
2.49 |
const_scatter / PartOpt / cpu / Primal |
0.000015779000000000003 s |
0.00000655729999380128 s |
2.41 |
const_scatter / IPartOpt / cpu / Primal |
0.000015969 s |
0.000007222479980555363 s |
2.21 |
const_scatter / DefOpt / cpu / Primal |
0.000016736 s |
0.000007224400014820276 s |
2.32 |
const_scatter / IDefOpt / cpu / Primal |
0.000016938999999999998 s |
0.000006710400039082742 s |
2.52 |
const_scatter / JaXPipe / cpu / Forward |
0.000022123 s |
0.000010482079960638658 s |
2.11 |
const_scatter / Jax / cpu / Forward |
0.000020636 s |
0.0000089807199765346 s |
2.30 |
const_scatter / HLOOpt / cpu / Forward |
0.000022229 s |
0.000011184680015503546 s |
1.99 |
const_scatter / PartOpt / cpu / Forward |
0.000022038 s |
0.000010262339983455604 s |
2.15 |
const_scatter / IPartOpt / cpu / Forward |
0.000021691 s |
0.000011011039996446923 s |
1.97 |
const_scatter / DefOpt / cpu / Forward |
0.000021991 s |
0.000010111440014952677 s |
2.17 |
const_scatter / IDefOpt / cpu / Forward |
0.000022313 s |
0.000010444079953231266 s |
2.14 |
const_scatter / JaXPipe / cpu / PreRev |
0.000522713 s |
0.0002865162400303 s |
1.82 |
const_scatter / JaXPipe / cpu / PostRev |
0.000540982 s |
0.0002814156199929 s |
1.92 |
const_scatter / JaXPipe / cpu / BothRev |
0.000540463 s |
0.0002842942999632 s |
1.90 |
const_scatter / Jax / cpu / BothRev |
0.00054738 s |
0.0002827953999803 s |
1.94 |
const_scatter / HLOOpt / cpu / PreRev |
0.000542306 s |
0.0002827894400161 s |
1.92 |
const_scatter / HLOOpt / cpu / PostRev |
0.000600173 s |
0.0002853909399709 s |
2.10 |
const_scatter / HLOOpt / cpu / BothRev |
0.000536242 s |
0.0002819706999434 s |
1.90 |
const_scatter / PartOpt / cpu / PreRev |
0.000537577 s |
0.0002821833399957 s |
1.91 |
const_scatter / PartOpt / cpu / PostRev |
0.000534114 s |
0.0002816280799561 s |
1.90 |
const_scatter / PartOpt / cpu / BothRev |
0.0005338389999999 s |
0.000282013979986 s |
1.89 |
const_scatter / IPartOpt / cpu / PreRev |
0.000542895 s |
0.0002821123599824 s |
1.92 |
const_scatter / IPartOpt / cpu / PostRev |
0.0005313879999999 s |
0.0002832193599897 s |
1.88 |
const_scatter / IPartOpt / cpu / BothRev |
0.0005392109999999 s |
0.0002784233399688 s |
1.94 |
const_scatter / DefOpt / cpu / PreRev |
0.000538989 s |
0.0002812062400516 s |
1.92 |
const_scatter / DefOpt / cpu / PostRev |
0.000542274 s |
0.0002820629599955 s |
1.92 |
const_scatter / DefOpt / cpu / BothRev |
0.00054305 s |
0.0002900112800307 s |
1.87 |
const_scatter / IDefOpt / cpu / PreRev |
0.000535274 s |
0.0002818730000035 s |
1.90 |
const_scatter / IDefOpt / cpu / PostRev |
0.000537066 s |
0.0002818949799802 s |
1.91 |
const_scatter / IDefOpt / cpu / BothRev |
0.000538098 s |
0.0002822107000065 s |
1.91 |
const_scatter / JaXPipe / cpu / Primal |
0.000008999999999999999 s |
0.000006484459991042968 s |
1.39 |
const_scatter / Jax / cpu / Primal |
0.000008 s |
0.000006152880005174666 s |
1.30 |
const_scatter / HLOOpt / cpu / Primal |
0.000008 s |
0.000006791900013922714 s |
1.18 |
const_scatter / PartOpt / cpu / Primal |
0.000008 s |
0.00000655729999380128 s |
1.22 |
const_scatter / IPartOpt / cpu / Primal |
0.000008 s |
0.000007222479980555363 s |
1.11 |
const_scatter / DefOpt / cpu / Primal |
0.000008 s |
0.000007224400014820276 s |
1.11 |
const_scatter / IDefOpt / cpu / Primal |
0.000008 s |
0.000006710400039082742 s |
1.19 |
const_scatter / JaXPipe / cpu / Forward |
0.000012 s |
0.000010482079960638658 s |
1.14 |
const_scatter / Jax / cpu / Forward |
0.000011 s |
0.0000089807199765346 s |
1.22 |
const_scatter / HLOOpt / cpu / Forward |
0.000013 s |
0.000011184680015503546 s |
1.16 |
const_scatter / PartOpt / cpu / Forward |
0.000013 s |
0.000010262339983455604 s |
1.27 |
const_scatter / IPartOpt / cpu / Forward |
0.000012 s |
0.000011011039996446923 s |
1.09 |
const_scatter / DefOpt / cpu / Forward |
0.000011 s |
0.000010111440014952677 s |
1.09 |
const_scatter / IDefOpt / cpu / Forward |
0.000012 s |
0.000010444079953231266 s |
1.15 |
const_scatter / JaXPipe / cpu / PreRev |
0.000337 s |
0.0002865162400303 s |
1.18 |
const_scatter / JaXPipe / cpu / PostRev |
0.000327 s |
0.0002814156199929 s |
1.16 |
const_scatter / JaXPipe / cpu / BothRev |
0.000352 s |
0.0002842942999632 s |
1.24 |
const_scatter / Jax / cpu / BothRev |
0.0003459999999999 s |
0.0002827953999803 s |
1.22 |
const_scatter / HLOOpt / cpu / PreRev |
0.00034 s |
0.0002827894400161 s |
1.20 |
const_scatter / HLOOpt / cpu / PostRev |
0.000389 s |
0.0002853909399709 s |
1.36 |
const_scatter / HLOOpt / cpu / BothRev |
0.0003509999999999 s |
0.0002819706999434 s |
1.24 |
const_scatter / PartOpt / cpu / PreRev |
0.000342 s |
0.0002821833399957 s |
1.21 |
const_scatter / PartOpt / cpu / PostRev |
0.000324 s |
0.0002816280799561 s |
1.15 |
const_scatter / PartOpt / cpu / BothRev |
0.000334 s |
0.000282013979986 s |
1.18 |
const_scatter / IPartOpt / cpu / PreRev |
0.000338 s |
0.0002821123599824 s |
1.20 |
const_scatter / IPartOpt / cpu / PostRev |
0.000343 s |
0.0002832193599897 s |
1.21 |
const_scatter / IPartOpt / cpu / BothRev |
0.0003439999999999 s |
0.0002784233399688 s |
1.24 |
const_scatter / DefOpt / cpu / PreRev |
0.000347 s |
0.0002812062400516 s |
1.23 |
const_scatter / DefOpt / cpu / PostRev |
0.000319 s |
0.0002820629599955 s |
1.13 |
const_scatter / DefOpt / cpu / BothRev |
0.0003489999999999 s |
0.0002900112800307 s |
1.20 |
const_scatter / IDefOpt / cpu / PreRev |
0.000373 s |
0.0002818730000035 s |
1.32 |
const_scatter / IDefOpt / cpu / PostRev |
0.0003599999999999 s |
0.0002818949799802 s |
1.28 |
const_scatter / IDefOpt / cpu / BothRev |
0.0003599999999999 s |
0.0002822107000065 s |
1.28 |
GenDot / JaXPipe / cpu / Primal |
0.000008656840000185184 s |
0.000006785620025766548 s |
1.28 |
GenDot / Jax / cpu / Primal |
0.000008176819974323735 s |
0.000006492779948530369 s |
1.26 |
GenDot / HLOOpt / cpu / Primal |
0.000007996700005605817 s |
0.000007109359985406627 s |
1.12 |
GenDot / PartOpt / cpu / Primal |
0.000007653119992028223 s |
0.000006990679985392489 s |
1.09 |
GenDot / IPartOpt / cpu / Primal |
0.000007516300001952914 s |
0.000007588700018459349 s |
0.99 |
GenDot / DefOpt / cpu / Primal |
0.000007598220017825952 s |
0.000006795659992349101 s |
1.12 |
GenDot / IDefOpt / cpu / Primal |
0.000007461439990947838 s |
0.000006810639997638646 s |
1.10 |
GenDot / JaXPipe / cpu / Forward |
0.000012946519991601237 s |
0.000011238680062888308 s |
1.15 |
GenDot / Jax / cpu / Forward |
0.000010978919999615754 s |
0.000009929460029525216 s |
1.11 |
GenDot / HLOOpt / cpu / Forward |
0.000012302599971008022 s |
0.000010993279984177208 s |
1.12 |
GenDot / PartOpt / cpu / Forward |
0.00001122088006013655 s |
0.000010583400007817544 s |
1.06 |
GenDot / IPartOpt / cpu / Forward |
0.00001201924002089072 s |
0.000010986179986502976 s |
1.09 |
GenDot / DefOpt / cpu / Forward |
0.000011489100033941211 s |
0.000010358100016674143 s |
1.11 |
GenDot / IDefOpt / cpu / Forward |
0.000012075439972250024 s |
0.000010391560035714065 s |
1.16 |
GenDot / JaXPipe / cpu / PreRev |
0.000011794660013038085 s |
0.000010806640020746272 s |
1.09 |
GenDot / JaXPipe / cpu / PostRev |
0.00001253369999176357 s |
0.000010060600034194068 s |
1.25 |
GenDot / JaXPipe / cpu / BothRev |
0.000013156439972590306 s |
0.000010620300008667982 s |
1.24 |
GenDot / Jax / cpu / BothRev |
0.00001182020001579076 s |
0.000010766199966383284 s |
1.10 |
GenDot / HLOOpt / cpu / PreRev |
0.000012600700019902433 s |
0.000012160900005255828 s |
1.04 |
GenDot / HLOOpt / cpu / PostRev |
0.00001453931996366009 s |
0.00001219715998558968 s |
1.19 |
GenDot / HLOOpt / cpu / BothRev |
0.000012114460041630082 s |
0.000010898959963014932 s |
1.11 |
GenDot / PartOpt / cpu / PreRev |
0.000011795039999924484 s |
0.000011172759996043168 s |
1.06 |
GenDot / PartOpt / cpu / PostRev |
0.00001192555999296019 s |
0.000010048879976238823 s |
1.19 |
GenDot / PartOpt / cpu / BothRev |
0.000012429520047589904 s |
0.000010884319999604486 s |
1.14 |
GenDot / IPartOpt / cpu / PreRev |
0.000011838640002679312 s |
0.000011299399939161956 s |
1.05 |
GenDot / IPartOpt / cpu / PostRev |
0.000012223699977766957 s |
0.000010203999981968082 s |
1.20 |
GenDot / IPartOpt / cpu / BothRev |
0.000012234440018801252 s |
0.000010894619981627327 s |
1.12 |
GenDot / DefOpt / cpu / PreRev |
0.000011757340043914157 s |
0.000011270700006207336 s |
1.04 |
GenDot / DefOpt / cpu / PostRev |
0.00001233499999216292 s |
0.000010326019992135117 s |
1.19 |
GenDot / DefOpt / cpu / BothRev |
0.00001236273996255477 s |
0.000010368180037403364 s |
1.19 |
GenDot / IDefOpt / cpu / PreRev |
0.000012222420027683256 s |
0.000010541539995756468 s |
1.16 |
GenDot / IDefOpt / cpu / PostRev |
0.000012530320018413475 s |
0.000010498439996808883 s |
1.19 |
GenDot / IDefOpt / cpu / BothRev |
0.000012059980026606354 s |
0.000010458060023665892 s |
1.15 |
GenDot / JaXPipe / cuda / Primal |
0.000002016 s |
0.000002496 s |
0.81 |
GenDot / Jax / cuda / Primal |
0.000002016 s |
0.000002496 s |
0.81 |
GenDot / HLOOpt / cuda / Primal |
0.000002015 s |
0.000002464 s |
0.82 |
GenDot / PartOpt / cuda / Primal |
0.000002015 s |
0.000002496 s |
0.81 |
GenDot / IPartOpt / cuda / Primal |
0.000002015 s |
0.000002527 s |
0.80 |
GenDot / DefOpt / cuda / Primal |
0.000002015 s |
0.000002495 s |
0.81 |
GenDot / IDefOpt / cuda / Primal |
0.000002015 s |
0.000002495 s |
0.81 |
GenDot / JaXPipe / cuda / Forward |
0.000010048 s |
0.000010751 s |
0.93 |
GenDot / Jax / cuda / Forward |
0.000010112 s |
0.000011872 s |
0.85 |
GenDot / HLOOpt / cuda / Forward |
0.000010336 s |
0.000011487 s |
0.90 |
GenDot / PartOpt / cuda / Forward |
0.000010753 s |
0.000012129 s |
0.89 |
GenDot / IPartOpt / cuda / Forward |
0.000010336 s |
0.000010784 s |
0.96 |
GenDot / DefOpt / cuda / Forward |
0.000010689 s |
0.000010753 s |
0.99 |
GenDot / IDefOpt / cuda / Forward |
0.000012544 s |
0.000013376 s |
0.94 |
GenDot / JaXPipe / cuda / PreRev |
0.000010176 s |
0.000010688 s |
0.95 |
GenDot / JaXPipe / cuda / PostRev |
0.000010336 s |
0.000010689 s |
0.97 |
GenDot / JaXPipe / cuda / BothRev |
0.000010047 s |
0.000010592 s |
0.95 |
GenDot / Jax / cuda / BothRev |
0.000011232 s |
0.000010752 s |
1.04 |
GenDot / HLOOpt / cuda / PreRev |
0.000011232 s |
0.000010944 s |
1.03 |
GenDot / HLOOpt / cuda / PostRev |
0.000011103 s |
0.000010432 s |
1.06 |
GenDot / HLOOpt / cuda / BothRev |
0.000010432 s |
0.000010625 s |
0.98 |
GenDot / PartOpt / cuda / PreRev |
0.000010144 s |
0.000010816 s |
0.94 |
GenDot / PartOpt / cuda / PostRev |
0.0000104 s |
0.000010912 s |
0.95 |
GenDot / PartOpt / cuda / BothRev |
0.000010015 s |
0.000010399 s |
0.96 |
GenDot / IPartOpt / cuda / PreRev |
0.00001008 s |
0.000010816 s |
0.93 |
GenDot / IPartOpt / cuda / PostRev |
0.000010271 s |
0.00001072 s |
0.96 |
GenDot / IPartOpt / cuda / BothRev |
0.000010143 s |
0.000013504 s |
0.75 |
GenDot / DefOpt / cuda / PreRev |
0.00001008 s |
0.000010976 s |
0.92 |
GenDot / DefOpt / cuda / PostRev |
0.000009984 s |
0.000010784 s |
0.93 |
GenDot / DefOpt / cuda / BothRev |
0.000010336 s |
0.00001072 s |
0.96 |
GenDot / IDefOpt / cuda / PreRev |
0.000010528 s |
0.000010976 s |
0.96 |
GenDot / IDefOpt / cuda / PostRev |
0.00000976 s |
0.000010624 s |
0.92 |
GenDot / IDefOpt / cuda / BothRev |
0.000011233 s |
0.00001056 s |
1.06 |
GenDot / JaXPipe / cpu / Primal |
0.000019022 s |
0.000006785620025766548 s |
2.80 |
GenDot / Jax / cpu / Primal |
0.000019278 s |
0.000006492779948530369 s |
2.97 |
GenDot / HLOOpt / cpu / Primal |
0.000017579000000000002 s |
0.000007109359985406627 s |
2.47 |
GenDot / PartOpt / cpu / Primal |
0.000018047 s |
0.000006990679985392489 s |
2.58 |
GenDot / IPartOpt / cpu / Primal |
0.000018282 s |
0.000007588700018459349 s |
2.41 |
GenDot / DefOpt / cpu / Primal |
0.000017391 s |
0.000006795659992349101 s |
2.56 |
GenDot / IDefOpt / cpu / Primal |
0.000017165 s |
0.000006810639997638646 s |
2.52 |
GenDot / JaXPipe / cpu / Forward |
0.000024037 s |
0.000011238680062888308 s |
2.14 |
GenDot / Jax / cpu / Forward |
0.000024988 s |
0.000009929460029525216 s |
2.52 |
GenDot / HLOOpt / cpu / Forward |
0.000023744 s |
0.000010993279984177208 s |
2.16 |
GenDot / PartOpt / cpu / Forward |
0.00002401 s |
0.000010583400007817544 s |
2.27 |
GenDot / IPartOpt / cpu / Forward |
0.000023993 s |
0.000010986179986502976 s |
2.18 |
GenDot / DefOpt / cpu / Forward |
0.000023949 s |
0.000010358100016674143 s |
2.31 |
GenDot / IDefOpt / cpu / Forward |
0.000024009 s |
0.000010391560035714065 s |
2.31 |
GenDot / JaXPipe / cpu / PreRev |
0.00002429 s |
0.000010806640020746272 s |
2.25 |
GenDot / JaXPipe / cpu / PostRev |
0.00002556 s |
0.000010060600034194068 s |
2.54 |
GenDot / JaXPipe / cpu / BothRev |
0.000024297 s |
0.000010620300008667982 s |
2.29 |
GenDot / Jax / cpu / BothRev |
0.000025573 s |
0.000010766199966383284 s |
2.38 |
GenDot / HLOOpt / cpu / PreRev |
0.00002391 s |
0.000012160900005255828 s |
1.97 |
GenDot / HLOOpt / cpu / PostRev |
0.000024048 s |
0.00001219715998558968 s |
1.97 |
GenDot / HLOOpt / cpu / BothRev |
0.000023803 s |
0.000010898959963014932 s |
2.18 |
GenDot / PartOpt / cpu / PreRev |
0.000023551 s |
0.000011172759996043168 s |
2.11 |
GenDot / PartOpt / cpu / PostRev |
0.000024934 s |
0.000010048879976238823 s |
2.48 |
GenDot / PartOpt / cpu / BothRev |
0.000031069 s |
0.000010884319999604486 s |
2.85 |
GenDot / IPartOpt / cpu / PreRev |
0.000024012 s |
0.000011299399939161956 s |
2.13 |
GenDot / IPartOpt / cpu / PostRev |
0.000025107 s |
0.000010203999981968082 s |
2.46 |
GenDot / IPartOpt / cpu / BothRev |
0.000024159 s |
0.000010894619981627327 s |
2.22 |
GenDot / DefOpt / cpu / PreRev |
0.000023781 s |
0.000011270700006207336 s |
2.11 |
GenDot / DefOpt / cpu / PostRev |
0.000024097 s |
0.000010326019992135117 s |
2.33 |
GenDot / DefOpt / cpu / BothRev |
0.000023892 s |
0.000010368180037403364 s |
2.30 |
GenDot / IDefOpt / cpu / PreRev |
0.000024027 s |
0.000010541539995756468 s |
2.28 |
GenDot / IDefOpt / cpu / PostRev |
0.000023834000000000003 s |
0.000010498439996808883 s |
2.27 |
GenDot / IDefOpt / cpu / BothRev |
0.000023968 s |
0.000010458060023665892 s |
2.29 |
GenDot / JaXPipe / cpu / Primal |
0.00001 s |
0.000006785620025766548 s |
1.47 |
GenDot / Jax / cpu / Primal |
0.00001 s |
0.000006492779948530369 s |
1.54 |
GenDot / HLOOpt / cpu / Primal |
0.00001 s |
0.000007109359985406627 s |
1.41 |
GenDot / PartOpt / cpu / Primal |
0.00001 s |
0.000006990679985392489 s |
1.43 |
GenDot / IPartOpt / cpu / Primal |
0.00001 s |
0.000007588700018459349 s |
1.32 |
GenDot / DefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000006795659992349101 s |
1.32 |
GenDot / IDefOpt / cpu / Primal |
0.00001 s |
0.000006810639997638646 s |
1.47 |
GenDot / JaXPipe / cpu / Forward |
0.000014 s |
0.000011238680062888308 s |
1.25 |
GenDot / Jax / cpu / Forward |
0.000014 s |
0.000009929460029525216 s |
1.41 |
GenDot / HLOOpt / cpu / Forward |
0.000014 s |
0.000010993279984177208 s |
1.27 |
GenDot / PartOpt / cpu / Forward |
0.000014 s |
0.000010583400007817544 s |
1.32 |
GenDot / IPartOpt / cpu / Forward |
0.000013 s |
0.000010986179986502976 s |
1.18 |
GenDot / DefOpt / cpu / Forward |
0.000013 s |
0.000010358100016674143 s |
1.26 |
GenDot / IDefOpt / cpu / Forward |
0.000014 s |
0.000010391560035714065 s |
1.35 |
GenDot / JaXPipe / cpu / PreRev |
0.000013 s |
0.000010806640020746272 s |
1.20 |
GenDot / JaXPipe / cpu / PostRev |
0.000014 s |
0.000010060600034194068 s |
1.39 |
GenDot / JaXPipe / cpu / BothRev |
0.000014 s |
0.000010620300008667982 s |
1.32 |
GenDot / Jax / cpu / BothRev |
0.000015 s |
0.000010766199966383284 s |
1.39 |
GenDot / HLOOpt / cpu / PreRev |
0.000014 s |
0.000012160900005255828 s |
1.15 |
GenDot / HLOOpt / cpu / PostRev |
0.000013 s |
0.00001219715998558968 s |
1.07 |
GenDot / HLOOpt / cpu / BothRev |
0.000013 s |
0.000010898959963014932 s |
1.19 |
GenDot / PartOpt / cpu / PreRev |
0.000014 s |
0.000011172759996043168 s |
1.25 |
GenDot / PartOpt / cpu / PostRev |
0.000015 s |
0.000010048879976238823 s |
1.49 |
GenDot / PartOpt / cpu / BothRev |
0.000014 s |
0.000010884319999604486 s |
1.29 |
GenDot / IPartOpt / cpu / PreRev |
0.000014 s |
0.000011299399939161956 s |
1.24 |
GenDot / IPartOpt / cpu / PostRev |
0.000014 s |
0.000010203999981968082 s |
1.37 |
GenDot / IPartOpt / cpu / BothRev |
0.000015 s |
0.000010894619981627327 s |
1.38 |
GenDot / DefOpt / cpu / PreRev |
0.000014 s |
0.000011270700006207336 s |
1.24 |
GenDot / DefOpt / cpu / PostRev |
0.000014 s |
0.000010326019992135117 s |
1.36 |
GenDot / DefOpt / cpu / BothRev |
0.000014 s |
0.000010368180037403364 s |
1.35 |
GenDot / IDefOpt / cpu / PreRev |
0.000014 s |
0.000010541539995756468 s |
1.33 |
GenDot / IDefOpt / cpu / PostRev |
0.000014 s |
0.000010498439996808883 s |
1.33 |
GenDot / IDefOpt / cpu / BothRev |
0.000014 s |
0.000010458060023665892 s |
1.34 |
hlo_ffi / JaXPipe / cpu / Primal |
0.00001142959999924642 s |
0.00001034003998938715 s |
1.11 |
hlo_ffi / Jax / cpu / Primal |
0.000011243679982726465 s |
0.000009985020033127513 s |
1.13 |
hlo_ffi / HLOOpt / cpu / Primal |
0.000010545180002736742 s |
0.000009755440023582196 s |
1.08 |
hlo_ffi / PartOpt / cpu / Primal |
0.000010499179943508352 s |
0.000009405199953107512 s |
1.12 |
hlo_ffi / IPartOpt / cpu / Primal |
0.000010649060059222392 s |
0.00000985210000180814 s |
1.08 |
hlo_ffi / DefOpt / cpu / Primal |
0.000010487179988558637 s |
0.00000947170000472397 s |
1.11 |
hlo_ffi / IDefOpt / cpu / Primal |
0.000010112999980265158 s |
0.000010050320024674877 s |
1.01 |
hlo_ffi / JaXPipe / cpu / Forward |
0.00001500110000051791 s |
0.000014069779990677488 s |
1.07 |
hlo_ffi / Jax / cpu / Forward |
0.000015473819976250523 s |
0.000013719179996769526 s |
1.13 |
hlo_ffi / HLOOpt / cpu / Forward |
0.000015370800047094234 s |
0.000013785899946014978 s |
1.11 |
hlo_ffi / PartOpt / cpu / Forward |
0.000015421419984704698 s |
0.000013894799985791906 s |
1.11 |
hlo_ffi / IPartOpt / cpu / Forward |
0.000015171480017670546 s |
0.000013855580018571343 s |
1.09 |
hlo_ffi / DefOpt / cpu / Forward |
0.00001529455999843776 s |
0.000014091939965510391 s |
1.09 |
hlo_ffi / IDefOpt / cpu / Forward |
0.00001514234002570447 s |
0.000013815360034641344 s |
1.10 |
hlo_ffi / JaXPipe / cpu / PreRev |
0.000015748579999126376 s |
0.00001372190001347917 s |
1.15 |
hlo_ffi / JaXPipe / cpu / PostRev |
0.000014633120008511468 s |
0.00001410404000125709 s |
1.04 |
hlo_ffi / JaXPipe / cpu / BothRev |
0.000014734080014022766 s |
0.00001385939998726826 s |
1.06 |
hlo_ffi / Jax / cpu / BothRev |
0.00001537492001261853 s |
0.00001422051998815732 s |
1.08 |
hlo_ffi / HLOOpt / cpu / PreRev |
0.000015553320035905927 s |
0.000014327220023915288 s |
1.09 |
hlo_ffi / HLOOpt / cpu / PostRev |
0.000017372820011587464 s |
0.00001546456001960905 s |
1.12 |
hlo_ffi / HLOOpt / cpu / BothRev |
0.000014697560009153675 s |
0.000013411179988906951 s |
1.10 |
hlo_ffi / PartOpt / cpu / PreRev |
0.00001543246000437648 s |
0.000013805800017507864 s |
1.12 |
hlo_ffi / PartOpt / cpu / PostRev |
0.000014537160013787798 s |
0.000013704339999094372 s |
1.06 |
hlo_ffi / PartOpt / cpu / BothRev |
0.000014870699978928314 s |
0.000014091119965087271 s |
1.06 |
hlo_ffi / IPartOpt / cpu / PreRev |
0.000014974020014051347 s |
0.000013858420024916996 s |
1.08 |
hlo_ffi / IPartOpt / cpu / PostRev |
0.000015494219969696132 s |
0.000013587200028268851 s |
1.14 |
hlo_ffi / IPartOpt / cpu / BothRev |
0.000014774379997106734 s |
0.00001375443998767878 s |
1.07 |
hlo_ffi / DefOpt / cpu / PreRev |
0.000015701319980507833 s |
0.000014191280033628573 s |
1.11 |
hlo_ffi / DefOpt / cpu / PostRev |
0.00001502381998761848 s |
0.000013898340012019616 s |
1.08 |
hlo_ffi / DefOpt / cpu / BothRev |
0.000015504480024901568 s |
0.000013873600018996512 s |
1.12 |
hlo_ffi / IDefOpt / cpu / PreRev |
0.000015300020058930387 s |
0.000014398280000023078 s |
1.06 |
hlo_ffi / IDefOpt / cpu / PostRev |
0.000015047620008772355 s |
0.000013474280058289878 s |
1.12 |
hlo_ffi / IDefOpt / cpu / BothRev |
0.000015251139975589467 s |
0.000013760899964836426 s |
1.11 |
hlo_ffi / JaXPipe / cuda / Primal |
0.000001984 s |
0.000002335 s |
0.85 |
hlo_ffi / Jax / cuda / Primal |
0.000001984 s |
0.000002336 s |
0.85 |
hlo_ffi / HLOOpt / cuda / Primal |
0.000001983 s |
0.000002336 s |
0.85 |
hlo_ffi / PartOpt / cuda / Primal |
0.000001983 s |
0.000002336 s |
0.85 |
hlo_ffi / IPartOpt / cuda / Primal |
0.000001984 s |
0.000002336 s |
0.85 |
hlo_ffi / DefOpt / cuda / Primal |
0.000001984 s |
0.000002336 s |
0.85 |
hlo_ffi / IDefOpt / cuda / Primal |
0.000001984 s |
0.000002336 s |
0.85 |
hlo_ffi / JaXPipe / cuda / Forward |
0.00000208 s |
0.000002431 s |
0.86 |
hlo_ffi / Jax / cuda / Forward |
0.00000208 s |
0.000002432 s |
0.86 |
hlo_ffi / HLOOpt / cuda / Forward |
0.000002079 s |
0.000002431 s |
0.86 |
hlo_ffi / PartOpt / cuda / Forward |
0.00000208 s |
0.000002431 s |
0.86 |
hlo_ffi / IPartOpt / cuda / Forward |
0.00000208 s |
0.000002431 s |
0.86 |
hlo_ffi / DefOpt / cuda / Forward |
0.00000208 s |
0.000002431 s |
0.86 |
hlo_ffi / IDefOpt / cuda / Forward |
0.00000208 s |
0.000002431 s |
0.86 |
hlo_ffi / JaXPipe / cuda / PreRev |
0.000002049 s |
0.0000024 s |
0.85 |
hlo_ffi / JaXPipe / cuda / PostRev |
0.000002048 s |
0.0000024 s |
0.85 |
hlo_ffi / JaXPipe / cuda / BothRev |
0.000002048 s |
0.0000024 s |
0.85 |
hlo_ffi / Jax / cuda / BothRev |
0.000002048 s |
0.0000024 s |
0.85 |
hlo_ffi / HLOOpt / cuda / PreRev |
0.000002048 s |
0.000002399 s |
0.85 |
hlo_ffi / HLOOpt / cuda / PostRev |
0.000002048 s |
0.000002431 s |
0.84 |
hlo_ffi / HLOOpt / cuda / BothRev |
0.000002047 s |
0.0000024 s |
0.85 |
hlo_ffi / PartOpt / cuda / PreRev |
0.000002048 s |
0.0000024 s |
0.85 |
hlo_ffi / PartOpt / cuda / PostRev |
0.000002047 s |
0.0000024 s |
0.85 |
hlo_ffi / PartOpt / cuda / BothRev |
0.000002047 s |
0.0000024 s |
0.85 |
hlo_ffi / IPartOpt / cuda / PreRev |
0.000002048 s |
0.0000024 s |
0.85 |
hlo_ffi / IPartOpt / cuda / PostRev |
0.000002048 s |
0.000002431 s |
0.84 |
hlo_ffi / IPartOpt / cuda / BothRev |
0.000002047 s |
0.0000024 s |
0.85 |
hlo_ffi / DefOpt / cuda / PreRev |
0.000002048 s |
0.000002431 s |
0.84 |
hlo_ffi / DefOpt / cuda / PostRev |
0.000002047 s |
0.0000024 s |
0.85 |
hlo_ffi / DefOpt / cuda / BothRev |
0.000002049 s |
0.000002431 s |
0.84 |
hlo_ffi / IDefOpt / cuda / PreRev |
0.000002048 s |
0.0000024 s |
0.85 |
hlo_ffi / IDefOpt / cuda / PostRev |
0.000002047 s |
0.000002431 s |
0.84 |
hlo_ffi / IDefOpt / cuda / BothRev |
0.000002049 s |
0.0000024 s |
0.85 |
hlo_ffi / JaXPipe / cpu / Primal |
0.000022094 s |
0.00001034003998938715 s |
2.14 |
hlo_ffi / Jax / cpu / Primal |
0.00002177 s |
0.000009985020033127513 s |
2.18 |
hlo_ffi / HLOOpt / cpu / Primal |
0.000021732 s |
0.000009755440023582196 s |
2.23 |
hlo_ffi / PartOpt / cpu / Primal |
0.000021493 s |
0.000009405199953107512 s |
2.29 |
hlo_ffi / IPartOpt / cpu / Primal |
0.0000219 s |
0.00000985210000180814 s |
2.22 |
hlo_ffi / DefOpt / cpu / Primal |
0.000021762 s |
0.00000947170000472397 s |
2.30 |
hlo_ffi / IDefOpt / cpu / Primal |
0.000021677 s |
0.000010050320024674877 s |
2.16 |
hlo_ffi / JaXPipe / cpu / Forward |
0.000029779 s |
0.000014069779990677488 s |
2.12 |
hlo_ffi / Jax / cpu / Forward |
0.000028941000000000003 s |
0.000013719179996769526 s |
2.11 |
hlo_ffi / HLOOpt / cpu / Forward |
0.000029501 s |
0.000013785899946014978 s |
2.14 |
hlo_ffi / PartOpt / cpu / Forward |
0.000029842 s |
0.000013894799985791906 s |
2.15 |
hlo_ffi / IPartOpt / cpu / Forward |
0.000029312 s |
0.000013855580018571343 s |
2.12 |
hlo_ffi / DefOpt / cpu / Forward |
0.00002909 s |
0.000014091939965510391 s |
2.06 |
hlo_ffi / IDefOpt / cpu / Forward |
0.000028834 s |
0.000013815360034641344 s |
2.09 |
hlo_ffi / JaXPipe / cpu / PreRev |
0.000030720000000000004 s |
0.00001372190001347917 s |
2.24 |
hlo_ffi / JaXPipe / cpu / PostRev |
0.000028937 s |
0.00001410404000125709 s |
2.05 |
hlo_ffi / JaXPipe / cpu / BothRev |
0.000029104 s |
0.00001385939998726826 s |
2.10 |
hlo_ffi / Jax / cpu / BothRev |
0.000029183 s |
0.00001422051998815732 s |
2.05 |
hlo_ffi / HLOOpt / cpu / PreRev |
0.000029522 s |
0.000014327220023915288 s |
2.06 |
hlo_ffi / HLOOpt / cpu / PostRev |
0.000029574 s |
0.00001546456001960905 s |
1.91 |
hlo_ffi / HLOOpt / cpu / BothRev |
0.000028877 s |
0.000013411179988906951 s |
2.15 |
hlo_ffi / PartOpt / cpu / PreRev |
0.000029324 s |
0.000013805800017507864 s |
2.12 |
hlo_ffi / PartOpt / cpu / PostRev |
0.000029225 s |
0.000013704339999094372 s |
2.13 |
hlo_ffi / PartOpt / cpu / BothRev |
0.000029181 s |
0.000014091119965087271 s |
2.07 |
hlo_ffi / IPartOpt / cpu / PreRev |
0.000029487 s |
0.000013858420024916996 s |
2.13 |
hlo_ffi / IPartOpt / cpu / PostRev |
0.00002922 s |
0.000013587200028268851 s |
2.15 |
hlo_ffi / IPartOpt / cpu / BothRev |
0.000028648 s |
0.00001375443998767878 s |
2.08 |
hlo_ffi / DefOpt / cpu / PreRev |
0.000028758 s |
0.000014191280033628573 s |
2.03 |
hlo_ffi / DefOpt / cpu / PostRev |
0.000029759 s |
0.000013898340012019616 s |
2.14 |
hlo_ffi / DefOpt / cpu / BothRev |
0.000029471 s |
0.000013873600018996512 s |
2.12 |
hlo_ffi / IDefOpt / cpu / PreRev |
0.000029344 s |
0.000014398280000023078 s |
2.04 |
hlo_ffi / IDefOpt / cpu / PostRev |
0.000029296 s |
0.000013474280058289878 s |
2.17 |
hlo_ffi / IDefOpt / cpu / BothRev |
0.000029921 s |
0.000013760899964836426 s |
2.17 |
hlo_ffi / JaXPipe / cpu / Primal |
0.000012 s |
0.00001034003998938715 s |
1.16 |
hlo_ffi / Jax / cpu / Primal |
0.000012 s |
0.000009985020033127513 s |
1.20 |
hlo_ffi / HLOOpt / cpu / Primal |
0.000013 s |
0.000009755440023582196 s |
1.33 |
hlo_ffi / PartOpt / cpu / Primal |
0.000013 s |
0.000009405199953107512 s |
1.38 |
hlo_ffi / IPartOpt / cpu / Primal |
0.000012 s |
0.00000985210000180814 s |
1.22 |
hlo_ffi / DefOpt / cpu / Primal |
0.000012 s |
0.00000947170000472397 s |
1.27 |
hlo_ffi / IDefOpt / cpu / Primal |
0.000013 s |
0.000010050320024674877 s |
1.29 |
hlo_ffi / JaXPipe / cpu / Forward |
0.000017999999999999997 s |
0.000014069779990677488 s |
1.28 |
hlo_ffi / Jax / cpu / Forward |
0.000017 s |
0.000013719179996769526 s |
1.24 |
hlo_ffi / HLOOpt / cpu / Forward |
0.000017999999999999997 s |
0.000013785899946014978 s |
1.31 |
hlo_ffi / PartOpt / cpu / Forward |
0.000016 s |
0.000013894799985791906 s |
1.15 |
hlo_ffi / IPartOpt / cpu / Forward |
0.000017 s |
0.000013855580018571343 s |
1.23 |
hlo_ffi / DefOpt / cpu / Forward |
0.000016 s |
0.000014091939965510391 s |
1.14 |
hlo_ffi / IDefOpt / cpu / Forward |
0.000016 s |
0.000013815360034641344 s |
1.16 |
hlo_ffi / JaXPipe / cpu / PreRev |
0.000017 s |
0.00001372190001347917 s |
1.24 |
hlo_ffi / JaXPipe / cpu / PostRev |
0.000017 s |
0.00001410404000125709 s |
1.21 |
hlo_ffi / JaXPipe / cpu / BothRev |
0.000017999999999999997 s |
0.00001385939998726826 s |
1.30 |
hlo_ffi / Jax / cpu / BothRev |
0.000016 s |
0.00001422051998815732 s |
1.13 |
hlo_ffi / HLOOpt / cpu / PreRev |
0.000017 s |
0.000014327220023915288 s |
1.19 |
hlo_ffi / HLOOpt / cpu / PostRev |
0.000016 s |
0.00001546456001960905 s |
1.03 |
hlo_ffi / HLOOpt / cpu / BothRev |
0.000017 s |
0.000013411179988906951 s |
1.27 |
hlo_ffi / PartOpt / cpu / PreRev |
0.000017 s |
0.000013805800017507864 s |
1.23 |
hlo_ffi / PartOpt / cpu / PostRev |
0.000017999999999999997 s |
0.000013704339999094372 s |
1.31 |
hlo_ffi / PartOpt / cpu / BothRev |
0.000016 s |
0.000014091119965087271 s |
1.14 |
hlo_ffi / IPartOpt / cpu / PreRev |
0.000016 s |
0.000013858420024916996 s |
1.15 |
hlo_ffi / IPartOpt / cpu / PostRev |
0.000017999999999999997 s |
0.000013587200028268851 s |
1.32 |
hlo_ffi / IPartOpt / cpu / BothRev |
0.000017 s |
0.00001375443998767878 s |
1.24 |
hlo_ffi / DefOpt / cpu / PreRev |
0.000017 s |
0.000014191280033628573 s |
1.20 |
hlo_ffi / DefOpt / cpu / PostRev |
0.000017999999999999997 s |
0.000013898340012019616 s |
1.30 |
hlo_ffi / DefOpt / cpu / BothRev |
0.000017999999999999997 s |
0.000013873600018996512 s |
1.30 |
hlo_ffi / IDefOpt / cpu / PreRev |
0.000017 s |
0.000014398280000023078 s |
1.18 |
hlo_ffi / IDefOpt / cpu / PostRev |
0.000017999999999999997 s |
0.000013474280058289878 s |
1.34 |
hlo_ffi / IDefOpt / cpu / BothRev |
0.000017 s |
0.000013760899964836426 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 / JaXPipe / cpu / Primal |
0.0009273859999666 s |
0.0009229465998942 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 |
0.0009706219999316 s |
0.0009119990000726 s |
1.06 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / Primal |
0.0011074124000515 s |
0.0009864477999144 s |
1.12 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / Primal |
0.0009495127998889 s |
0.000910505199954 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / Primal |
0.0009582693999618 s |
0.0009079460000066 s |
1.06 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / Primal |
0.0010921891999714 s |
0.000968284999908 s |
1.13 |
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 |
0.0010247340000205 s |
0.0009673217999079 s |
1.06 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / Forward |
0.0022640104000856 s |
0.0022036135999769 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 / Jax / cpu / Forward |
0.0024008147999666 s |
0.002319625400014 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / Forward |
0.0023431599999639 s |
0.0023093662000974 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 / cpu / Forward |
0.0023479276000216 s |
0.002246114600075 s |
1.05 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / Forward |
0.0023397281999677 s |
0.0022535512000104 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / Forward |
0.0023795155999323 s |
0.0022791456000049 s |
1.04 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / Forward |
0.002403184600007 s |
0.0022178986001563 s |
1.08 |
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 |
0.0047994137999921 s |
0.0053250911999384 s |
0.90 |
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 |
0.0074123698000221 s |
0.006841429799897 s |
1.08 |
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 |
0.0064801378000993 s |
0.0050563927999974 s |
1.28 |
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 |
0.0058879400001387 s |
0.003611056200043 s |
1.63 |
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 |
0.0063722793999659 s |
0.0039472775999456 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 / HLOOpt / cpu / PostRev |
0.0058287695999752 s |
0.0034661294000216 s |
1.68 |
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 |
0.0065286275999824 s |
0.0039695853999546 s |
1.64 |
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 |
0.0060593400002289 s |
0.0036196867999933 s |
1.67 |
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 |
0.0066648701999838 s |
0.0054723276000913 s |
1.22 |
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 |
0.0059148293998987 s |
0.0036316738000095 s |
1.63 |
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 |
0.0063839675999588 s |
0.0039416476000951 s |
1.62 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / PostRev |
0.0037342372000239 s |
0.0036786910000046 s |
1.02 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / BothRev |
0.0062646737999784 s |
0.0040019157999267 s |
1.57 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / PreRev |
0.0036747080000168 s |
0.003655396799968 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 / DefOpt / cpu / PostRev |
0.0060792082001171 s |
0.0051918388001467 s |
1.17 |
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 |
0.0036439008000343 s |
0.0036631044000387 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 / IDefOpt / cpu / PreRev |
0.0064476069999727 s |
0.0039127513999119 s |
1.65 |
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 |
0.0061106655999537 s |
0.0035613681999166 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 / IDefOpt / cpu / BothRev |
0.0065615644000899 s |
0.0039233681999576 s |
1.67 |
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 |
0.000282143 s |
0.000294909 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 / Jax / cuda / Primal |
0.000280864 s |
0.000296094 s |
0.95 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cuda / Primal |
0.000288032 s |
0.000301917 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 / PartOpt / cuda / Primal |
0.00028032 s |
0.000295934 s |
0.95 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cuda / Primal |
0.000280383 s |
0.000295262 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 / DefOpt / cuda / Primal |
0.000288736 s |
0.000303229 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 / IDefOpt / cuda / Primal |
0.000289184 s |
0.000301214 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 / JaXPipe / cuda / Forward |
0.000559007 s |
0.000582395 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 / Jax / cuda / Forward |
0.000539455 s |
0.000566299 s |
0.95 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cuda / Forward |
0.000558687 s |
0.000582876 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 / PartOpt / cuda / Forward |
0.000558334 s |
0.000582684 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 / IPartOpt / cuda / Forward |
0.000557919 s |
0.000581371 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 / cuda / Forward |
0.000557599 s |
0.000582492 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 / cuda / Forward |
0.000558751 s |
0.000582396 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 / JaXPipe / cuda / PreRev |
0.001028702 s |
0.001050295 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 / cuda / PostRev |
0.000986846 s |
0.001012952 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 / JaXPipe / cuda / BothRev |
0.001023326 s |
0.001050488 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 / Jax / cuda / BothRev |
0.000990686 s |
0.001005304 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 / PreRev |
0.001012254 s |
0.001037496 s |
0.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cuda / PostRev |
0.00104003 s |
0.001060185 s |
0.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cuda / BothRev |
0.00101315 s |
0.001039449 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 / PartOpt / cuda / PreRev |
0.001028862 s |
0.001046776 s |
0.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cuda / PostRev |
0.0009785899999999 s |
0.000999065 s |
0.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cuda / BothRev |
0.001027806 s |
0.001049976 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 / cuda / PreRev |
0.001027902 s |
0.001048824 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 / cuda / PostRev |
0.000977438 s |
0.000998905 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 / cuda / BothRev |
0.001028478 s |
0.001050392 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 / DefOpt / cuda / PreRev |
0.0010243169999999 s |
0.001051288 s |
0.97 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cuda / PostRev |
0.000962334 s |
0.000986041 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 / DefOpt / cuda / BothRev |
0.001026813 s |
0.0010518959999999 s |
0.98 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cuda / PreRev |
0.001023358 s |
0.00105228 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 / IDefOpt / cuda / PostRev |
0.001023678 s |
0.00105532 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 / IDefOpt / cuda / BothRev |
0.001024191 s |
0.0010518 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 / JaXPipe / cpu / Primal |
0.003362661 s |
0.0009229465998942 s |
3.64 |
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 |
0.003279186 s |
0.0009119990000726 s |
3.60 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / HLOOpt / cpu / Primal |
0.003260833 s |
0.0009864477999144 s |
3.31 |
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 |
0.003235415 s |
0.000910505199954 s |
3.55 |
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 |
0.003051283 s |
0.0009079460000066 s |
3.36 |
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 |
0.003591194 s |
0.000968284999908 s |
3.71 |
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 |
0.003498412 s |
0.0009673217999079 s |
3.62 |
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 |
0.007712724 s |
0.0022036135999769 s |
3.50 |
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 |
0.0076308559999999 s |
0.002319625400014 s |
3.29 |
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 |
0.0077180569999999 s |
0.0023093662000974 s |
3.34 |
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 |
0.008106907 s |
0.002246114600075 s |
3.61 |
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 |
0.007428345 s |
0.0022535512000104 s |
3.30 |
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 |
0.00790386 s |
0.0022791456000049 s |
3.47 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / Forward |
0.0077495279999999 s |
0.0022178986001563 s |
3.49 |
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 |
0.013501572 s |
0.0053250911999384 s |
2.54 |
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 |
0.012703642 s |
0.006841429799897 s |
1.86 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / BothRev |
0.011327017 s |
0.0050563927999974 s |
2.24 |
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 |
0.011805541 s |
0.003611056200043 s |
3.27 |
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 |
0.011613656 s |
0.0039472775999456 s |
2.94 |
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 |
0.011593199 s |
0.0034661294000216 s |
3.34 |
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 |
0.0108864269999999 s |
0.0039695853999546 s |
2.74 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / PreRev |
0.011494437 s |
0.0036196867999933 s |
3.18 |
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 |
0.011443002 s |
0.0054723276000913 s |
2.09 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / PartOpt / cpu / BothRev |
0.012536304 s |
0.0036316738000095 s |
3.45 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IPartOpt / cpu / PreRev |
0.012335336 s |
0.0039416476000951 s |
3.13 |
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 |
0.012828929 s |
0.0036786910000046 s |
3.49 |
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 |
0.010943121 s |
0.0040019157999267 s |
2.73 |
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 |
0.011207761 s |
0.003655396799968 s |
3.07 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / DefOpt / cpu / PostRev |
0.010366711 s |
0.0051918388001467 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 / DefOpt / cpu / BothRev |
0.011863737 s |
0.0036631044000387 s |
3.24 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / PreRev |
0.011272592 s |
0.0039127513999119 s |
2.88 |
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 |
0.0117375439999999 s |
0.0035613681999166 s |
3.30 |
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 |
0.011315218 s |
0.0039233681999576 s |
2.88 |
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 |
0.001836 s |
0.0009229465998942 s |
1.99 |
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 |
0.001728 s |
0.0009119990000726 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 / HLOOpt / cpu / Primal |
0.0017569999999999 s |
0.0009864477999144 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 / PartOpt / cpu / Primal |
0.001616 s |
0.000910505199954 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 / Primal |
0.001694 s |
0.0009079460000066 s |
1.87 |
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 |
0.001703 s |
0.000968284999908 s |
1.76 |
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 |
0.001787 s |
0.0009673217999079 s |
1.85 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / Forward |
0.0043879999999999 s |
0.0022036135999769 s |
1.99 |
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 |
0.00462 s |
0.002319625400014 s |
1.99 |
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 |
0.004523 s |
0.0023093662000974 s |
1.96 |
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 |
0.004293 s |
0.002246114600075 s |
1.91 |
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 |
0.004483 s |
0.0022535512000104 s |
1.99 |
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 |
0.0047539999999999 s |
0.0022791456000049 s |
2.09 |
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 |
0.004501 s |
0.0022178986001563 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 / PreRev |
0.007839 s |
0.0053250911999384 s |
1.47 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / JaXPipe / cpu / PostRev |
0.011437 s |
0.006841429799897 s |
1.67 |
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 |
0.008211 s |
0.0050563927999974 s |
1.62 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / Jax / cpu / BothRev |
0.011253 s |
0.003611056200043 s |
3.12 |
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 |
0.007911 s |
0.0039472775999456 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 / HLOOpt / cpu / PostRev |
0.006957 s |
0.0034661294000216 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 / HLOOpt / cpu / BothRev |
0.007993 s |
0.0039695853999546 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 / PartOpt / cpu / PreRev |
0.008024 s |
0.0036196867999933 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 / PartOpt / cpu / PostRev |
0.008816 s |
0.0054723276000913 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 / PartOpt / cpu / BothRev |
0.007626 s |
0.0036316738000095 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 / IPartOpt / cpu / PreRev |
0.0076619999999999 s |
0.0039416476000951 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 / IPartOpt / cpu / PostRev |
0.0099589999999999 s |
0.0036786910000046 s |
2.71 |
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 |
0.007945 s |
0.0040019157999267 s |
1.99 |
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 |
0.007876 s |
0.003655396799968 s |
2.15 |
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 |
0.0075 s |
0.0051918388001467 s |
1.44 |
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 |
0.008123 s |
0.0036631044000387 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 / IDefOpt / cpu / PreRev |
0.007935 s |
0.0039127513999119 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 / IDefOpt / cpu / PostRev |
0.008779 s |
0.0035613681999166 s |
2.47 |
llama_dim_288_hidden_dim_768_n_layers_6_n_heads_6_n_kv_heads_6_vocab_size_32000_seq_len_256 / IDefOpt / cpu / BothRev |
0.007837 s |
0.0039233681999576 s |
2.00 |
scatter_sum / JaXPipe / cpu / Primal |
0.00000854826001159381 s |
0.000007293080025192467 s |
1.17 |
scatter_sum / Jax / cpu / Primal |
0.000009777659970495734 s |
0.000007368420028797118 s |
1.33 |
scatter_sum / HLOOpt / cpu / Primal |
0.000009618560015951516 s |
0.000007614999994984828 s |
1.26 |
scatter_sum / PartOpt / cpu / Primal |
0.000009392419970026822 s |
0.000007398499983537476 s |
1.27 |
scatter_sum / IPartOpt / cpu / Primal |
0.000009554020007271902 s |
0.00000839928000459622 s |
1.14 |
scatter_sum / DefOpt / cpu / Primal |
0.000009214919973601354 s |
0.00000760586000069452 s |
1.21 |
scatter_sum / IDefOpt / cpu / Primal |
0.000008909699990908848 s |
0.000007895500002632617 s |
1.13 |
scatter_sum / JaXPipe / cpu / Forward |
0.000012803000008716482 s |
0.000011051000001316424 s |
1.16 |
scatter_sum / Jax / cpu / Forward |
0.000012527980034064968 s |
0.000011056919956899949 s |
1.13 |
scatter_sum / HLOOpt / cpu / Forward |
0.000012888320015917998 s |
0.000011551779998626443 s |
1.12 |
scatter_sum / PartOpt / cpu / Forward |
0.000013123299977451095 s |
0.0000112276599429606 s |
1.17 |
scatter_sum / IPartOpt / cpu / Forward |
0.000013046359936197404 s |
0.000012088699995729258 s |
1.08 |
scatter_sum / DefOpt / cpu / Forward |
0.000012670119995163986 s |
0.000011231580010644392 s |
1.13 |
scatter_sum / IDefOpt / cpu / Forward |
0.00001270444001420401 s |
0.000011144800018882962 s |
1.14 |
scatter_sum / JaXPipe / cpu / PreRev |
0.00001348696000604832 s |
0.000011565399991013691 s |
1.17 |
scatter_sum / JaXPipe / cpu / PostRev |
0.000012847220050389296 s |
0.000011652520015559276 s |
1.10 |
scatter_sum / JaXPipe / cpu / BothRev |
0.000013316939975993593 s |
0.000012168000021119953 s |
1.09 |
scatter_sum / Jax / cpu / BothRev |
0.00001300185999753012 s |
0.000011563099978957326 s |
1.12 |
scatter_sum / HLOOpt / cpu / PreRev |
0.000013202240015743884 s |
0.000011992620029559475 s |
1.10 |
scatter_sum / HLOOpt / cpu / PostRev |
0.000015387239973279065 s |
0.00001322634002463019 s |
1.16 |
scatter_sum / HLOOpt / cpu / BothRev |
0.00001257035997696221 s |
0.000011021819973393577 s |
1.14 |
scatter_sum / PartOpt / cpu / PreRev |
0.000013365859995246864 s |
0.000011223419969610404 s |
1.19 |
scatter_sum / PartOpt / cpu / PostRev |
0.000013373980027608923 s |
0.0000114243200096098 s |
1.17 |
scatter_sum / PartOpt / cpu / BothRev |
0.0000127674599934835 s |
0.000011949159988944302 s |
1.07 |
scatter_sum / IPartOpt / cpu / PreRev |
0.00001254196003174002 s |
0.000011477380021460704 s |
1.09 |
scatter_sum / IPartOpt / cpu / PostRev |
0.000012499079984991112 s |
0.000011408740001570547 s |
1.10 |
scatter_sum / IPartOpt / cpu / BothRev |
0.000012673539986280956 s |
0.000011129459999210668 s |
1.14 |
scatter_sum / DefOpt / cpu / PreRev |
0.000012270660017748012 s |
0.00001116801998250594 s |
1.10 |
scatter_sum / DefOpt / cpu / PostRev |
0.00001271709999855375 s |
0.000011219919979339466 s |
1.13 |
scatter_sum / DefOpt / cpu / BothRev |
0.00001294224000048416 s |
0.000011300279984425288 s |
1.15 |
scatter_sum / IDefOpt / cpu / PreRev |
0.000012876220016551088 s |
0.000011794680040111416 s |
1.09 |
scatter_sum / IDefOpt / cpu / PostRev |
0.000012888500023109372 s |
0.000011621759967965771 s |
1.11 |
scatter_sum / IDefOpt / cpu / BothRev |
0.00001329422001617786 s |
0.00001147384000432794 s |
1.16 |
scatter_sum / JaXPipe / cuda / Primal |
0.000014432 s |
0.00001056 s |
1.37 |
scatter_sum / Jax / cuda / Primal |
0.000010208 s |
0.000010464 s |
0.98 |
scatter_sum / HLOOpt / cuda / Primal |
0.000010208 s |
0.000011136 s |
0.92 |
scatter_sum / PartOpt / cuda / Primal |
0.000009984 s |
0.000010305 s |
0.97 |
scatter_sum / IPartOpt / cuda / Primal |
0.000011520000000000002 s |
0.000010592 s |
1.09 |
scatter_sum / DefOpt / cuda / Primal |
0.000011455999999999998 s |
0.000010272 s |
1.12 |
scatter_sum / IDefOpt / cuda / Primal |
0.000010432 s |
0.0000104 s |
1.00 |
scatter_sum / JaXPipe / cuda / Forward |
0.000017152 s |
0.0000176 s |
0.97 |
scatter_sum / Jax / cuda / Forward |
0.000018976 s |
0.000017792 s |
1.07 |
scatter_sum / HLOOpt / cuda / Forward |
0.000019616 s |
0.000017856 s |
1.10 |
scatter_sum / PartOpt / cuda / Forward |
0.000017760000000000003 s |
0.000017919000000000002 s |
0.99 |
scatter_sum / IPartOpt / cuda / Forward |
0.000017855 s |
0.000017728 s |
1.01 |
scatter_sum / DefOpt / cuda / Forward |
0.000017503 s |
0.0000176 s |
0.99 |
scatter_sum / IDefOpt / cuda / Forward |
0.000017536 s |
0.000017664 s |
0.99 |
scatter_sum / JaXPipe / cuda / PreRev |
0.00001744 s |
0.000017375999999999998 s |
1.00 |
scatter_sum / JaXPipe / cuda / PostRev |
0.00001728 s |
0.000016736 s |
1.03 |
scatter_sum / JaXPipe / cuda / BothRev |
0.000016927000000000002 s |
0.000017760000000000003 s |
0.95 |
scatter_sum / Jax / cuda / BothRev |
0.00001728 s |
0.000017568000000000002 s |
0.98 |
scatter_sum / HLOOpt / cuda / PreRev |
0.000017472 s |
0.00001712 s |
1.02 |
scatter_sum / HLOOpt / cuda / PostRev |
0.000017632 s |
0.000017375999999999998 s |
1.01 |
scatter_sum / HLOOpt / cuda / BothRev |
0.000017184 s |
0.00001728 s |
0.99 |
scatter_sum / PartOpt / cuda / PreRev |
0.000017632 s |
0.000017247999999999998 s |
1.02 |
scatter_sum / PartOpt / cuda / PostRev |
0.000017408 s |
0.00001744 s |
1.00 |
scatter_sum / PartOpt / cuda / BothRev |
0.000017505 s |
0.000017408 s |
1.01 |
scatter_sum / IPartOpt / cuda / PreRev |
0.000017247999999999998 s |
0.000017536 s |
0.98 |
scatter_sum / IPartOpt / cuda / PostRev |
0.000016992 s |
0.000017247 s |
0.99 |
scatter_sum / IPartOpt / cuda / BothRev |
0.000017311 s |
0.000017216 s |
1.01 |
scatter_sum / DefOpt / cuda / PreRev |
0.000017312 s |
0.000018016 s |
0.96 |
scatter_sum / DefOpt / cuda / PostRev |
0.000017088 s |
0.000017728 s |
0.96 |
scatter_sum / DefOpt / cuda / BothRev |
0.000016896000000000002 s |
0.00001808 s |
0.93 |
scatter_sum / IDefOpt / cuda / PreRev |
0.000017313 s |
0.000017984 s |
0.96 |
scatter_sum / IDefOpt / cuda / PostRev |
0.000016768000000000003 s |
0.000017503999999999997 s |
0.96 |
scatter_sum / IDefOpt / cuda / BothRev |
0.000017216 s |
0.000017408 s |
0.99 |
scatter_sum / JaXPipe / cpu / Primal |
0.000019687 s |
0.000007293080025192467 s |
2.70 |
scatter_sum / Jax / cpu / Primal |
0.000019655 s |
0.000007368420028797118 s |
2.67 |
scatter_sum / HLOOpt / cpu / Primal |
0.000018872 s |
0.000007614999994984828 s |
2.48 |
scatter_sum / PartOpt / cpu / Primal |
0.000019664 s |
0.000007398499983537476 s |
2.66 |
scatter_sum / IPartOpt / cpu / Primal |
0.000020345 s |
0.00000839928000459622 s |
2.42 |
scatter_sum / DefOpt / cpu / Primal |
0.000019579 s |
0.00000760586000069452 s |
2.57 |
scatter_sum / IDefOpt / cpu / Primal |
0.000019726 s |
0.000007895500002632617 s |
2.50 |
scatter_sum / JaXPipe / cpu / Forward |
0.000028248 s |
0.000011051000001316424 s |
2.56 |
scatter_sum / Jax / cpu / Forward |
0.000028006 s |
0.000011056919956899949 s |
2.53 |
scatter_sum / HLOOpt / cpu / Forward |
0.000029069 s |
0.000011551779998626443 s |
2.52 |
scatter_sum / PartOpt / cpu / Forward |
0.000027023 s |
0.0000112276599429606 s |
2.41 |
scatter_sum / IPartOpt / cpu / Forward |
0.000028034 s |
0.000012088699995729258 s |
2.32 |
scatter_sum / DefOpt / cpu / Forward |
0.000028627 s |
0.000011231580010644392 s |
2.55 |
scatter_sum / IDefOpt / cpu / Forward |
0.000028502 s |
0.000011144800018882962 s |
2.56 |
scatter_sum / JaXPipe / cpu / PreRev |
0.000029416 s |
0.000011565399991013691 s |
2.54 |
scatter_sum / JaXPipe / cpu / PostRev |
0.00002814 s |
0.000011652520015559276 s |
2.41 |
scatter_sum / JaXPipe / cpu / BothRev |
0.000028517 s |
0.000012168000021119953 s |
2.34 |
scatter_sum / Jax / cpu / BothRev |
0.000028502 s |
0.000011563099978957326 s |
2.46 |
scatter_sum / HLOOpt / cpu / PreRev |
0.00002866 s |
0.000011992620029559475 s |
2.39 |
scatter_sum / HLOOpt / cpu / PostRev |
0.000028129 s |
0.00001322634002463019 s |
2.13 |
scatter_sum / HLOOpt / cpu / BothRev |
0.00002834 s |
0.000011021819973393577 s |
2.57 |
scatter_sum / PartOpt / cpu / PreRev |
0.000028683 s |
0.000011223419969610404 s |
2.56 |
scatter_sum / PartOpt / cpu / PostRev |
0.000028604000000000003 s |
0.0000114243200096098 s |
2.50 |
scatter_sum / PartOpt / cpu / BothRev |
0.000028685 s |
0.000011949159988944302 s |
2.40 |
scatter_sum / IPartOpt / cpu / PreRev |
0.000029073 s |
0.000011477380021460704 s |
2.53 |
scatter_sum / IPartOpt / cpu / PostRev |
0.000028015 s |
0.000011408740001570547 s |
2.46 |
scatter_sum / IPartOpt / cpu / BothRev |
0.000028062 s |
0.000011129459999210668 s |
2.52 |
scatter_sum / DefOpt / cpu / PreRev |
0.0000289 s |
0.00001116801998250594 s |
2.59 |
scatter_sum / DefOpt / cpu / PostRev |
0.00002846 s |
0.000011219919979339466 s |
2.54 |
scatter_sum / DefOpt / cpu / BothRev |
0.000027613 s |
0.000011300279984425288 s |
2.44 |
scatter_sum / IDefOpt / cpu / PreRev |
0.000028301 s |
0.000011794680040111416 s |
2.40 |
scatter_sum / IDefOpt / cpu / PostRev |
0.000028158 s |
0.000011621759967965771 s |
2.42 |
scatter_sum / IDefOpt / cpu / BothRev |
0.000028087 s |
0.00001147384000432794 s |
2.45 |
scatter_sum / JaXPipe / cpu / Primal |
0.000011 s |
0.000007293080025192467 s |
1.51 |
scatter_sum / Jax / cpu / Primal |
0.00001 s |
0.000007368420028797118 s |
1.36 |
scatter_sum / HLOOpt / cpu / Primal |
0.000011 s |
0.000007614999994984828 s |
1.44 |
scatter_sum / PartOpt / cpu / Primal |
0.00001 s |
0.000007398499983537476 s |
1.35 |
scatter_sum / IPartOpt / cpu / Primal |
0.000011 s |
0.00000839928000459622 s |
1.31 |
scatter_sum / DefOpt / cpu / Primal |
0.000011 s |
0.00000760586000069452 s |
1.45 |
scatter_sum / IDefOpt / cpu / Primal |
0.00001 s |
0.000007895500002632617 s |
1.27 |
scatter_sum / JaXPipe / cpu / Forward |
0.000015 s |
0.000011051000001316424 s |
1.36 |
scatter_sum / Jax / cpu / Forward |
0.000017 s |
0.000011056919956899949 s |
1.54 |
scatter_sum / HLOOpt / cpu / Forward |
0.000015 s |
0.000011551779998626443 s |
1.30 |
scatter_sum / PartOpt / cpu / Forward |
0.000015 s |
0.0000112276599429606 s |
1.34 |
scatter_sum / IPartOpt / cpu / Forward |
0.000015 s |
0.000012088699995729258 s |
1.24 |
scatter_sum / DefOpt / cpu / Forward |
0.000016 s |
0.000011231580010644392 s |
1.42 |
scatter_sum / IDefOpt / cpu / Forward |
0.000016 s |
0.000011144800018882962 s |
1.44 |
scatter_sum / JaXPipe / cpu / PreRev |
0.000015 s |
0.000011565399991013691 s |
1.30 |
scatter_sum / JaXPipe / cpu / PostRev |
0.000017 s |
0.000011652520015559276 s |
1.46 |
scatter_sum / JaXPipe / cpu / BothRev |
0.000016 s |
0.000012168000021119953 s |
1.31 |
scatter_sum / Jax / cpu / BothRev |
0.000016 s |
0.000011563099978957326 s |
1.38 |
scatter_sum / HLOOpt / cpu / PreRev |
0.000016 s |
0.000011992620029559475 s |
1.33 |
scatter_sum / HLOOpt / cpu / PostRev |
0.000016 s |
0.00001322634002463019 s |
1.21 |
scatter_sum / HLOOpt / cpu / BothRev |
0.000016 s |
0.000011021819973393577 s |
1.45 |
scatter_sum / PartOpt / cpu / PreRev |
0.000016 s |
0.000011223419969610404 s |
1.43 |
scatter_sum / PartOpt / cpu / PostRev |
0.000016 s |
0.0000114243200096098 s |
1.40 |
scatter_sum / PartOpt / cpu / BothRev |
0.000017 s |
0.000011949159988944302 s |
1.42 |
scatter_sum / IPartOpt / cpu / PreRev |
0.000016 s |
0.000011477380021460704 s |
1.39 |
scatter_sum / IPartOpt / cpu / PostRev |
0.000017 s |
0.000011408740001570547 s |
1.49 |
scatter_sum / IPartOpt / cpu / BothRev |
0.000016 s |
0.000011129459999210668 s |
1.44 |
scatter_sum / DefOpt / cpu / PreRev |
0.000016 s |
0.00001116801998250594 s |
1.43 |
scatter_sum / DefOpt / cpu / PostRev |
0.000017 s |
0.000011219919979339466 s |
1.52 |
scatter_sum / DefOpt / cpu / BothRev |
0.000016 s |
0.000011300279984425288 s |
1.42 |
scatter_sum / IDefOpt / cpu / PreRev |
0.000015 s |
0.000011794680040111416 s |
1.27 |
scatter_sum / IDefOpt / cpu / PostRev |
0.000016 s |
0.000011621759967965771 s |
1.38 |
scatter_sum / IDefOpt / cpu / BothRev |
0.000016 s |
0.00001147384000432794 s |
1.39 |
slicing / JaXPipe / cpu / Primal |
0.000007072680009514443 s |
0.000006105479969846783 s |
1.16 |
slicing / Jax / cpu / Primal |
0.000006875539993416169 s |
0.000006445079934565001 s |
1.07 |
slicing / HLOOpt / cpu / Primal |
0.000006939439972484252 s |
0.00000628132000201731 s |
1.10 |
slicing / PartOpt / cpu / Primal |
0.000006835779977336643 s |
0.000006503840004370431 s |
1.05 |
slicing / IPartOpt / cpu / Primal |
0.000006885220054755336 s |
0.0000062055800208327125 s |
1.11 |
slicing / DefOpt / cpu / Primal |
0.000007369079985437565 s |
0.000005963279991192394 s |
1.24 |
slicing / IDefOpt / cpu / Primal |
0.000006561360032719677 s |
0.000006107699982749182 s |
1.07 |
slicing / JaXPipe / cpu / Forward |
0.000010604539993437356 s |
0.000009115100056078518 s |
1.16 |
slicing / Jax / cpu / Forward |
0.000010815260002345895 s |
0.000009063039960892638 s |
1.19 |
slicing / HLOOpt / cpu / Forward |
0.000010827839987541666 s |
0.000009695840053609571 s |
1.12 |
slicing / PartOpt / cpu / Forward |
0.000010221399979855053 s |
0.000009678519982116995 s |
1.06 |
slicing / IPartOpt / cpu / Forward |
0.000010239699995509 s |
0.000009239900036845938 s |
1.11 |
slicing / DefOpt / cpu / Forward |
0.000010574199995971868 s |
0.000009654360001150051 s |
1.10 |
slicing / IDefOpt / cpu / Forward |
0.000010517159998926218 s |
0.000009053420035343151 s |
1.16 |
slicing / JaXPipe / cpu / PreRev |
0.00001092198001970246 s |
0.000009943859995473758 s |
1.10 |
slicing / JaXPipe / cpu / PostRev |
0.000011007100001734215 s |
0.000009751880015755888 s |
1.13 |
slicing / JaXPipe / cpu / BothRev |
0.000010583900011624792 s |
0.000010119999988091875 s |
1.05 |
slicing / Jax / cpu / BothRev |
0.000011150719992656376 s |
0.000009722339973450289 s |
1.15 |
slicing / HLOOpt / cpu / PreRev |
0.000011511659995449008 s |
0.000010054979975393508 s |
1.14 |
slicing / HLOOpt / cpu / PostRev |
0.00001309478001530806 s |
0.000011490859997138614 s |
1.14 |
slicing / HLOOpt / cpu / BothRev |
0.000010798079983942444 s |
0.000010083439983645805 s |
1.07 |
slicing / PartOpt / cpu / PreRev |
0.000010721339986048406 s |
0.000009542460002194276 s |
1.12 |
slicing / PartOpt / cpu / PostRev |
0.000011308099965390284 s |
0.000010058039961222676 s |
1.12 |
slicing / PartOpt / cpu / BothRev |
0.000011830819985334527 s |
0.000009834440006670775 s |
1.20 |
slicing / IPartOpt / cpu / PreRev |
0.000011211820019525476 s |
0.000009511259995633735 s |
1.18 |
slicing / IPartOpt / cpu / PostRev |
0.000011183899978277625 s |
0.000009962139984054376 s |
1.12 |
slicing / IPartOpt / cpu / BothRev |
0.00001071633997526078 s |
0.000009858120038188644 s |
1.09 |
slicing / DefOpt / cpu / PreRev |
0.0000108408799769677 s |
0.00000974007996774162 s |
1.11 |
slicing / DefOpt / cpu / PostRev |
0.00001123721996009408 s |
0.000009928380022756756 s |
1.13 |
slicing / DefOpt / cpu / BothRev |
0.000010833019987330772 s |
0.000009863400027825264 s |
1.10 |
slicing / IDefOpt / cpu / PreRev |
0.000011150459986311034 s |
0.000010070900007121964 s |
1.11 |
slicing / IDefOpt / cpu / PostRev |
0.000010810279982251813 s |
0.000010034859997176682 s |
1.08 |
slicing / IDefOpt / cpu / BothRev |
0.000010720560012487111 s |
0.000010459839986651786 s |
1.02 |
slicing / JaXPipe / cuda / Primal |
0.000001887 s |
0.000002271 s |
0.83 |
slicing / Jax / cuda / Primal |
0.000001887 s |
0.000002271 s |
0.83 |
slicing / HLOOpt / cuda / Primal |
0.000001887 s |
0.000002271 s |
0.83 |
slicing / PartOpt / cuda / Primal |
0.000001887 s |
0.000002271 s |
0.83 |
slicing / IPartOpt / cuda / Primal |
0.000001887 s |
0.000002271 s |
0.83 |
slicing / DefOpt / cuda / Primal |
0.000001887 s |
0.000002271 s |
0.83 |
slicing / IDefOpt / cuda / Primal |
0.000001888 s |
0.000002271 s |
0.83 |
slicing / JaXPipe / cuda / Forward |
0.00001008 s |
0.000010848 s |
0.93 |
slicing / Jax / cuda / Forward |
0.00001024 s |
0.000010816 s |
0.95 |
slicing / HLOOpt / cuda / Forward |
0.000011616 s |
0.000010944 s |
1.06 |
slicing / PartOpt / cuda / Forward |
0.000011424 s |
0.000010528 s |
1.09 |
slicing / IPartOpt / cuda / Forward |
0.000011264 s |
0.000010208 s |
1.10 |
slicing / DefOpt / cuda / Forward |
0.000011488 s |
0.00001296 s |
0.89 |
slicing / IDefOpt / cuda / Forward |
0.000010304 s |
0.000010527 s |
0.98 |
slicing / JaXPipe / cuda / PreRev |
0.000009952 s |
0.000010272 s |
0.97 |
slicing / JaXPipe / cuda / PostRev |
0.000010144 s |
0.000010496 s |
0.97 |
slicing / JaXPipe / cuda / BothRev |
0.000011904 s |
0.00001024 s |
1.16 |
slicing / Jax / cuda / BothRev |
0.000009984 s |
0.000010368 s |
0.96 |
slicing / HLOOpt / cuda / PreRev |
0.000010304 s |
0.000010368 s |
0.99 |
slicing / HLOOpt / cuda / PostRev |
0.00001024 s |
0.000010208 s |
1.00 |
slicing / HLOOpt / cuda / BothRev |
0.00000992 s |
0.000009856 s |
1.01 |
slicing / PartOpt / cuda / PreRev |
0.000011712 s |
0.000010272 s |
1.14 |
slicing / PartOpt / cuda / PostRev |
0.000011551 s |
0.000010176 s |
1.14 |
slicing / PartOpt / cuda / BothRev |
0.00001168 s |
0.000010176 s |
1.15 |
slicing / IPartOpt / cuda / PreRev |
0.000011616 s |
0.000010112 s |
1.15 |
slicing / IPartOpt / cuda / PostRev |
0.000010144 s |
0.000010433 s |
0.97 |
slicing / IPartOpt / cuda / BothRev |
0.00001008 s |
0.00001072 s |
0.94 |
slicing / DefOpt / cuda / PreRev |
0.000009632 s |
0.000010848 s |
0.89 |
slicing / DefOpt / cuda / PostRev |
0.000010016 s |
0.000010112 s |
0.99 |
slicing / DefOpt / cuda / BothRev |
0.000010208 s |
0.000010464 s |
0.98 |
slicing / IDefOpt / cuda / PreRev |
0.000010176 s |
0.00001024 s |
0.99 |
slicing / IDefOpt / cuda / PostRev |
0.000009952 s |
0.000010176 s |
0.98 |
slicing / IDefOpt / cuda / BothRev |
0.000009984 s |
0.000010432 s |
0.96 |
slicing / JaXPipe / cpu / Primal |
0.000016127 s |
0.000006105479969846783 s |
2.64 |
slicing / Jax / cpu / Primal |
0.000015798 s |
0.000006445079934565001 s |
2.45 |
slicing / HLOOpt / cpu / Primal |
0.000015833 s |
0.00000628132000201731 s |
2.52 |
slicing / PartOpt / cpu / Primal |
0.000015518999999999998 s |
0.000006503840004370431 s |
2.39 |
slicing / IPartOpt / cpu / Primal |
0.000015987 s |
0.0000062055800208327125 s |
2.58 |
slicing / DefOpt / cpu / Primal |
0.000015873000000000002 s |
0.000005963279991192394 s |
2.66 |
slicing / IDefOpt / cpu / Primal |
0.000015743 s |
0.000006107699982749182 s |
2.58 |
slicing / JaXPipe / cpu / Forward |
0.000021136 s |
0.000009115100056078518 s |
2.32 |
slicing / Jax / cpu / Forward |
0.000021326 s |
0.000009063039960892638 s |
2.35 |
slicing / HLOOpt / cpu / Forward |
0.000021211 s |
0.000009695840053609571 s |
2.19 |
slicing / PartOpt / cpu / Forward |
0.000021075 s |
0.000009678519982116995 s |
2.18 |
slicing / IPartOpt / cpu / Forward |
0.000020954 s |
0.000009239900036845938 s |
2.27 |
slicing / DefOpt / cpu / Forward |
0.000020715 s |
0.000009654360001150051 s |
2.15 |
slicing / IDefOpt / cpu / Forward |
0.000020762 s |
0.000009053420035343151 s |
2.29 |
slicing / JaXPipe / cpu / PreRev |
0.000022336 s |
0.000009943859995473758 s |
2.25 |
slicing / JaXPipe / cpu / PostRev |
0.000021524000000000003 s |
0.000009751880015755888 s |
2.21 |
slicing / JaXPipe / cpu / BothRev |
0.000021551 s |
0.000010119999988091875 s |
2.13 |
slicing / Jax / cpu / BothRev |
0.000021548 s |
0.000009722339973450289 s |
2.22 |
slicing / HLOOpt / cpu / PreRev |
0.00002195 s |
0.000010054979975393508 s |
2.18 |
slicing / HLOOpt / cpu / PostRev |
0.000021652 s |
0.000011490859997138614 s |
1.88 |
slicing / HLOOpt / cpu / BothRev |
0.000027274 s |
0.000010083439983645805 s |
2.70 |
slicing / PartOpt / cpu / PreRev |
0.000021248 s |
0.000009542460002194276 s |
2.23 |
slicing / PartOpt / cpu / PostRev |
0.00002125 s |
0.000010058039961222676 s |
2.11 |
slicing / PartOpt / cpu / BothRev |
0.000021711000000000003 s |
0.000009834440006670775 s |
2.21 |
slicing / IPartOpt / cpu / PreRev |
0.000021607 s |
0.000009511259995633735 s |
2.27 |
slicing / IPartOpt / cpu / PostRev |
0.00002173 s |
0.000009962139984054376 s |
2.18 |
slicing / IPartOpt / cpu / BothRev |
0.000021667 s |
0.000009858120038188644 s |
2.20 |
slicing / DefOpt / cpu / PreRev |
0.000022127 s |
0.00000974007996774162 s |
2.27 |
slicing / DefOpt / cpu / PostRev |
0.000021291 s |
0.000009928380022756756 s |
2.14 |
slicing / DefOpt / cpu / BothRev |
0.000021183 s |
0.000009863400027825264 s |
2.15 |
slicing / IDefOpt / cpu / PreRev |
0.000021505 s |
0.000010070900007121964 s |
2.14 |
slicing / IDefOpt / cpu / PostRev |
0.000021432 s |
0.000010034859997176682 s |
2.14 |
slicing / IDefOpt / cpu / BothRev |
0.000021705 s |
0.000010459839986651786 s |
2.08 |
slicing / JaXPipe / cpu / Primal |
0.000008 s |
0.000006105479969846783 s |
1.31 |
slicing / Jax / cpu / Primal |
0.000008 s |
0.000006445079934565001 s |
1.24 |
slicing / HLOOpt / cpu / Primal |
0.000008 s |
0.00000628132000201731 s |
1.27 |
slicing / PartOpt / cpu / Primal |
0.000008 s |
0.000006503840004370431 s |
1.23 |
slicing / IPartOpt / cpu / Primal |
0.000008 s |
0.0000062055800208327125 s |
1.29 |
slicing / DefOpt / cpu / Primal |
0.000008 s |
0.000005963279991192394 s |
1.34 |
slicing / IDefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000006107699982749182 s |
1.47 |
slicing / JaXPipe / cpu / Forward |
0.000011 s |
0.000009115100056078518 s |
1.21 |
slicing / Jax / cpu / Forward |
0.000012 s |
0.000009063039960892638 s |
1.32 |
slicing / HLOOpt / cpu / Forward |
0.000011 s |
0.000009695840053609571 s |
1.13 |
slicing / PartOpt / cpu / Forward |
0.000011 s |
0.000009678519982116995 s |
1.14 |
slicing / IPartOpt / cpu / Forward |
0.000012 s |
0.000009239900036845938 s |
1.30 |
slicing / DefOpt / cpu / Forward |
0.000012 s |
0.000009654360001150051 s |
1.24 |
slicing / IDefOpt / cpu / Forward |
0.000011 s |
0.000009053420035343151 s |
1.22 |
slicing / JaXPipe / cpu / PreRev |
0.000011 s |
0.000009943859995473758 s |
1.11 |
slicing / JaXPipe / cpu / PostRev |
0.000011 s |
0.000009751880015755888 s |
1.13 |
slicing / JaXPipe / cpu / BothRev |
0.000011 s |
0.000010119999988091875 s |
1.09 |
slicing / Jax / cpu / BothRev |
0.000011 s |
0.000009722339973450289 s |
1.13 |
slicing / HLOOpt / cpu / PreRev |
0.000012 s |
0.000010054979975393508 s |
1.19 |
slicing / HLOOpt / cpu / PostRev |
0.000012 s |
0.000011490859997138614 s |
1.04 |
slicing / HLOOpt / cpu / BothRev |
0.000011 s |
0.000010083439983645805 s |
1.09 |
slicing / PartOpt / cpu / PreRev |
0.000011 s |
0.000009542460002194276 s |
1.15 |
slicing / PartOpt / cpu / PostRev |
0.000012 s |
0.000010058039961222676 s |
1.19 |
slicing / PartOpt / cpu / BothRev |
0.000011 s |
0.000009834440006670775 s |
1.12 |
slicing / IPartOpt / cpu / PreRev |
0.000011 s |
0.000009511259995633735 s |
1.16 |
slicing / IPartOpt / cpu / PostRev |
0.000011 s |
0.000009962139984054376 s |
1.10 |
slicing / IPartOpt / cpu / BothRev |
0.000011 s |
0.000009858120038188644 s |
1.12 |
slicing / DefOpt / cpu / PreRev |
0.000011 s |
0.00000974007996774162 s |
1.13 |
slicing / DefOpt / cpu / PostRev |
0.000011 s |
0.000009928380022756756 s |
1.11 |
slicing / DefOpt / cpu / BothRev |
0.000011 s |
0.000009863400027825264 s |
1.12 |
slicing / IDefOpt / cpu / PreRev |
0.000011 s |
0.000010070900007121964 s |
1.09 |
slicing / IDefOpt / cpu / PostRev |
0.000013 s |
0.000010034859997176682 s |
1.30 |
slicing / IDefOpt / cpu / BothRev |
0.000012 s |
0.000010459839986651786 s |
1.15 |
sum / JaXPipe / cpu / Primal |
0.000008715359999769135 s |
0.0000073881599928427025 s |
1.18 |
sum / Jax / cpu / Primal |
0.000008151920001182589 s |
0.000007606680019307532 s |
1.07 |
sum / HLOOpt / cpu / Primal |
0.000008555880003768835 s |
0.000007699859970671241 s |
1.11 |
sum / PartOpt / cpu / Primal |
0.000008650040044813067 s |
0.00000777084002038464 s |
1.11 |
sum / IPartOpt / cpu / Primal |
0.000008798940007181954 s |
0.00000749566004742519 s |
1.17 |
sum / DefOpt / cpu / Primal |
0.000008418339984928024 s |
0.000007629619976796676 s |
1.10 |
sum / IDefOpt / cpu / Primal |
0.000008378480015380773 s |
0.000007243439986268641 s |
1.16 |
sum / JaXPipe / cpu / Forward |
0.000012536779995571124 s |
0.000011274139997112795 s |
1.11 |
sum / Jax / cpu / Forward |
0.000012656279986913432 s |
0.000010950659971058486 s |
1.16 |
sum / HLOOpt / cpu / Forward |
0.000012773319986081333 s |
0.000011121959987576702 s |
1.15 |
sum / PartOpt / cpu / Forward |
0.000012433999991117162 s |
0.000011287819997960469 s |
1.10 |
sum / IPartOpt / cpu / Forward |
0.000012751299982483033 s |
0.0000114213600045332 s |
1.12 |
sum / DefOpt / cpu / Forward |
0.000012822940007026772 s |
0.000011161999964315328 s |
1.15 |
sum / IDefOpt / cpu / Forward |
0.000012294300004214164 s |
0.000011449259982327933 s |
1.07 |
sum / JaXPipe / cpu / PreRev |
0.000012110420002500177 s |
0.000010970679995807589 s |
1.10 |
sum / JaXPipe / cpu / PostRev |
0.000012548359991342296 s |
0.000011371539985702838 s |
1.10 |
sum / JaXPipe / cpu / BothRev |
0.000012523639943538 s |
0.000011114360004285118 s |
1.13 |
sum / Jax / cpu / BothRev |
0.000011538140006450705 s |
0.000010417740004413644 s |
1.11 |
sum / HLOOpt / cpu / PreRev |
0.000012443179975889509 s |
0.000011315600022498985 s |
1.10 |
sum / HLOOpt / cpu / PostRev |
0.000014539679996232736 s |
0.00001315417999649071 s |
1.11 |
sum / HLOOpt / cpu / BothRev |
0.000012475919984353824 s |
0.000010805659994730375 s |
1.15 |
sum / PartOpt / cpu / PreRev |
0.000011450560023149592 s |
0.000010901019986704342 s |
1.05 |
sum / PartOpt / cpu / PostRev |
0.000012371379971227726 s |
0.00001103297999179631 s |
1.12 |
sum / PartOpt / cpu / BothRev |
0.000012325580000833724 s |
0.00001119064000704384 s |
1.10 |
sum / IPartOpt / cpu / PreRev |
0.0000117862199931551 s |
0.000011013659996024215 s |
1.07 |
sum / IPartOpt / cpu / PostRev |
0.000011925599983442223 s |
0.000011391500020181411 s |
1.05 |
sum / IPartOpt / cpu / BothRev |
0.000012248879993421724 s |
0.000010877200002141763 s |
1.13 |
sum / DefOpt / cpu / PreRev |
0.000011541199983184924 s |
0.000010321480012862591 s |
1.12 |
sum / DefOpt / cpu / PostRev |
0.0000125501800175698 s |
0.000010651199982021354 s |
1.18 |
sum / DefOpt / cpu / BothRev |
0.000012303919957048491 s |
0.00001095006002287846 s |
1.12 |
sum / IDefOpt / cpu / PreRev |
0.000011430859985921416 s |
0.000011108100034107338 s |
1.03 |
sum / IDefOpt / cpu / PostRev |
0.000012197559990454464 s |
0.000011055079985453633 s |
1.10 |
sum / IDefOpt / cpu / BothRev |
0.000012244700019437004 s |
0.000010697860016080086 s |
1.14 |
sum / JaXPipe / cuda / Primal |
0.000002047 s |
0.000002495 s |
0.82 |
sum / Jax / cuda / Primal |
0.000002048 s |
0.000002463 s |
0.83 |
sum / HLOOpt / cuda / Primal |
0.000002047 s |
0.000002464 s |
0.83 |
sum / PartOpt / cuda / Primal |
0.000002047 s |
0.000002465 s |
0.83 |
sum / IPartOpt / cuda / Primal |
0.000002047 s |
0.000002464 s |
0.83 |
sum / DefOpt / cuda / Primal |
0.000002048 s |
0.000002495 s |
0.82 |
sum / IDefOpt / cuda / Primal |
0.000002048 s |
0.000002464 s |
0.83 |
sum / JaXPipe / cuda / Forward |
0.000010208 s |
0.000010752 s |
0.95 |
sum / Jax / cuda / Forward |
0.000010529 s |
0.000010687 s |
0.99 |
sum / HLOOpt / cuda / Forward |
0.000010496 s |
0.000011072 s |
0.95 |
sum / PartOpt / cuda / Forward |
0.000010464 s |
0.000010624 s |
0.98 |
sum / IPartOpt / cuda / Forward |
0.000010496 s |
0.00001184 s |
0.89 |
sum / DefOpt / cuda / Forward |
0.000010144 s |
0.000010752 s |
0.94 |
sum / IDefOpt / cuda / Forward |
0.000009472 s |
0.000012256 s |
0.77 |
sum / JaXPipe / cuda / PreRev |
0.000010528 s |
0.000010208 s |
1.03 |
sum / JaXPipe / cuda / PostRev |
0.0000096 s |
0.000010176 s |
0.94 |
sum / JaXPipe / cuda / BothRev |
0.000010144 s |
0.00001024 s |
0.99 |
sum / Jax / cuda / BothRev |
0.000010176 s |
0.000010464 s |
0.97 |
sum / HLOOpt / cuda / PreRev |
0.000010048 s |
0.00001056 s |
0.95 |
sum / HLOOpt / cuda / PostRev |
0.00000992 s |
0.000010112 s |
0.98 |
sum / HLOOpt / cuda / BothRev |
0.000009888 s |
0.000010111 s |
0.98 |
sum / PartOpt / cuda / PreRev |
0.000010112 s |
0.000010016 s |
1.01 |
sum / PartOpt / cuda / PostRev |
0.000010208 s |
0.000010176 s |
1.00 |
sum / PartOpt / cuda / BothRev |
0.000009856 s |
0.00001024 s |
0.96 |
sum / IPartOpt / cuda / PreRev |
0.000009856 s |
0.000010496 s |
0.94 |
sum / IPartOpt / cuda / PostRev |
0.000010017 s |
0.000010784 s |
0.93 |
sum / IPartOpt / cuda / BothRev |
0.000009824 s |
0.000012031 s |
0.82 |
sum / DefOpt / cuda / PreRev |
0.000010112 s |
0.000010496 s |
0.96 |
sum / DefOpt / cuda / PostRev |
0.000010017 s |
0.000010113 s |
0.99 |
sum / DefOpt / cuda / BothRev |
0.000010176 s |
0.000012319 s |
0.83 |
sum / IDefOpt / cuda / PreRev |
0.000009888 s |
0.000010752 s |
0.92 |
sum / IDefOpt / cuda / PostRev |
0.000010047 s |
0.000010176 s |
0.99 |
sum / IDefOpt / cuda / BothRev |
0.00000992 s |
0.000010496 s |
0.95 |
sum / JaXPipe / cpu / Primal |
0.000018646 s |
0.0000073881599928427025 s |
2.52 |
sum / Jax / cpu / Primal |
0.000018217 s |
0.000007606680019307532 s |
2.39 |
sum / HLOOpt / cpu / Primal |
0.00001789 s |
0.000007699859970671241 s |
2.32 |
sum / PartOpt / cpu / Primal |
0.000017714 s |
0.00000777084002038464 s |
2.28 |
sum / IPartOpt / cpu / Primal |
0.000018121 s |
0.00000749566004742519 s |
2.42 |
sum / DefOpt / cpu / Primal |
0.000018531 s |
0.000007629619976796676 s |
2.43 |
sum / IDefOpt / cpu / Primal |
0.000018134 s |
0.000007243439986268641 s |
2.50 |
sum / JaXPipe / cpu / Forward |
0.000025115 s |
0.000011274139997112795 s |
2.23 |
sum / Jax / cpu / Forward |
0.000024609 s |
0.000010950659971058486 s |
2.25 |
sum / HLOOpt / cpu / Forward |
0.00002482 s |
0.000011121959987576702 s |
2.23 |
sum / PartOpt / cpu / Forward |
0.000024294 s |
0.000011287819997960469 s |
2.15 |
sum / IPartOpt / cpu / Forward |
0.00002487 s |
0.0000114213600045332 s |
2.18 |
sum / DefOpt / cpu / Forward |
0.000024993000000000003 s |
0.000011161999964315328 s |
2.24 |
sum / IDefOpt / cpu / Forward |
0.000024404 s |
0.000011449259982327933 s |
2.13 |
sum / JaXPipe / cpu / PreRev |
0.000023627 s |
0.000010970679995807589 s |
2.15 |
sum / JaXPipe / cpu / PostRev |
0.00002945 s |
0.000011371539985702838 s |
2.59 |
sum / JaXPipe / cpu / BothRev |
0.000023335000000000003 s |
0.000011114360004285118 s |
2.10 |
sum / Jax / cpu / BothRev |
0.000023153 s |
0.000010417740004413644 s |
2.22 |
sum / HLOOpt / cpu / PreRev |
0.00002357 s |
0.000011315600022498985 s |
2.08 |
sum / HLOOpt / cpu / PostRev |
0.000023704 s |
0.00001315417999649071 s |
1.80 |
sum / HLOOpt / cpu / BothRev |
0.000023039 s |
0.000010805659994730375 s |
2.13 |
sum / PartOpt / cpu / PreRev |
0.00002342 s |
0.000010901019986704342 s |
2.15 |
sum / PartOpt / cpu / PostRev |
0.000023519000000000003 s |
0.00001103297999179631 s |
2.13 |
sum / PartOpt / cpu / BothRev |
0.000023309 s |
0.00001119064000704384 s |
2.08 |
sum / IPartOpt / cpu / PreRev |
0.000023341 s |
0.000011013659996024215 s |
2.12 |
sum / IPartOpt / cpu / PostRev |
0.000022994 s |
0.000011391500020181411 s |
2.02 |
sum / IPartOpt / cpu / BothRev |
0.000023242 s |
0.000010877200002141763 s |
2.14 |
sum / DefOpt / cpu / PreRev |
0.000023677 s |
0.000010321480012862591 s |
2.29 |
sum / DefOpt / cpu / PostRev |
0.000022903 s |
0.000010651199982021354 s |
2.15 |
sum / DefOpt / cpu / BothRev |
0.000023462 s |
0.00001095006002287846 s |
2.14 |
sum / IDefOpt / cpu / PreRev |
0.000023322 s |
0.000011108100034107338 s |
2.10 |
sum / IDefOpt / cpu / PostRev |
0.000023361 s |
0.000011055079985453633 s |
2.11 |
sum / IDefOpt / cpu / BothRev |
0.000023371 s |
0.000010697860016080086 s |
2.18 |
sum / JaXPipe / cpu / Primal |
0.00001 s |
0.0000073881599928427025 s |
1.35 |
sum / Jax / cpu / Primal |
0.00001 s |
0.000007606680019307532 s |
1.31 |
sum / HLOOpt / cpu / Primal |
0.00001 s |
0.000007699859970671241 s |
1.30 |
sum / PartOpt / cpu / Primal |
0.00001 s |
0.00000777084002038464 s |
1.29 |
sum / IPartOpt / cpu / Primal |
0.00001 s |
0.00000749566004742519 s |
1.33 |
sum / DefOpt / cpu / Primal |
0.000008999999999999999 s |
0.000007629619976796676 s |
1.18 |
sum / IDefOpt / cpu / Primal |
0.00001 s |
0.000007243439986268641 s |
1.38 |
sum / JaXPipe / cpu / Forward |
0.000014 s |
0.000011274139997112795 s |
1.24 |
sum / Jax / cpu / Forward |
0.000014 s |
0.000010950659971058486 s |
1.28 |
sum / HLOOpt / cpu / Forward |
0.000014 s |
0.000011121959987576702 s |
1.26 |
sum / PartOpt / cpu / Forward |
0.000014 s |
0.000011287819997960469 s |
1.24 |
sum / IPartOpt / cpu / Forward |
0.000014 s |
0.0000114213600045332 s |
1.23 |
sum / DefOpt / cpu / Forward |
0.000013 s |
0.000011161999964315328 s |
1.16 |
sum / IDefOpt / cpu / Forward |
0.000014 s |
0.000011449259982327933 s |
1.22 |
sum / JaXPipe / cpu / PreRev |
0.000013 s |
0.000010970679995807589 s |
1.18 |
sum / JaXPipe / cpu / PostRev |
0.000012 s |
0.000011371539985702838 s |
1.06 |
sum / JaXPipe / cpu / BothRev |
0.000013 s |
0.000011114360004285118 s |
1.17 |
sum / Jax / cpu / BothRev |
0.000013 s |
0.000010417740004413644 s |
1.25 |
sum / HLOOpt / cpu / PreRev |
0.000013 s |
0.000011315600022498985 s |
1.15 |
sum / HLOOpt / cpu / PostRev |
0.000013 s |
0.00001315417999649071 s |
0.99 |
sum / HLOOpt / cpu / BothRev |
0.000013 s |
0.000010805659994730375 s |
1.20 |
sum / PartOpt / cpu / PreRev |
0.000013 s |
0.000010901019986704342 s |
1.19 |
sum / PartOpt / cpu / PostRev |
0.000013 s |
0.00001103297999179631 s |
1.18 |
sum / PartOpt / cpu / BothRev |
0.000013 s |
0.00001119064000704384 s |
1.16 |
sum / IPartOpt / cpu / PreRev |
0.000014 s |
0.000011013659996024215 s |
1.27 |
sum / IPartOpt / cpu / PostRev |
0.000013 s |
0.000011391500020181411 s |
1.14 |
sum / IPartOpt / cpu / BothRev |
0.000013 s |
0.000010877200002141763 s |
1.20 |
sum / DefOpt / cpu / PreRev |
0.000014 s |
0.000010321480012862591 s |
1.36 |
sum / DefOpt / cpu / PostRev |
0.000014 s |
0.000010651199982021354 s |
1.31 |
sum / DefOpt / cpu / BothRev |
0.000013 s |
0.00001095006002287846 s |
1.19 |
sum / IDefOpt / cpu / PreRev |
0.000014 s |
0.000011108100034107338 s |
1.26 |
sum / IDefOpt / cpu / PostRev |
0.000014 s |
0.000011055079985453633 s |
1.27 |
sum / IDefOpt / cpu / BothRev |
0.000013 s |
0.000010697860016080086 s |
1.22 |
value_and_grad / JaXPipe / cpu / Primal |
0.000015930119952827227 s |
0.00001368987998830562 s |
1.16 |
value_and_grad / Jax / cpu / Primal |
0.000015021599992905976 s |
0.000012834780009143288 s |
1.17 |
value_and_grad / HLOOpt / cpu / Primal |
0.000015309559958041065 s |
0.00001359859998956381 s |
1.13 |
value_and_grad / PartOpt / cpu / Primal |
0.000015057340006023878 s |
0.000013147720010238115 s |
1.15 |
value_and_grad / IPartOpt / cpu / Primal |
0.000014695000018036808 s |
0.000013329280009202191 s |
1.10 |
value_and_grad / DefOpt / cpu / Primal |
0.000014958280034989002 s |
0.000013371560044106444 s |
1.12 |
value_and_grad / IDefOpt / cpu / Primal |
0.000015102360011951532 s |
0.000013235739997981 s |
1.14 |
value_and_grad / JaXPipe / cuda / Primal |
0.000033056 s |
0.000034432 s |
0.96 |
value_and_grad / Jax / cuda / Primal |
0.000033568 s |
0.000034368 s |
0.98 |
value_and_grad / HLOOpt / cuda / Primal |
0.000032992 s |
0.000033568 s |
0.98 |
value_and_grad / PartOpt / cuda / Primal |
0.000032992 s |
0.000034176 s |
0.97 |
value_and_grad / IPartOpt / cuda / Primal |
0.000033216 s |
0.00003344 s |
0.99 |
value_and_grad / DefOpt / cuda / Primal |
0.000032576 s |
0.000033536000000000006 s |
0.97 |
value_and_grad / IDefOpt / cuda / Primal |
0.000032767999999999995 s |
0.000033952 s |
0.97 |
value_and_grad / JaXPipe / cpu / Primal |
0.000028611 s |
0.00001368987998830562 s |
2.09 |
value_and_grad / Jax / cpu / Primal |
0.000027771 s |
0.000012834780009143288 s |
2.16 |
value_and_grad / HLOOpt / cpu / Primal |
0.000027703 s |
0.00001359859998956381 s |
2.04 |
value_and_grad / PartOpt / cpu / Primal |
0.000027714 s |
0.000013147720010238115 s |
2.11 |
value_and_grad / IPartOpt / cpu / Primal |
0.000028142 s |
0.000013329280009202191 s |
2.11 |
value_and_grad / DefOpt / cpu / Primal |
0.0000279 s |
0.000013371560044106444 s |
2.09 |
value_and_grad / IDefOpt / cpu / Primal |
0.000028269 s |
0.000013235739997981 s |
2.14 |
value_and_grad / JaXPipe / cpu / Primal |
0.000015 s |
0.00001368987998830562 s |
1.10 |
value_and_grad / Jax / cpu / Primal |
0.000016 s |
0.000012834780009143288 s |
1.25 |
value_and_grad / HLOOpt / cpu / Primal |
0.000015 s |
0.00001359859998956381 s |
1.10 |
value_and_grad / PartOpt / cpu / Primal |
0.000015 s |
0.000013147720010238115 s |
1.14 |
value_and_grad / IPartOpt / cpu / Primal |
0.000015 s |
0.000013329280009202191 s |
1.13 |
value_and_grad / DefOpt / cpu / Primal |
0.000015 s |
0.000013371560044106444 s |
1.12 |
value_and_grad / IDefOpt / cpu / Primal |
0.000016 s |
0.000013235739997981 s |
1.21 |
jaxmd20 / JaXPipe / cuda / Primal |
0.001527549 s |
0.001523829 s |
1.00 |
jaxmd20 / Jax / cuda / Primal |
0.001514558 s |
0.001504916 s |
1.01 |
jaxmd20 / HLOOpt / cuda / Primal |
0.001385021 s |
0.001365685 s |
1.01 |
jaxmd20 / PartOpt / cuda / Primal |
0.00136643 s |
0.00139615 s |
0.98 |
jaxmd20 / IPartOpt / cuda / Primal |
0.0013335019999999 s |
0.001369014 s |
0.97 |
jaxmd20 / DefOpt / cuda / Primal |
0.0009229739999999 s |
0.000948793 s |
0.97 |
jaxmd20 / IDefOpt / cuda / Primal |
0.000958494 s |
0.00096684 s |
0.99 |
jaxmd20 / JaXPipe / cuda / Forward |
0.001555739 s |
0.0016365 s |
0.95 |
jaxmd20 / Jax / cuda / Forward |
0.001855548 s |
0.001862161 s |
1.00 |
jaxmd20 / HLOOpt / cuda / Forward |
0.001632605 s |
0.001722931 s |
0.95 |
jaxmd20 / PartOpt / cuda / Forward |
0.0016486369999999 s |
0.001712275 s |
0.96 |
jaxmd20 / IPartOpt / cuda / Forward |
0.001666045 s |
0.00171954 s |
0.97 |
jaxmd20 / DefOpt / cuda / Forward |
0.001665373 s |
0.0017042749999999 s |
0.98 |
jaxmd20 / IDefOpt / cuda / Forward |
0.001649724 s |
0.001722099 s |
0.96 |
jaxmd20 / JaXPipe / cuda / PreRev |
0.0026787779999999 s |
0.0027976109999999 s |
0.96 |
jaxmd20 / JaXPipe / cuda / PostRev |
0.005343381 s |
0.005463702 s |
0.98 |
jaxmd20 / JaXPipe / cuda / BothRev |
0.00268153 s |
0.002757612 s |
0.97 |
jaxmd20 / Jax / cuda / BothRev |
0.005417877 s |
0.005447255 s |
0.99 |
jaxmd20 / HLOOpt / cuda / PreRev |
0.002739002 s |
0.0028474349999999 s |
0.96 |
jaxmd20 / HLOOpt / cuda / PostRev |
0.0053263569999999 s |
0.005511671 s |
0.97 |
jaxmd20 / HLOOpt / cuda / BothRev |
0.002718299 s |
0.002862442 s |
0.95 |
jaxmd20 / PartOpt / cuda / PreRev |
0.00283977 s |
0.002884907 s |
0.98 |
jaxmd20 / PartOpt / cuda / PostRev |
0.005411541 s |
0.005561206 s |
0.97 |
jaxmd20 / PartOpt / cuda / BothRev |
0.002761051 s |
0.002824139 s |
0.98 |
jaxmd20 / IPartOpt / cuda / PreRev |
0.002824634 s |
0.002907402 s |
0.97 |
jaxmd20 / IPartOpt / cuda / PostRev |
0.005408373 s |
0.00555839 s |
0.97 |
jaxmd20 / IPartOpt / cuda / BothRev |
0.002756186 s |
0.002819179 s |
0.98 |
jaxmd20 / DefOpt / cuda / PreRev |
0.002836763 s |
0.002906218 s |
0.98 |
jaxmd20 / DefOpt / cuda / PostRev |
0.002746106 s |
0.002843402 s |
0.97 |
jaxmd20 / DefOpt / cuda / BothRev |
0.002788507 s |
0.002841227 s |
0.98 |
jaxmd20 / IDefOpt / cuda / PreRev |
0.002815739 s |
0.002915049 s |
0.97 |
jaxmd20 / IDefOpt / cuda / PostRev |
0.002395323 s |
0.002349326 s |
1.02 |
jaxmd20 / IDefOpt / cuda / BothRev |
0.002758202 s |
0.002841963 s |
0.97 |
jaxmd40 / JaXPipe / cpu / Primal |
0.080885238 s |
0.061100785 s |
1.32 |
jaxmd40 / Jax / cpu / Primal |
0.098504534 s |
0.0635065839999999 s |
1.55 |
jaxmd40 / HLOOpt / cpu / Primal |
0.121969451 s |
0.091494653 s |
1.33 |
jaxmd40 / PartOpt / cpu / Primal |
0.089284166 s |
0.0693478159999999 s |
1.29 |
jaxmd40 / IPartOpt / cpu / Primal |
0.077659733 s |
0.069367468 s |
1.12 |
jaxmd40 / DefOpt / cpu / Primal |
0.111010423 s |
0.0884403949999999 s |
1.26 |
jaxmd40 / IDefOpt / cpu / Primal |
0.108832161 s |
0.0901378229999999 s |
1.21 |
jaxmd40 / JaXPipe / cpu / Forward |
0.2017681939999999 s |
0.155904045 s |
1.29 |
jaxmd40 / Jax / cpu / Forward |
0.111006957 s |
0.087002351 s |
1.28 |
jaxmd40 / HLOOpt / cpu / Forward |
0.203296768 s |
0.159402504 s |
1.28 |
jaxmd40 / PartOpt / cpu / Forward |
0.209359532 s |
0.156365765 s |
1.34 |
jaxmd40 / IPartOpt / cpu / Forward |
0.205539039 s |
0.1550916729999999 s |
1.33 |
jaxmd40 / DefOpt / cpu / Forward |
0.2047300229999999 s |
0.155764771 s |
1.31 |
jaxmd40 / IDefOpt / cpu / Forward |
0.218962713 s |
0.153444358 s |
1.43 |
jaxmd40 / JaXPipe / cpu / PreRev |
0.257737572 s |
0.222640007 s |
1.16 |
jaxmd40 / JaXPipe / cpu / PostRev |
0.166776502 s |
0.137700003 s |
1.21 |
jaxmd40 / JaXPipe / cpu / BothRev |
0.270335774 s |
0.213017677 s |
1.27 |
jaxmd40 / Jax / cpu / BothRev |
0.1804737199999999 s |
0.138194075 s |
1.31 |
jaxmd40 / HLOOpt / cpu / PreRev |
0.2725959599999999 s |
0.213665446 s |
1.28 |
jaxmd40 / HLOOpt / cpu / PostRev |
0.229173852 s |
0.177621278 s |
1.29 |
jaxmd40 / HLOOpt / cpu / BothRev |
0.29715314 s |
0.246586547 s |
1.21 |
jaxmd40 / PartOpt / cpu / PreRev |
0.265850237 s |
0.229487209 s |
1.16 |
jaxmd40 / PartOpt / cpu / PostRev |
0.168415175 s |
0.127357375 s |
1.32 |
jaxmd40 / PartOpt / cpu / BothRev |
0.298241561 s |
0.235627231 s |
1.27 |
jaxmd40 / IPartOpt / cpu / PreRev |
0.262833271 s |
0.221533793 s |
1.19 |
jaxmd40 / IPartOpt / cpu / PostRev |
0.1743218 s |
0.1329925619999999 s |
1.31 |
jaxmd40 / IPartOpt / cpu / BothRev |
0.297889984 s |
0.249216651 s |
1.20 |
jaxmd40 / DefOpt / cpu / PreRev |
0.25976506 s |
0.238000395 s |
1.09 |
jaxmd40 / DefOpt / cpu / PostRev |
0.226279066 s |
0.160789668 s |
1.41 |
jaxmd40 / DefOpt / cpu / BothRev |
0.295166876 s |
0.262327709 s |
1.13 |
jaxmd40 / IDefOpt / cpu / PreRev |
0.257158728 s |
0.217784267 s |
1.18 |
jaxmd40 / IDefOpt / cpu / PostRev |
0.215873199 s |
0.169755992 s |
1.27 |
jaxmd40 / IDefOpt / cpu / BothRev |
0.302506992 s |
0.253954129 s |
1.19 |
v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / JaXPipe / cuda / Primal |
1.70068685 s |
1.702594998 s |
1.00 |
v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / Jax / cuda / Primal |
1.703306042 s |
1.705126831 s |
1.00 |
v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / HLOOpt / cuda / Primal |
1.714219211 s |
1.714914401 s |
1.00 |
v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / PartOpt / cuda / Primal |
1.695130324 s |
1.696614098 s |
1.00 |
v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / IPartOpt / cuda / Primal |
1.692980566 s |
1.694511569 s |
1.00 |
v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / DefOpt / cuda / Primal |
1.664084373 s |
1.665037519 s |
1.00 |
v1/deterministic_2_8_deg_inner_steps_24_outer_steps_4 / IDefOpt / cuda / Primal |
1.919464038 s |
1.922172896 s |
1.00 |
v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / JaXPipe / cpu / Primal |
7.465378834 s |
5.840688598 s |
1.28 |
v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / Jax / cpu / Primal |
7.45591651 s |
5.832999721 s |
1.28 |
v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / HLOOpt / cpu / Primal |
7.123531047 s |
5.8651677200000005 s |
1.21 |
v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / PartOpt / cpu / Primal |
7.383126970999999 s |
5.8983041830000005 s |
1.25 |
v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / IPartOpt / cpu / Primal |
7.433135508999999 s |
6.019389234 s |
1.23 |
v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / DefOpt / cpu / Primal |
3.157163911 s |
2.290181343 s |
1.38 |
v1/deterministic_2_8_deg_inner_steps_2_outer_steps_2 / IDefOpt / cpu / Primal |
7.901866218 s |
6.410226099000001 s |
1.23 |
This comment was automatically generated by workflow using github-action-benchmark.
7c302fb to
b9efdda
Compare
b9efdda to
f906581
Compare
f906581 to
e82ff21
Compare
e82ff21 to
8599fa5
Compare
8599fa5 to
2c373da
Compare
2c373da to
3035827
Compare
3035827 to
555879c
Compare
555879c to
3897032
Compare
3897032 to
a146de0
Compare
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.
Diff: jax-ml/jax@ba024e3...816e644