-
Notifications
You must be signed in to change notification settings - Fork 33
feat: new upstream opt passes #1684
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
Conversation
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #1684 +/- ##
=======================================
Coverage 67.85% 67.85%
=======================================
Files 108 108
Lines 11772 11772
=======================================
Hits 7988 7988
Misses 3784 3784 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
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.
Reactant.jl Benchmarks
| Benchmark suite | Current: 28f5c89 | Previous: 670b480 | Ratio |
|---|---|---|---|
DeepONet ([64, 1024], [1, 128])/forward/CPU/Default |
0.001349617 s |
0.0027640620000000003 s |
0.49 |
DeepONet ([64, 1024], [1, 128])/forward/CPU/DisableScatterGatherPad |
0.0012237860000000001 s |
0.002834215 s |
0.43 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisablePadAfterEnzyme |
0.0032420480000000004 s |
0.0068642880000000005 s |
0.47 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DefaultAfterEnzyme |
0.0032380470000000004 s |
0.006667628 s |
0.49 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisableScatterGatherPadBeforeEnzyme |
0.003288998 s |
0.006256986 s |
0.53 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisableScatterGatherPadAll |
0.0031775180000000003 s |
0.006593565 s |
0.48 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisablePadBeforeEnzyme |
0.0031784170000000002 s |
0.006250632000000001 s |
0.51 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisablePadAll |
0.0032379450000000003 s |
0.006878530000000001 s |
0.47 |
DeepONet ([64, 1024], [1, 128])/forward/CPU/DisableScatterGather |
0.001267555 s |
0.003002134 s |
0.42 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DefaultAll |
0.0033504480000000002 s |
0.006976556 s |
0.48 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisableTransposeReshapeAfterEnzyme |
0.0032238590000000004 s |
0.006424152000000001 s |
0.50 |
DeepONet ([64, 1024], [1, 128])/forward/CPU/XLA |
0.001560566 s |
0.002926595 s |
0.53 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/XLA |
0.003171367 s |
0.006283277 s |
0.50 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisableScatterGatherAfterEnzyme |
0.0032161200000000003 s |
0.006926369000000001 s |
0.46 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DefaultBeforeEnzyme |
0.0032873280000000004 s |
0.006892713000000001 s |
0.48 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisableTransposeReshapeBeforeEnzyme |
0.003371193 s |
0.006415914 s |
0.53 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisableScatterGatherPadAfterEnzyme |
0.0032388 s |
0.006691506000000001 s |
0.48 |
DeepONet ([64, 1024], [1, 128])/forward/CPU/DisablePad |
0.001217105 s |
0.0027958270000000003 s |
0.44 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisableTransposeReshapeAll |
0.0033245230000000002 s |
0.006947857000000001 s |
0.48 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisableScatterGatherAll |
0.003158441 s |
0.006691673 s |
0.47 |
DeepONet ([64, 1024], [1, 128])/forward/CPU/DisableTransposeReshape |
0.00135592 s |
0.003069885 s |
0.44 |
DeepONet ([64, 1024], [1, 128])/backward/CPU/DisableScatterGatherBeforeEnzyme |
0.0032649050000000002 s |
0.006662285 s |
0.49 |
VGG11 bn=true [224, 224, 3, 4]/forward/CUDA/DisablePad |
0.0020088090000000003 s |
0.0020071 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisableScatterGatherAll |
0.000656395 s |
0.000661261 s |
0.99 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/XLA |
0.0007595070000000001 s |
0.0007559890000000001 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisableTransposeReshapeAll |
0.007157111000000001 s |
0.0071443 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DefaultBeforeEnzyme |
0.0006823010000000001 s |
0.0006784860000000001 s |
1.01 |
FNO [64, 64, 1, 4]/backward/CUDA/DefaultAll |
0.002976372 s |
0.0029501220000000003 s |
1.01 |
VGG11 bn=true [224, 224, 3, 4]/forward/CUDA/DisableScatterGatherPad |
0.0020128520000000003 s |
0.0019970020000000003 s |
1.01 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisableTransposeReshapeBeforeEnzyme |
0.007253883 s |
0.00722341 s |
1.00 |
FNO [64, 64, 1, 4]/backward/CUDA/DefaultBeforeEnzyme |
0.0030029540000000004 s |
0.0030136890000000004 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/forward/CUDA/XLA |
0.000366534 s |
0.000354015 s |
1.04 |
FNO [64, 64, 1, 4]/backward/CUDA/DisablePadBeforeEnzyme |
0.0030121820000000004 s |
0.00298859 s |
1.01 |
FNO [64, 64, 1, 4]/backward/CUDA/DisableScatterGatherPadAll |
0.002965197 s |
0.0029435570000000003 s |
1.01 |
FNO [64, 64, 1, 4]/forward/CUDA/DisablePad |
0.001090953 s |
0.001086989 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisablePadBeforeEnzyme |
0.007214666000000001 s |
0.007233908000000001 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisableScatterGatherPadBeforeEnzyme |
0.007214898000000001 s |
0.007207276 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisableScatterGatherAfterEnzyme |
0.007129927 s |
0.007154596 s |
1.00 |
FNO [64, 64, 1, 4]/forward/CUDA/DisableScatterGatherPad |
0.001095824 s |
0.001114535 s |
0.98 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisablePadAll |
0.000647683 s |
0.0007195210000000001 s |
0.90 |
DeepONet ([64, 1024], [1, 128])/forward/CUDA/DisableTransposeReshape |
0.00031442300000000004 s |
0.00032367 s |
0.97 |
ViT tiny [256, 256, 3, 4]/forward/CUDA/DisableScatterGatherPad |
0.003105659 s |
0.0031074640000000003 s |
1.00 |
ViT tiny [256, 256, 3, 4]/forward/CUDA/DisableScatterGather |
0.003111546 s |
0.003105263 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DefaultAfterEnzyme |
0.000663742 s |
0.000664801 s |
1.00 |
ViT tiny [256, 256, 3, 4]/backward/CUDA/XLA |
0.010491584 s |
0.010420036 s |
1.01 |
FNO [64, 64, 1, 4]/backward/CUDA/DisableScatterGatherAfterEnzyme |
0.0029506380000000002 s |
0.002928972 s |
1.01 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DefaultAfterEnzyme |
0.007163023 s |
0.007123775000000001 s |
1.01 |
DeepONet ([64, 1024], [1, 128])/forward/CUDA/DisableScatterGather |
0.000316924 s |
0.00031832000000000003 s |
1.00 |
FNO [64, 64, 1, 4]/forward/CUDA/DisableTransposeReshape |
0.0011424920000000002 s |
0.001134737 s |
1.01 |
FNO [64, 64, 1, 4]/backward/CUDA/DisablePadAll |
0.002954893 s |
0.002934453 s |
1.01 |
ViT tiny [256, 256, 3, 4]/forward/CUDA/XLA |
0.003290901 s |
0.003332816 s |
0.99 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisableScatterGatherBeforeEnzyme |
0.007243553000000001 s |
0.007222719000000001 s |
1.00 |
FNO [64, 64, 1, 4]/backward/CUDA/DisableTransposeReshapeAll |
0.0030972250000000003 s |
0.00305555 s |
1.01 |
ViT tiny [256, 256, 3, 4]/forward/CUDA/DisableTransposeReshape |
0.0030637280000000004 s |
0.0030500780000000003 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisablePadAll |
0.0071317970000000005 s |
0.007097975 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisableScatterGatherPadAfterEnzyme |
0.007138297 s |
0.007120118000000001 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/forward/CUDA/DisablePad |
0.000304694 s |
0.000311184 s |
0.98 |
FNO [64, 64, 1, 4]/backward/CUDA/DisableTransposeReshapeBeforeEnzyme |
0.0031063370000000002 s |
0.0031280170000000003 s |
0.99 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisableScatterGatherAfterEnzyme |
0.00066244 s |
0.000670725 s |
0.99 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisableTransposeReshapeAfterEnzyme |
0.0006692800000000001 s |
0.0006503990000000001 s |
1.03 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisableScatterGatherPadAll |
0.007109906 s |
0.007114771000000001 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisableTransposeReshapeBeforeEnzyme |
0.000688083 s |
0.0006777290000000001 s |
1.02 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DefaultAll |
0.007136619 s |
0.007130952 s |
1.00 |
FNO [64, 64, 1, 4]/backward/CUDA/XLA |
0.0031238240000000003 s |
0.003127176 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/XLA |
0.007261091000000001 s |
0.0072779690000000005 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/forward/CUDA/DisableTransposeReshape |
0.002011436 s |
0.002010444 s |
1.00 |
FNO [64, 64, 1, 4]/backward/CUDA/DisableTransposeReshapeAfterEnzyme |
0.0030897800000000003 s |
0.0030678090000000003 s |
1.01 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DefaultAll |
0.000672267 s |
0.000653007 s |
1.03 |
FNO [64, 64, 1, 4]/backward/CUDA/DisablePadAfterEnzyme |
0.0029353030000000002 s |
0.0029185030000000002 s |
1.01 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisableScatterGatherAll |
0.0071286000000000006 s |
0.00711759 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisableScatterGatherPadAfterEnzyme |
0.0006622640000000001 s |
0.0006618440000000001 s |
1.00 |
FNO [64, 64, 1, 4]/forward/CUDA/XLA |
0.001178728 s |
0.001167541 s |
1.01 |
ViT tiny [256, 256, 3, 4]/forward/CUDA/DisablePad |
0.002450714 s |
0.0024550170000000003 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/forward/CUDA/XLA |
0.002075897 s |
0.002064718 s |
1.01 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisablePadAfterEnzyme |
0.00714985 s |
0.0070958340000000005 s |
1.01 |
FNO [64, 64, 1, 4]/backward/CUDA/DisableScatterGatherBeforeEnzyme |
0.0030103490000000003 s |
0.0029879990000000003 s |
1.01 |
ViT tiny [256, 256, 3, 4]/forward/CUDA/Default |
0.0031487420000000004 s |
0.0031179190000000002 s |
1.01 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisableScatterGatherBeforeEnzyme |
0.000708086 s |
0.000691727 s |
1.02 |
FNO [64, 64, 1, 4]/forward/CUDA/DisableScatterGather |
0.0011036280000000002 s |
0.001091488 s |
1.01 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DisableTransposeReshapeAfterEnzyme |
0.007134582 s |
0.007138152 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisablePadAfterEnzyme |
0.0006693770000000001 s |
0.000659727 s |
1.01 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisableScatterGatherPadAll |
0.000643509 s |
0.0006512950000000001 s |
0.99 |
FNO [64, 64, 1, 4]/backward/CUDA/DisableScatterGatherAll |
0.0029675590000000003 s |
0.0029385260000000003 s |
1.01 |
FNO [64, 64, 1, 4]/backward/CUDA/DefaultAfterEnzyme |
0.002951228 s |
0.002939876 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisableTransposeReshapeAll |
0.000669716 s |
0.0006570590000000001 s |
1.02 |
VGG11 bn=true [224, 224, 3, 4]/forward/CUDA/Default |
0.0020257400000000003 s |
0.002004702 s |
1.01 |
FNO [64, 64, 1, 4]/forward/CUDA/Default |
0.001095723 s |
0.001095781 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/forward/CUDA/DisableScatterGatherPad |
0.000311033 s |
0.000305221 s |
1.02 |
VGG11 bn=true [224, 224, 3, 4]/forward/CUDA/DisableScatterGather |
0.002009504 s |
0.0020108020000000003 s |
1.00 |
ViT tiny [256, 256, 3, 4]/backward/CUDA/DefaultAll |
0.010397481 s |
0.010502326000000001 s |
0.99 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisablePadBeforeEnzyme |
0.000686738 s |
0.000662947 s |
1.04 |
DeepONet ([64, 1024], [1, 128])/forward/CUDA/Default |
0.00031843700000000003 s |
0.000313138 s |
1.02 |
FNO [64, 64, 1, 4]/backward/CUDA/DisableScatterGatherPadAfterEnzyme |
0.002942375 s |
0.002955905 s |
1.00 |
FNO [64, 64, 1, 4]/backward/CUDA/DisableScatterGatherPadBeforeEnzyme |
0.0030008530000000004 s |
0.002985886 s |
1.01 |
VGG11 bn=true [224, 224, 3, 4]/backward/CUDA/DefaultBeforeEnzyme |
0.007265314 s |
0.007230926 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/CUDA/DisableScatterGatherPadBeforeEnzyme |
0.0006946890000000001 s |
0.0006883530000000001 s |
1.01 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisableScatterGatherPadAfterEnzyme |
0.0047613 s |
0.004745551000000001 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/forward/TPU/DisablePad |
0.0011885600000000002 s |
0.00117253 s |
1.01 |
FNO [64, 64, 1, 4]/backward/TPU/DisableScatterGatherPadAll |
0.00298831 s |
0.00300263 s |
1.00 |
ViT tiny [256, 256, 3, 4]/backward/TPU/XLA |
0.0022191100000000003 s |
0.00218447 s |
1.02 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisablePadBeforeEnzyme |
0.00034470000000000003 s |
0.00033360000000000003 s |
1.03 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisableTransposeReshapeAfterEnzyme |
0.00034538 s |
0.00033629 s |
1.03 |
FNO [64, 64, 1, 4]/backward/TPU/DisableScatterGatherAfterEnzyme |
0.0028620100000000003 s |
0.00289915 s |
0.99 |
FNO [64, 64, 1, 4]/backward/TPU/DefaultAll |
0.0029879900000000003 s |
0.00300393 s |
0.99 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisableScatterGatherPadAll |
0.00477869 s |
0.00475926 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisableScatterGatherPadBeforeEnzyme |
0.00034470000000000003 s |
0.00033661000000000005 s |
1.02 |
DeepONet ([64, 1024], [1, 128])/forward/TPU/Default |
0.00018460000000000001 s |
0.00016552 s |
1.12 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisablePadBeforeEnzyme |
0.00476474 s |
0.00475095 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/forward/TPU/DisableScatterGatherPad |
0.00119698 s |
0.00117157 s |
1.02 |
FNO [64, 64, 1, 4]/backward/TPU/DisableTransposeReshapeAfterEnzyme |
0.00299218 s |
0.00301906 s |
0.99 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisableScatterGatherBeforeEnzyme |
0.00034495 s |
0.00033484000000000004 s |
1.03 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisableScatterGatherAfterEnzyme |
0.00034083000000000003 s |
0.00033613 s |
1.01 |
ViT tiny [256, 256, 3, 4]/forward/TPU/DisableScatterGatherPad |
0.00045138000000000003 s |
0.00044488000000000004 s |
1.01 |
FNO [64, 64, 1, 4]/backward/TPU/DisableTransposeReshapeAll |
0.0029801800000000002 s |
0.0029921600000000002 s |
1.00 |
FNO [64, 64, 1, 4]/backward/TPU/DisableTransposeReshapeBeforeEnzyme |
0.00297815 s |
0.003001259 s |
0.99 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DefaultAfterEnzyme |
0.004785191 s |
0.004771500000000001 s |
1.00 |
FNO [64, 64, 1, 4]/forward/TPU/DisableScatterGather |
0.0011068410000000001 s |
0.00111234 s |
1.00 |
FNO [64, 64, 1, 4]/backward/TPU/DisablePadBeforeEnzyme |
0.0029946200000000004 s |
0.00299928 s |
1.00 |
ViT tiny [256, 256, 3, 4]/forward/TPU/XLA |
0.0007863000000000001 s |
0.0007893900000000001 s |
1.00 |
ViT tiny [256, 256, 3, 4]/backward/TPU/DefaultAll |
0.00247502 s |
0.00246953 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/forward/TPU/Default |
0.00119304 s |
0.00117095 s |
1.02 |
DeepONet ([64, 1024], [1, 128])/forward/TPU/DisableScatterGatherPad |
0.00018937 s |
0.0001644 s |
1.15 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DefaultAll |
0.00034796 s |
0.00033065000000000004 s |
1.05 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DefaultAll |
0.00476137 s |
0.00472845 s |
1.01 |
DeepONet ([64, 1024], [1, 128])/forward/TPU/DisableScatterGather |
0.00019245000000000002 s |
0.00016663000000000002 s |
1.15 |
VGG11 bn=true [224, 224, 3, 4]/forward/TPU/DisableTransposeReshape |
0.00119479 s |
0.0011814500000000001 s |
1.01 |
FNO [64, 64, 1, 4]/backward/TPU/DisableScatterGatherPadBeforeEnzyme |
0.0029930300000000003 s |
0.00301111 s |
0.99 |
ViT tiny [256, 256, 3, 4]/forward/TPU/DisablePad |
0.00045872 s |
0.00044431 s |
1.03 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DefaultBeforeEnzyme |
0.00034356 s |
0.00033088000000000003 s |
1.04 |
DeepONet ([64, 1024], [1, 128])/forward/TPU/DisablePad |
0.00019017 s |
0.00015879000000000002 s |
1.20 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/XLA |
0.00035013000000000004 s |
0.00033349000000000003 s |
1.05 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisableTransposeReshapeAll |
0.004797930000000001 s |
0.00477299 s |
1.01 |
FNO [64, 64, 1, 4]/backward/TPU/DisableScatterGatherAll |
0.0029936900000000002 s |
0.00300394 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisableScatterGatherPadAll |
0.000342519 s |
0.00033743 s |
1.02 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisableTransposeReshapeBeforeEnzyme |
0.00478292 s |
0.0047531000000000006 s |
1.01 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisableTransposeReshapeAfterEnzyme |
0.00479185 s |
0.0047541300000000005 s |
1.01 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisableScatterGatherAll |
0.00477113 s |
0.00474663 s |
1.01 |
FNO [64, 64, 1, 4]/backward/TPU/DisablePadAfterEnzyme |
0.00287441 s |
0.0028714500000000002 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisableScatterGatherBeforeEnzyme |
0.004790679 s |
0.00478295 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisableScatterGatherAfterEnzyme |
0.00474369 s |
0.004757470000000001 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/forward/TPU/XLA |
0.00137725 s |
0.0013455000000000001 s |
1.02 |
ViT tiny [256, 256, 3, 4]/forward/TPU/DisableTransposeReshape |
0.00045823 s |
0.00045458 s |
1.01 |
ViT tiny [256, 256, 3, 4]/forward/TPU/Default |
0.00044921 s |
0.00045470000000000005 s |
0.99 |
FNO [64, 64, 1, 4]/backward/TPU/DefaultBeforeEnzyme |
0.0029897500000000002 s |
0.0029963900000000003 s |
1.00 |
FNO [64, 64, 1, 4]/forward/TPU/Default |
0.00110793 s |
0.00111345 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/XLA |
0.00465651 s |
0.00463068 s |
1.01 |
FNO [64, 64, 1, 4]/forward/TPU/XLA |
0.00138282 s |
0.001380411 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/forward/TPU/DisableTransposeReshape |
0.00019243 s |
0.00014961 s |
1.29 |
FNO [64, 64, 1, 4]/backward/TPU/DisablePadAll |
0.0029847800000000002 s |
0.0030175700000000002 s |
0.99 |
DeepONet ([64, 1024], [1, 128])/forward/TPU/XLA |
0.00028495 s |
0.00026558 s |
1.07 |
FNO [64, 64, 1, 4]/forward/TPU/DisableScatterGatherPad |
0.001117079 s |
0.00110917 s |
1.01 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisablePadAfterEnzyme |
0.00477205 s |
0.004758330000000001 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DefaultAfterEnzyme |
0.00034346 s |
0.00033344 s |
1.03 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisablePadAll |
0.0047721000000000005 s |
0.004773540000000001 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DefaultBeforeEnzyme |
0.004782261 s |
0.0047601100000000006 s |
1.00 |
VGG11 bn=true [224, 224, 3, 4]/forward/TPU/DisableScatterGather |
0.00118923 s |
0.0011653500000000001 s |
1.02 |
ViT tiny [256, 256, 3, 4]/forward/TPU/DisableScatterGather |
0.00045798000000000003 s |
0.00044451 s |
1.03 |
FNO [64, 64, 1, 4]/backward/TPU/DisableScatterGatherBeforeEnzyme |
0.00299656 s |
0.00300108 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisableTransposeReshapeBeforeEnzyme |
0.00034970000000000004 s |
0.00033571 s |
1.04 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisableScatterGatherPadAfterEnzyme |
0.000339869 s |
0.00033867 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisablePadAll |
0.00034252 s |
0.00033584 s |
1.02 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisableScatterGatherAll |
0.0003463 s |
0.00033564 s |
1.03 |
FNO [64, 64, 1, 4]/forward/TPU/DisableTransposeReshape |
0.0011359500000000002 s |
0.00113881 s |
1.00 |
FNO [64, 64, 1, 4]/backward/TPU/DefaultAfterEnzyme |
0.0028683100000000002 s |
0.00288199 s |
1.00 |
FNO [64, 64, 1, 4]/backward/TPU/DisableScatterGatherPadAfterEnzyme |
0.0028836 s |
0.0028984 s |
0.99 |
VGG11 bn=true [224, 224, 3, 4]/backward/TPU/DisableScatterGatherPadBeforeEnzyme |
0.00479071 s |
0.00476311 s |
1.01 |
FNO [64, 64, 1, 4]/forward/TPU/DisablePad |
0.00110409 s |
0.0011101000000000001 s |
0.99 |
FNO [64, 64, 1, 4]/backward/TPU/XLA |
0.0031633800000000004 s |
0.0031764500000000004 s |
1.00 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisableTransposeReshapeAll |
0.00034939000000000004 s |
0.00033436 s |
1.04 |
DeepONet ([64, 1024], [1, 128])/backward/TPU/DisablePadAfterEnzyme |
0.00033895 s |
0.00033649 s |
1.01 |
This comment was automatically generated by workflow using github-action-benchmark.
No description provided.