-
Notifications
You must be signed in to change notification settings - Fork 15
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat: allow type-casting numbers to tracednumbers (#209)
* feat: allow type-casting numbers to tracednumbers * chore: apply formatting suggestion
- Loading branch information
Showing
2 changed files
with
15 additions
and
0 deletions.
There are no files selected for viewing
This file contains 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
This file contains 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
babeb7c
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
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :after_enzyme)
1418797944
ns1340567545
ns1.06
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Reactant
1230657063
ns1354795677
ns0.91
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :before_enzyme)
1210055514
ns1296358153
ns0.93
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :only_enzyme)
2321453182
ns2617478292
ns0.89
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Lux
215031968
ns207121854
ns1.04
ViT base (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :after_enzyme)
5458708327
ns5245986343
ns1.04
ViT base (256 x 256 x 3 x 32)/forward/CPU/Reactant
5179301625
ns5473784946
ns0.95
ViT base (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :before_enzyme)
5152065959
ns5562801011
ns0.93
ViT base (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :only_enzyme)
6914653384
ns6785865699
ns1.02
ViT base (256 x 256 x 3 x 32)/forward/CPU/Lux
29634509034
ns28788392011
ns1.03
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :after_enzyme)
1303933391
ns1329681507
ns0.98
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Reactant
1288941570.5
ns1310470804
ns0.98
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :before_enzyme)
1246884488
ns1322248869
ns0.94
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :only_enzyme)
2588209027
ns2593706297
ns1.00
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Lux
8825930
ns8538279.5
ns1.03
ViT small (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :after_enzyme)
1637260762
ns1569392248
ns1.04
ViT small (256 x 256 x 3 x 4)/forward/CPU/Reactant
1607338067
ns1563566948
ns1.03
ViT small (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :before_enzyme)
1592753746
ns1601308923.5
ns0.99
ViT small (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :only_enzyme)
2888392716
ns2743850639
ns1.05
ViT small (256 x 256 x 3 x 4)/forward/CPU/Lux
2959415354
ns2498208075
ns1.18
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :after_enzyme)
1320589513
ns1314553261
ns1.00
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Reactant
1232647002.5
ns1520974050.5
ns0.81
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :before_enzyme)
1233197730.5
ns1289846630
ns0.96
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :only_enzyme)
2510219663
ns2616640648
ns0.96
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Lux
22686905
ns21421171
ns1.06
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :after_enzyme)
2195365921
ns2256971186
ns0.97
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Reactant
2173148463
ns2259019481
ns0.96
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :before_enzyme)
2160517237
ns2253385981
ns0.96
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :only_enzyme)
3389252115
ns3571597383
ns0.95
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Lux
5458754250.5
ns6399412347.5
ns0.85
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :after_enzyme)
1336344147
ns1315428709.5
ns1.02
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Reactant
1284165465.5
ns1285752949.5
ns1.00
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :before_enzyme)
1264413606
ns1352009040.5
ns0.94
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :only_enzyme)
2388755659
ns2483558090
ns0.96
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Lux
7116389
ns7375914.5
ns0.96
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :after_enzyme)
1494584041
ns1471123545
ns1.02
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Reactant
1490742502
ns1460958972
ns1.02
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :before_enzyme)
1473980569
ns1467352849
ns1.00
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :only_enzyme)
2796807816
ns2771232207
ns1.01
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Lux
1669183460
ns1067840903.5
ns1.56
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :after_enzyme)
1220367359.5
ns1265463942
ns0.96
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Reactant
1264274640.5
ns1336662627
ns0.95
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :before_enzyme)
1345724410.5
ns1343776367
ns1.00
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :only_enzyme)
2566724316
ns2625246543
ns0.98
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Lux
12278807
ns15448376
ns0.79
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :after_enzyme)
1777269725
ns1762453178
ns1.01
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Reactant
1763977334
ns1744480870
ns1.01
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :before_enzyme)
1773537556
ns1747667945
ns1.01
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :only_enzyme)
3105794746
ns3050720896
ns1.02
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Lux
3076042064.5
ns2931138896
ns1.05
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :after_enzyme)
1271346742
ns1334489477
ns0.95
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Reactant
1246562750
ns1354072030
ns0.92
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :before_enzyme)
1309043330
ns1326138010.5
ns0.99
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :only_enzyme)
2442642621
ns2585240240
ns0.94
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Lux
27314834
ns25592502.5
ns1.07
ViT small (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :after_enzyme)
2242544865
ns2380176040
ns0.94
ViT small (256 x 256 x 3 x 16)/forward/CPU/Reactant
2216501128
ns2263350697
ns0.98
ViT small (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :before_enzyme)
2196805969
ns2217766749
ns0.99
ViT small (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :only_enzyme)
3556647163
ns3470178449
ns1.02
ViT small (256 x 256 x 3 x 16)/forward/CPU/Lux
5559034960
ns7784948885.5
ns0.71
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :after_enzyme)
1242324757
ns1267787779
ns0.98
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Reactant
1298352031
ns1334201675
ns0.97
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :before_enzyme)
1230035861
ns1233375595
ns1.00
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :only_enzyme)
2637986128
ns2426265268
ns1.09
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Lux
52652664
ns50717982
ns1.04
ViT small (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :after_enzyme)
3060315768
ns3180815831
ns0.96
ViT small (256 x 256 x 3 x 32)/forward/CPU/Reactant
3106069884
ns3006942334
ns1.03
ViT small (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :before_enzyme)
3053865991
ns3048786017
ns1.00
ViT small (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :only_enzyme)
4567618226
ns4420144603
ns1.03
ViT small (256 x 256 x 3 x 32)/forward/CPU/Lux
9483960261
ns8266182250
ns1.15
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :after_enzyme)
1231844420
ns1289431106
ns0.96
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Reactant
1232961844
ns1307821758
ns0.94
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :before_enzyme)
1246778659.5
ns1319155148
ns0.95
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :only_enzyme)
2387803469
ns2570243985
ns0.93
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Lux
70768943
ns68121207.5
ns1.04
ViT base (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :after_enzyme)
3264057828
ns3184641683
ns1.02
ViT base (256 x 256 x 3 x 16)/forward/CPU/Reactant
3289278023
ns3196688266
ns1.03
ViT base (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :before_enzyme)
3264052473
ns3219193931
ns1.01
ViT base (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :only_enzyme)
4733831239
ns4600542400
ns1.03
ViT base (256 x 256 x 3 x 16)/forward/CPU/Lux
10856363466
ns14366625373
ns0.76
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :after_enzyme)
1204313355
ns1248144802
ns0.96
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Reactant
1195727515.5
ns1280560424
ns0.93
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :before_enzyme)
1220121107.5
ns1260333857
ns0.97
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :only_enzyme)
2407152921
ns2541156555
ns0.95
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Lux
20638923
ns19634575
ns1.05
ViT base (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :after_enzyme)
1946630937
ns1915886353
ns1.02
ViT base (256 x 256 x 3 x 4)/forward/CPU/Reactant
1945684183
ns1903714614
ns1.02
ViT base (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :before_enzyme)
1942898142
ns1892177049
ns1.03
ViT base (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :only_enzyme)
3272416211
ns3107063618
ns1.05
ViT base (256 x 256 x 3 x 4)/forward/CPU/Lux
3630039016.5
ns3075524538.5
ns1.18
This comment was automatically generated by workflow using github-action-benchmark.