Skip to content

Commit

Permalink
Prefetch clang lazy artifact
Browse files Browse the repository at this point in the history
  • Loading branch information
@Pangoraw
Pangoraw committed Oct 28, 2024
1 parent adaf47f commit c071271
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion .github/workflows/regenerate-mlir-bindings.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ jobs:
run: |
import Pkg
Pkg.add("JuliaFormatter")
- run: julia --project=. -e 'using Pkg; pkg"instantiate"; pkg"update"; pkg"precompile"'
- run: julia --project=. -e 'using Pkg; pkg"instantiate"; pkg"update"; pkg"precompile"; using Clang; Clang.JLLEnvs.get_system_includes()'
working-directory: ./deps/ReactantExtra
env:
JULIA_DEPOT_PATH: ${{ runner.temp }}/julia_depot
Expand Down

1 comment on commit c071271

@github-actions
Copy link
Contributor

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: c071271 Previous: adaf47f Ratio
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :after_enzyme) 1346072366 ns 1326790352 ns 1.01
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Reactant 1329447509 ns 1363362852 ns 0.98
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :before_enzyme) 1307398450 ns 1264158724 ns 1.03
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :only_enzyme) 2616692459 ns 2512944686 ns 1.04
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Lux 220907885 ns 208866219 ns 1.06
ViT base (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :after_enzyme) 7159620815 ns 6203466975 ns 1.15
ViT base (256 x 256 x 3 x 32)/forward/CPU/Reactant 5148165106 ns 5277032832 ns 0.98
ViT base (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :before_enzyme) 5116900190 ns 5437726666 ns 0.94
ViT base (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :only_enzyme) 6688643556 ns 7202793079 ns 0.93
ViT base (256 x 256 x 3 x 32)/forward/CPU/Lux 33451876662 ns 30686367467 ns 1.09
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :after_enzyme) 1543361668 ns 1548259631 ns 1.00
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Reactant 1296707129.5 ns 1293145577 ns 1.00
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :before_enzyme) 1314183460.5 ns 1337591055.5 ns 0.98
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :only_enzyme) 2540794836 ns 2595368361 ns 0.98
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Lux 8640674 ns 8732091 ns 0.99
ViT small (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :after_enzyme) 1570842065 ns 1617855952 ns 0.97
ViT small (256 x 256 x 3 x 4)/forward/CPU/Reactant 1571704575 ns 1614775455 ns 0.97
ViT small (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :before_enzyme) 1566452731 ns 1588884622 ns 0.99
ViT small (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :only_enzyme) 2748308764 ns 2866251207 ns 0.96
ViT small (256 x 256 x 3 x 4)/forward/CPU/Lux 2904831857 ns 2293819764 ns 1.27
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :after_enzyme) 1271376697.5 ns 1300327322 ns 0.98
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Reactant 1292114763 ns 1315833068.5 ns 0.98
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :before_enzyme) 1287030291.5 ns 1292237616 ns 1.00
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :only_enzyme) 2688383854 ns 2562151867 ns 1.05
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Lux 22713679.5 ns 22724451 ns 1.00
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :after_enzyme) 2126498296 ns 2206811606 ns 0.96
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Reactant 2152227554 ns 2274548394 ns 0.95
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :before_enzyme) 2115369108 ns 2223046136 ns 0.95
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :only_enzyme) 3347806867 ns 3510804330 ns 0.95
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Lux 6364245448 ns 5720188106.5 ns 1.11
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :after_enzyme) 1325175460 ns 1256821950.5 ns 1.05
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Reactant 1300015882.5 ns 1288170988 ns 1.01
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :before_enzyme) 1305493220 ns 1367705731.5 ns 0.95
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :only_enzyme) 2607501634 ns 2729390029 ns 0.96
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Lux 7033888 ns 7144976 ns 0.98
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :after_enzyme) 1463105950 ns 1457145407 ns 1.00
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Reactant 1451403205 ns 1449213894 ns 1.00
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :before_enzyme) 1425460590 ns 1453063995 ns 0.98
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :only_enzyme) 2668761981 ns 2689643346 ns 0.99
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Lux 1096721461 ns 1312702814 ns 0.84
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :after_enzyme) 1311636450 ns 1311294949.5 ns 1.00
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Reactant 1337267407 ns 1329881753 ns 1.01
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :before_enzyme) 1347845402.5 ns 1290636649 ns 1.04
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :only_enzyme) 2884646614 ns 2612367052 ns 1.10
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Lux 12312923 ns 12328771 ns 1.00
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :after_enzyme) 1729459837 ns 1758712756 ns 0.98
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Reactant 1726720273 ns 1757425385 ns 0.98
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :before_enzyme) 1727102285 ns 1735235563 ns 1.00
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :only_enzyme) 2966098081 ns 3025181128 ns 0.98
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Lux 3508350121 ns 2744388846 ns 1.28
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :after_enzyme) 1322022902 ns 1329494416 ns 0.99
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Reactant 1285772923 ns 1315875781 ns 0.98
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :before_enzyme) 1305829828.5 ns 1273853570 ns 1.03
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :only_enzyme) 2620764003 ns 2397785960 ns 1.09
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Lux 27355686 ns 27299308 ns 1.00
ViT small (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :after_enzyme) 2213433122 ns 2231661762 ns 0.99
ViT small (256 x 256 x 3 x 16)/forward/CPU/Reactant 2197052471 ns 2228700161 ns 0.99
ViT small (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :before_enzyme) 2180243964 ns 2215196278 ns 0.98
ViT small (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :only_enzyme) 3427813806 ns 3518199375 ns 0.97
ViT small (256 x 256 x 3 x 16)/forward/CPU/Lux 5437385449.5 ns 6951126916 ns 0.78
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :after_enzyme) 1271922231 ns 1313658125 ns 0.97
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Reactant 1265911189 ns 1209300000 ns 1.05
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :before_enzyme) 1321677112.5 ns 1289065003 ns 1.03
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Reactant (optimize = :only_enzyme) 2573788194 ns 2580296701 ns 1.00
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Lux 52828053.5 ns 52804211 ns 1.00
ViT small (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :after_enzyme) 2988327264 ns 3039672304 ns 0.98
ViT small (256 x 256 x 3 x 32)/forward/CPU/Reactant 2979341995 ns 3081374573 ns 0.97
ViT small (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :before_enzyme) 2989964585 ns 3055647227 ns 0.98
ViT small (256 x 256 x 3 x 32)/forward/CPU/Reactant (optimize = :only_enzyme) 4306275320 ns 4441886641 ns 0.97
ViT small (256 x 256 x 3 x 32)/forward/CPU/Lux 11352990940 ns 9554521564 ns 1.19
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :after_enzyme) 1263156495 ns 1220435809 ns 1.04
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Reactant 1245875427 ns 1258545982 ns 0.99
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :before_enzyme) 1262324857.5 ns 1279515211 ns 0.99
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Reactant (optimize = :only_enzyme) 2528756885 ns 2543547035 ns 0.99
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Lux 70902097.5 ns 71048313 ns 1.00
ViT base (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :after_enzyme) 3144430262 ns 3328025653 ns 0.94
ViT base (256 x 256 x 3 x 16)/forward/CPU/Reactant 3135646302 ns 3733324934 ns 0.84
ViT base (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :before_enzyme) 3120408939 ns 3424995362 ns 0.91
ViT base (256 x 256 x 3 x 16)/forward/CPU/Reactant (optimize = :only_enzyme) 4465736172 ns 4557583299 ns 0.98
ViT base (256 x 256 x 3 x 16)/forward/CPU/Lux 12927829683 ns 14822133310 ns 0.87
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :after_enzyme) 1251790538 ns 1217458774 ns 1.03
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Reactant 1229488589 ns 1284792522.5 ns 0.96
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :before_enzyme) 1247143102 ns 1286126304 ns 0.97
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Reactant (optimize = :only_enzyme) 2564237277 ns 2557926161 ns 1.00
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Lux 20781327 ns 20801582.5 ns 1.00
ViT base (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :after_enzyme) 1852976170 ns 1859646875 ns 1.00
ViT base (256 x 256 x 3 x 4)/forward/CPU/Reactant 1867441413 ns 1856108900 ns 1.01
ViT base (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :before_enzyme) 1854228561 ns 1847421552 ns 1.00
ViT base (256 x 256 x 3 x 4)/forward/CPU/Reactant (optimize = :only_enzyme) 3063066781 ns 3058721860 ns 1.00
ViT base (256 x 256 x 3 x 4)/forward/CPU/Lux 3181672566 ns 3441868405 ns 0.92

This comment was automatically generated by workflow using github-action-benchmark.

Please sign in to comment.