Skip to content

Commit

Permalink
don't build rocm
Browse files Browse the repository at this point in the history
  • Loading branch information
William Moses committed Oct 2, 2024
1 parent 55ce2cd commit 4f4cb40
Showing 1 changed file with 0 additions and 1 deletion.
1 change: 0 additions & 1 deletion deps/ReactantExtra/BUILD
Original file line number Diff line number Diff line change
Expand Up @@ -367,7 +367,6 @@ cc_library(
] + select({
"@xla//xla/tsl:is_cuda_enabled_and_oss":[
"@xla//xla/stream_executor/cuda:all_runtime",
"@xla//xla/stream_executor/rocm:all_runtime",
"@xla//xla/service/gpu/model:hlo_op_profiles",
"@xla//xla/service/gpu/model:hlo_op_profile_proto_cc_impl",
"@xla//xla/service/gpu:nvptx_compiler",
Expand Down

1 comment on commit 4f4cb40

@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: 4f4cb40 Previous: 55ce2cd Ratio
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Reactant 1427801876 ns 1511306590 ns 0.94
ViT base (256 x 256 x 3 x 32)/forward/CUDA/Lux 241937991 ns 220630508 ns 1.10
ViT base (256 x 256 x 3 x 32)/forward/CPU/Reactant 5706546145 ns 6086790888 ns 0.94
ViT base (256 x 256 x 3 x 32)/forward/CPU/Lux 19592540088 ns 20987570101 ns 0.93
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Reactant 1367040220.5 ns 1442706109 ns 0.95
ViT small (256 x 256 x 3 x 4)/forward/CUDA/Lux 8765018 ns 8958787 ns 0.98
ViT small (256 x 256 x 3 x 4)/forward/CPU/Reactant 1617045921.5 ns 1759361667 ns 0.92
ViT small (256 x 256 x 3 x 4)/forward/CPU/Lux 2228339749.5 ns 2171845551 ns 1.03
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Reactant 1369778487.5 ns 1513155642 ns 0.91
ViT tiny (256 x 256 x 3 x 32)/forward/CUDA/Lux 95384074 ns 88431013 ns 1.08
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Reactant 2267863268 ns 2209228872 ns 1.03
ViT tiny (256 x 256 x 3 x 32)/forward/CPU/Lux 4660275687.5 ns 7276493924.5 ns 0.64
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Reactant 1374725656.5 ns 1391234101.5 ns 0.99
ViT tiny (256 x 256 x 3 x 4)/forward/CUDA/Lux 7919007 ns 8028951 ns 0.99
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Reactant 1523146334.5 ns 1463259455 ns 1.04
ViT tiny (256 x 256 x 3 x 4)/forward/CPU/Lux 1657446563 ns 1505466535.5 ns 1.10
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Reactant 1293396969 ns 1395090007.5 ns 0.93
ViT tiny (256 x 256 x 3 x 16)/forward/CUDA/Lux 84573801 ns 91438172.5 ns 0.92
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Reactant 1829891224 ns 1750380825 ns 1.05
ViT tiny (256 x 256 x 3 x 16)/forward/CPU/Lux 3023920644 ns 2588957726 ns 1.17
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Reactant 1292433719 ns 1353809315 ns 0.95
ViT small (256 x 256 x 3 x 16)/forward/CUDA/Lux 88498026 ns 96514528 ns 0.92
ViT small (256 x 256 x 3 x 16)/forward/CPU/Reactant 2315496105 ns 2235469049 ns 1.04
ViT small (256 x 256 x 3 x 16)/forward/CPU/Lux 4181219607 ns 3644458748 ns 1.15
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Reactant 1367617841 ns 1342936571 ns 1.02
ViT small (256 x 256 x 3 x 32)/forward/CUDA/Lux 113824695 ns 119408913 ns 0.95
ViT small (256 x 256 x 3 x 32)/forward/CPU/Reactant 3118475424 ns 3018633262 ns 1.03
ViT small (256 x 256 x 3 x 32)/forward/CPU/Lux 6707702872 ns 10685489431 ns 0.63
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Reactant 1342010577 ns 1414936998 ns 0.95
ViT base (256 x 256 x 3 x 16)/forward/CUDA/Lux 129882165.5 ns 143053914 ns 0.91
ViT base (256 x 256 x 3 x 16)/forward/CPU/Reactant 3304575961 ns 3250590467 ns 1.02
ViT base (256 x 256 x 3 x 16)/forward/CPU/Lux 9641559937 ns 7186489751 ns 1.34
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Reactant 1318534127.5 ns 1435836062 ns 0.92
ViT base (256 x 256 x 3 x 4)/forward/CUDA/Lux 87600441 ns 90822248.5 ns 0.96
ViT base (256 x 256 x 3 x 4)/forward/CPU/Reactant 1971771485 ns 1897964660 ns 1.04
ViT base (256 x 256 x 3 x 4)/forward/CPU/Lux 2525837503 ns 2611187269 ns 0.97

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

Please sign in to comment.