Skip to content

Update detray to v0.100.0 [CI TEST] #1027

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

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

stephenswat
Copy link
Member

This commit updates detray to version 0.100.0 which should significantly improve performance.

@stephenswat stephenswat added the build This relates to the build system label Jun 19, 2025
@stephenswat stephenswat changed the title Update detray to v0.100.0 Update detray to v0.100.0 [CI TEST] Jun 19, 2025
This commit updates detray to version 0.100.0 which should significantly
improve performance.
@stephenswat stephenswat force-pushed the build/detray_0_100_0 branch from 6a84c9f to d2d4c43 Compare June 19, 2025 11:19
Copy link

@stephenswat
Copy link
Member Author

Performance summary

Here is a summary of the performance effects of this PR:

Graphical

Tabular

Kernel 8c39659 d2d4c43 Delta
fit_forward 109.64 ms 88.97 ms -18.9%
propagate_to_next_surface 69.84 ms 62.82 ms -10.0%
fit_backward 53.70 ms 39.44 ms -26.6%
count_triplets 14.24 ms 14.23 ms -0.0%
find_triplets 6.02 ms 6.00 ms -0.2%
find_tracks 4.29 ms 4.29 ms 0.0%
fit_prelude 1.12 ms 1.12 ms 0.2%
find_doublets 896.29 μs 907.22 μs 1.2%
ccl_kernel 871.93 μs 869.33 μs -0.3%
count_doublets 619.58 μs 616.27 μs -0.5%
select_seeds 360.40 μs 358.84 μs -0.4%
Thrust::sort 271.93 μs 271.45 μs -0.2%
build_tracks 193.09 μs 193.34 μs 0.1%
update_triplet_weights 100.27 μs 100.12 μs -0.1%
DeviceRadixSortHistogramKernel 98.06 μs 98.01 μs -0.0%
apply_interaction 63.81 μs 63.83 μs 0.0%
DeviceRadixSortOnesweepKernel 54.73 μs 54.72 μs -0.0%
fill_sort_keys 44.70 μs 44.66 μs -0.1%
estimate_track_params 34.36 μs 34.33 μs -0.1%
populate_grid 30.38 μs 30.45 μs 0.2%
count_grid_capacities 29.09 μs 29.10 μs 0.0%
unknown 20.57 μs 20.49 μs -0.4%
form_spacepoints 12.60 μs 12.51 μs -0.7%
reduce_triplet_counts 6.68 μs 6.68 μs -0.1%
make_barcode_sequence 1.02 μs 1.02 μs 0.0%
DeviceRadixSortExclusiveSumKernel 513.09 ns 513.64 ns 0.1%
fill_prefix_sum 165.41 ns 165.43 ns 0.0%
Total 262.54 ms 220.59 ms -16.0%

Important

All metrics in this report are given as reciprocal throughput, not as wallclock runtime.

Note

This is an automated message produced on the explicit request of a human being.

@stephenswat
Copy link
Member Author

Nice. 😎

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
build This relates to the build system
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant