Skip to content

Switch back to using LDS in func_broad_phase kernel.#56

Open
chien-an-chen wants to merge 1 commit intoamd-integrationfrom
perf/chienach/lds_broad_phase_without_clear_collision_normal_cache
Open

Switch back to using LDS in func_broad_phase kernel.#56
chien-an-chen wants to merge 1 commit intoamd-integrationfrom
perf/chienach/lds_broad_phase_without_clear_collision_normal_cache

Conversation

@chien-an-chen
Copy link
Copy Markdown

@chien-an-chen chien-an-chen commented Apr 30, 2026

Summary
Switch back to using LDS in func_broad_phase kernel. cherry-pick from 77c421b

Add more optimization:

  1. Change to use lds_sort_packed to store i_g and is_max.
  2. Remove duplicate checking max_a_axis < min_b0

change to use lds_sort_packed to store i_g and is_max.
lds_active no longer copy data from collider_state.active_buffer for init.

only copy lds_sort_value to collider_state.sort_buffer.value when
use_hibernation=True.
@chien-an-chen
Copy link
Copy Markdown
Author

/run-ci

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant