Skip to content
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.

Sign up for GitHub

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

Jump to bottom

[Feature Request] support neighbor stat on GPUs #2619

Closed
njzjz opened this issue Jun 16, 2023 · 0 comments · Fixed by #2897
Closed

[Feature Request] support neighbor stat on GPUs #2619

njzjz opened this issue Jun 16, 2023 · 0 comments · Fixed by #2897
Assignees
@njzjz
Labels
enhancement

Comments

@njzjz
Copy link
Member

njzjz commented Jun 16, 2023

Summary

Currently, the neighbor stat is conducted in CPUs. It is slower than that on GPUs, but we do not have GPU implementation.

Detailed Description

The current neighbor stat code is

deepmd-kit/deepmd/utils/neighbor_stat.py

Lines 75 to 82 in 92ca097

_max_nbor_size, _min_nbor_dist = op_module.neighbor_stat(
place_holders["coord"],
t_type,
t_natoms,
place_holders["box"],
place_holders["default_mesh"],
rcut=self.rcut,
)

Ideally, parallelism in the dimension of the frames is also required to handle many structures.

Further Information, Files, and Links

No response
@njzjz njzjz self-assigned this Oct 4, 2023
@njzjz njzjz mentioned this issue Oct 4, 2023
Merged
@njzjz njzjz linked a pull request Oct 4, 2023 that will close this issue
support neighbor stat on GPUs #2897
Merged
wanghan-iapcm pushed a commit that referenced this issue Oct 7, 2023
@njzjz
support neighbor stat on GPUs (#2897)
da100dc 
Fix #2619.

The GPU implementation in this PR is usually faster than the CPU in one
thread (i.e., not using the feature implemented in #1624). Still, it
needs parallelism in the batch dimension, which is blocked by #2618,
regarding building the neighbor list. The GPU utilization is less than
10% for the water system. It should be improved when #2618 makes
progress.

---------

Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
@njzjz njzjz closed this as completed Oct 7, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@njzjz njzjz

Labels
enhancement
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

support neighbor stat on GPUs njzjz/deepmd-kit
1 participant
@njzjz