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

Make use of boost container custimization #3638

Closed
fweik opened this issue Apr 7, 2020 · 0 comments · Fixed by #4414
Closed

Make use of boost container custimization #3638

fweik opened this issue Apr 7, 2020 · 0 comments · Fixed by #4414
Labels
Core Improvement Performance

Comments

@fweik
Copy link
Contributor

fweik commented Apr 7, 2020

Make the bond and exclusion lists in Particle smaller by using customization options, which are available starting from boost 1.67.
@jngrad jngrad mentioned this issue Jul 27, 2021
Merged
kodiakhq bot added a commit that referenced this issue Jul 28, 2021
@kodiakhq
Bump version requirements (#4312)
1d27884 
Description of changes:
- require Python 3.7+, scipy 1.4.0+, numpy 1.17.4+ (as per #3421, fixes #4258)
- require Boost 1.69+ (enables #3638)
- remove OpenSUSE job from CI (Leap 15.3 doesn't package Python3 and Boost, Leap 15.2 is outdated)
This was referenced Mar 17, 2022
Closed
Merged
@kodiakhq kodiakhq bot closed this as completed in #4414 Mar 28, 2022
kodiakhq bot added a commit that referenced this issue Mar 28, 2022
@kodiakhq
Reduce MPI communication overhead (#4414)
4a5022a 
Fixes #4415, fixes #3638

Description of changes:
- mark classes `Utils::Array`, `Utils::Vector` and `Utils::Quaternion` as MPI datatypes and bitwise serializable
- remove MPI communication overhead for `Utils::Vector` and `Particle` by removing tracking information and metadata
- check in unit tests that all `Particle` substructs are bitwise serializable
- use compact vectors for the bond list and exclusion list

For a LJ fluid simulation, the speed-up is around 8% on maxset configuration and 3% on empty configuration.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Core Improvement Performance
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Reduce MPI communication overhead jngrad/espresso
1 participant
@fweik