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.

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

Small number of cores for partition #15464

Closed
fdkong opened this issue Jun 16, 2020 · 0 comments · Fixed by #15465
Closed

Small number of cores for partition #15464

fdkong opened this issue Jun 16, 2020 · 0 comments · Fixed by #15465
Labels
P: normal A defect affecting operation with a low possibility of significantly affects. T: task An enhancement to the software.

Comments

@fdkong
Copy link
Contributor

fdkong commented Jun 16, 2020

Reason

The number of cores for the graph partition can be different from that used
for mesh generation and simulation. Partitioners often become inefficient in
compute time when the number of cores is large (around 10,0000).

Design

A "fix" is to partition the graph using a small number of cores
when the mesh generation and the numerical simulation use a large number of processor cores.

Impact

None

@fdkong fdkong added T: task An enhancement to the software. P: normal A defect affecting operation with a low possibility of significantly affects. labels Jun 16, 2020
fdkong added a commit to fdkong/moose that referenced this issue Jun 16, 2020
The number of cores for the graph partition can be different from that used
for mesh generation and simulation. Partitioners often become inefficient in
compute time when the number of cores is large (around 10,0000).
A possible "fix" is to partition the graph using a small number of cores
when the mesh generation and the numerical simulation use a large number of processor cores.

Closes idaholab#15464
fdkong added a commit to fdkong/moose that referenced this issue Jun 16, 2020
The number of cores for the graph partition can be different from that used
for mesh generation and simulation. Partitioners often become inefficient in
compute time when the number of cores is large (around 10,0000).
A possible "fix" is to partition the graph using a small number of cores
when the mesh generation and the numerical simulation use a large number of processor cores.

Closes idaholab#15464
fdkong added a commit to fdkong/moose that referenced this issue Jun 16, 2020
The number of cores for the graph partition can be different from that used
for mesh generation and simulation. Partitioners often become inefficient in
compute time when the number of cores is large (around 10,0000).
A possible "fix" is to partition the graph using a small number of cores
when the mesh generation and the numerical simulation use a large number of processor cores.

Closes idaholab#15464
fdkong added a commit to fdkong/moose that referenced this issue Jun 17, 2020
The number of cores for the graph partition can be different from that used
for mesh generation and simulation. Partitioners often become inefficient in
compute time when the number of cores is large (around 10,0000).
A possible "fix" is to partition the graph using a small number of cores
when the mesh generation and the numerical simulation use a large number of processor cores.

Closes idaholab#15464
fdkong added a commit to fdkong/moose that referenced this issue Jun 17, 2020
The number of cores for the graph partition can be different from that used
for mesh generation and simulation. Partitioners often become inefficient in
compute time when the number of cores is large (around 10,0000).
A possible "fix" is to partition the graph using a small number of cores
when the mesh generation and the numerical simulation use a large number of processor cores.

Closes idaholab#15464
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
P: normal A defect affecting operation with a low possibility of significantly affects. T: task An enhancement to the software.
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant