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

make memory a parameter #215

Open
JavierCladellas opened this issue Jan 17, 2025 · 0 comments · May be fixed by #218
Open

make memory a parameter #215

JavierCladellas opened this issue Jan 17, 2025 · 0 comments · May be fixed by #218
Assignees
Labels
benchmarking Issues related to benchmarking enhancement A new feature or request hpc High-performance computing related

Comments

@JavierCladellas
Copy link
Collaborator

The number of allocated nodes should also be determined from the application memory, depending on other parameters.

E.g. If the thermal-bridged M3 - P3 case takes 1Tb of memory, and each node has 256Gb and we want to run on 128 tasks, then distribute the tasks on 5 nodes ( tasks per node: 26, 26, 26, 26, 24) .

Example params for [P2-P3] - [M2,M3] cartesian product:

{
"name" : "discretization",
"sequence":[
  {
    "M":2,
    "P":2,
    "mem":"250G"
  },
  {
    "M":2,
    "P":3,
    "mem":"500G"
  },
  {
    "M":3,
    "P":2,
    "mem":"400G"
  },
  {
    "M":3,
    "P":3,
    "mem":"1T"
  },
]
}
@JavierCladellas JavierCladellas added benchmarking Issues related to benchmarking enhancement A new feature or request hpc High-performance computing related labels Jan 17, 2025
@JavierCladellas JavierCladellas self-assigned this Jan 17, 2025
JavierCladellas added a commit that referenced this issue Jan 17, 2025
JavierCladellas added a commit that referenced this issue Jan 20, 2025
JavierCladellas added a commit that referenced this issue Jan 20, 2025
JavierCladellas added a commit that referenced this issue Jan 20, 2025
JavierCladellas added a commit that referenced this issue Jan 20, 2025
JavierCladellas added a commit that referenced this issue Jan 20, 2025
JavierCladellas added a commit that referenced this issue Jan 20, 2025
JavierCladellas added a commit that referenced this issue Jan 21, 2025
JavierCladellas added a commit that referenced this issue Jan 21, 2025
JavierCladellas added a commit that referenced this issue Jan 21, 2025
JavierCladellas added a commit that referenced this issue Jan 22, 2025
JavierCladellas added a commit that referenced this issue Jan 22, 2025
(sets nodes = tasks if no tasks_per_node specified...rfm bug?)
@JavierCladellas JavierCladellas linked a pull request Jan 22, 2025 that will close this issue
10 tasks
@JavierCladellas JavierCladellas linked a pull request Jan 22, 2025 that will close this issue
10 tasks
JavierCladellas added a commit that referenced this issue Jan 22, 2025
JavierCladellas added a commit that referenced this issue Jan 23, 2025
…d job result (status)

( This will change upon report lib refactoring )
JavierCladellas added a commit that referenced this issue Jan 23, 2025
JavierCladellas added a commit that referenced this issue Jan 23, 2025
(this should be calculated by the scheduler
JavierCladellas added a commit that referenced this issue Jan 23, 2025
JavierCladellas added a commit that referenced this issue Jan 23, 2025
JavierCladellas added a commit that referenced this issue Jan 30, 2025
JavierCladellas added a commit that referenced this issue Feb 6, 2025
JavierCladellas added a commit that referenced this issue Feb 7, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
benchmarking Issues related to benchmarking enhancement A new feature or request hpc High-performance computing related
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant