Attention: The Collaboratory IAM will down for up to 1 hour on today, the 8th of July 2025 starting from 4.30pm CEST (my timezone) for up to 1 hour. Any and all services, which require a user login with an EBRAINS account, will be un-available during that time

Warning: The EBRAINS Drive and EBRAINS Lab will down on Tuesday, the 8th of July 2025 starting from 5pm CEST (my timezone) for up to 1 hour.


Changes for page Benchmarking

Last modified by paulapopa on 2022/10/04 08:19

From version 4.1
edited by paulapopa
on 2022/08/03 16:00
Change comment: There is no comment for this version
To version 1.1
edited by paulapopa
on 2022/08/03 15:01
Change comment: There is no comment for this version

Summary

Details

Page properties
Content
... ... @@ -1,5 +1,6 @@
1 1  == WIP ==
2 2  
3 +(% class="wikigeneratedid" %)
3 3  == TVB-INVERSION 1.0.0 ==
4 4  
5 5  === Sampling priors - Remote execution ===
... ... @@ -12,12 +12,11 @@
12 12  
13 13  These have been computed on DAINT-CSCS HPC, on a single node, with different configurations for the number of simulations and the number of workers.
14 14  
15 -
16 16  |=(% scope="row" %)(((
17 17  Model
18 18  )))|=(((
19 19  Sim length (s)
20 -)))|=Regions|=Nr simulations|=Nr workers|=Execution time (hh:mm)
20 +)))|=Nodes|=Nr simulations|=Nr workers|=Execution time (hh:mm)
21 21  |=MontbrioPazoRoxin|30|100|(((
22 22  30
23 23  )))|30|00:17
... ... @@ -31,21 +31,6 @@
31 31  |=MontbrioPazoRoxin|60|100|500|55|(((
32 32  OOM
33 33  )))
34 -| | | | | |
35 -| | | | | |
36 -| | | | | |
37 -| | | | | |
38 -| | | | | |
39 -| | | | | |
40 -| | | | | |
41 -| | | | | |
42 -| | | | | |
43 -| | | | | |
44 -| | | | | |
45 -| | | | | |
46 -| | | | | |
47 -| | | | | |
48 -| | | | | |
49 49  
50 50  ==== ====
51 51  
... ... @@ -52,8 +52,8 @@
52 52  ==== 2. Limitations ====
53 53  
54 54  * Reaching he memory limit on the CSCS node.
55 -** For a simulation of 30 seconds, we can fit 55 parallel workers in the available memory
56 -** For a simulation of 60 seconds, we can fit 40 parallel workers in the available memory
40 +** For a simulation of 30 seconds, we can fit 55 parallel workers in the available memory.
41 +** For a simulation of 60 seconds, we can fit 40 parallel workers in the available memory.
57 57  * Reaching the maximum connections on CSCS could happen during a run
58 58  ** connect once to launch the job
59 59  ** connect multiple times during the monitoring step to check the status of the job
Public

TVB Inversion