Changes for page Benchmarking
Last modified by paulapopa on 2022/10/04 08:19
Summary
-
Page properties (1 modified, 0 added, 0 removed)
Details
- Page properties
-
- Content
-
... ... @@ -12,11 +12,12 @@ 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 + 15 15 |=(% scope="row" %)((( 16 16 Model 17 17 )))|=((( 18 18 Sim length (s) 19 -)))|= Regions|=Nr simulations|=Nr workers|=Execution time (hh:mm)20 +)))|=Nodes|=Nr simulations|=Nr workers|=Execution time (hh:mm) 20 20 |=MontbrioPazoRoxin|30|100|((( 21 21 30 22 22 )))|30|00:17 ... ... @@ -27,30 +27,31 @@ 27 27 |=MontbrioPazoRoxin|30|100|500|55|01:30 28 28 |=MontbrioPazoRoxin|30|100|600|55|01:45 29 29 |=MontbrioPazoRoxin|30|100|600|60|OOM 30 -|=MontbrioPazoRoxin|60|100|500| 40|(((31 - 03:0731 +|=MontbrioPazoRoxin|60|100|500|55|((( 32 +OOM 32 32 ))) 33 -|(% scope="row" %)**MontbrioPazoRoxin**|60|100|500|55|OOM 34 -|= |= |= |= |= |= 35 -|= | | | | | 36 -|= | | | | | 37 -|= | | | | | 38 -|= | | | | | 39 -|= | | | | | 40 -|= | | | | | 41 -|= | | | | | 42 -|= | | | | | 43 -|= | | | | | 44 -|= | | | | | 45 -|= | | | | | 34 +| | | | | | 35 +| | | | | | 36 +| | | | | | 37 +| | | | | | 38 +| | | | | | 39 +| | | | | | 40 +| | | | | | 41 +| | | | | | 42 +| | | | | | 43 +| | | | | | 44 +| | | | | | 45 +| | | | | | 46 +| | | | | | 47 +| | | | | | 48 +| | | | | | 46 46 47 -==== ==== 48 48 49 49 ==== 2. Limitations ==== 50 50 51 51 * Reaching he memory limit on the CSCS node. 52 -** For a simulation of 30 seconds, we can fit 55 parallel workers in the available memory 53 -** For a simulation of 60 seconds, we can fit 40 parallel workers in the available memory 54 +** For a simulation of 30 seconds, we can fit 55 parallel workers in the available memory. 55 +** For a simulation of 60 seconds, we can fit 40 parallel workers in the available memory. 54 54 * Reaching the maximum connections on CSCS could happen during a run 55 55 ** connect once to launch the job 56 56 ** connect multiple times during the monitoring step to check the status of the job