|
[Sponsors] |
Number of CPU cores used does not increase speed! |
|
LinkBack | Thread Tools | Search this Thread | Display Modes |
September 24, 2021, 08:47 |
Number of CPU cores used does not increase speed!
|
#1 |
New Member
adad
Join Date: Sep 2021
Posts: 3
Rep Power: 4 |
Hello,
We bought an new computer for CFX calculations. It has an AMD Threadripper 32 core processor and 256Gb 3600Mhz DDR4 Ram. When I test the speed performance of each simulation, it is the same using 32 partitions or 64, even 20 partitions runs at the same speed. I have tried to disable SMT mode and this did not help either. I also tested to run two simulations on the same time, each using 32 cores each. This resulted that each simulation would take 2x longer time. Anyone know what the problem might be? |
|
September 24, 2021, 11:17 |
|
#2 |
Senior Member
Join Date: Jun 2009
Posts: 1,815
Rep Power: 32 |
Check with ANSYS CFX support and they should be able to stir you in the right direction.
Warning: do not expect linear scalability (for any software in general) to the full number of cores on these processors. I do not recall if the Threadripper has 64 real CPU cores, 32 real ones plus 32 virtual ones. In addition, if the memory bandwidth is not there, any software will waste time moving data between memory banks. It is not about the total memory available, but how it is distributed and allocated.
__________________
Note: I do not answer CFD questions by PM. CFD questions should be posted on the forum. |
|
September 24, 2021, 14:37 |
|
#3 | |
New Member
adad
Join Date: Sep 2021
Posts: 3
Rep Power: 4 |
Quote:
Threadripper has 32 cores, and 64 virtual. I turned of the virtual ones but this did not help. |
||
September 24, 2021, 21:17 |
|
#4 |
Super Moderator
Glenn Horrocks
Join Date: Mar 2009
Location: Sydney, Australia
Posts: 17,728
Rep Power: 143 |
If you do a speed-up test from 1x, 2x, 4x, 8x, 16x, 32x you will probably find that it speeds up nicely to 16x, but 32x does not give you much extra. This is pretty normal for running lots of cores in a single workstation. You will get better speedups at 16x and 32x by running across multiple workstations - but note you will need a high-end network interconnect to get good speed up here too. Ethernet is not good enough, 10G ethernet not much better; you will need infiniband or myranet or one of the those specialist interconnects.
In short - getting good speed up beyond about 16x requires careful planning and testing. You cannot just buy off the shelf stuff.
__________________
Note: I do not answer CFD questions by PM. CFD questions should be posted on the forum. |
|
September 25, 2021, 11:41 |
|
#5 | |
New Member
adad
Join Date: Sep 2021
Posts: 3
Rep Power: 4 |
Quote:
|
||
September 27, 2021, 12:03 |
|
#6 |
Senior Member
Join Date: Jun 2009
Posts: 1,815
Rep Power: 32 |
There is a reason why supercomputers (or high-end cluster) providers exist, it is not trivial (nor cheap) to build a high-performance computer machine.
__________________
Note: I do not answer CFD questions by PM. CFD questions should be posted on the forum. |
|
|
|
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
[snappyHexMesh] snappyHexMesh stuck when snap is turned on | yukuns | OpenFOAM Meshing & Mesh Conversion | 3 | February 2, 2021 13:05 |
[mesh manipulation] Mesh Refinement | Luiz Eduardo Bittencourt Sampaio (Sampaio) | OpenFOAM Meshing & Mesh Conversion | 42 | January 8, 2017 12:55 |
decomposePar -allRegions | stru | OpenFOAM Pre-Processing | 2 | August 25, 2015 03:58 |
simpleFoam parallel | AndrewMortimer | OpenFOAM Running, Solving & CFD | 12 | August 7, 2015 18:45 |
SigFpe when running ANY application in parallel | Pj. | OpenFOAM Running, Solving & CFD | 3 | April 23, 2015 14:53 |