From: Gerald Keller (gerald.keller_at_uni-wuerzburg.de)
Date: Thu Mar 19 2020 - 11:21:26 CDT
Hi Stefano,
I played around with the same issue.
You will only be able to run 2 namd instances on the same machine with no performence loss if your used cores are on different sockets.
In your case cores 0-15 should be on socket 1 and cores 32-47 on socket 2, respectivley. If you only have 1 socket I wouldn't reccomend to run more than 1 namd instance per node.
Best,
Gerald
>>> Stefano Guglielmo <stefano.guglielmo_at_unito.it> 19.03.20 17.00 Uhr >>>
Dear all,
thanks for your advice and sorry for my late reply. I finally managed to optimize performance for a single simulation.
Now I am trying to run two simulations in parallel using NAMD 2.13 multicore-CUDA version. I used the following option to run the two simulations:
+p16 +idlepoll +setcpuaffinity +devices 0 +pemap 0-15
and
+p16 +idlepoll +setcpuaffinity +devices 1 +pemap 32-47.
For two systems of comparable dimension I observed a sizeable performance loss when starting the second simulation (from 0.017 s/step to 0.028 s/step). In your opinion is this reasonable or shall I tune some options differently/use a different version of NAMD?
Thanks in advance for sharing advice,
all the best
Stefano
Il giorno gio 5 mar 2020 alle ore 22:03 Josh Vermaas <joshua.vermaas_at_gmail.com> ha scritto:
Don't forget to compare against multicore builds. On one node with shared memory, those builds often win for maximum 1 gpu throughput. Since you have 2 on the same node, an smp build without communication threads may win.Josh
On Thu, Mar 5, 2020, 10:23 AM Victor Kwan <vkwan8_at_uwo.ca> wrote:
Hi Stefano,
Since you already have a system in mind, you can compare the time it takes to perform a 10ps simulation with different setups.
> one or both gpu, number of cores
* With NAMD 2.13 comes a large improvement in dual gpu/single node performance and we observe almost linear scaling when going from 1 to 2 GPUs.
* 16core/GPU is sufficient, from our experience 6-8core/GPU is the lower limit.
* For GPU runs, hyperthreading should not increase affect performance.
> pemap/commap options
* check the output of nvidia-smi topo matrix - leaving cpu/gpu affinity as default should be fine.
On Thu, Mar 5, 2020 at 10:12 AM Stefano Guglielmo <stefano.guglielmo_at_unito.it> wrote:
Dear NAMD users,
I am using a workstation with an AMD Ryzen Threadripper 2990WX 32-Core Processor, 128 GB RAM and two RTX 2080 Ti cards with NVlink; I am here to ask for suggestions on what could be the "best" options to run a single simulation on a 200K atom system with NAMD 2.13 (one or both gpu, number of cores, hyperthreading or not, pemap/commap options...)
Thanks in advance for your time
Stefano
--
Stefano GUGLIELMO PhD
Assistant Professor of Medicinal Chemistry
Department of Drug Science and Technology
Via P. Giuria 9
10125 Turin, ITALY
ph. +39 (0)11 6707178
Mail priva di virus. www.avast.com
-- Stefano GUGLIELMO PhD Assistant Professor of Medicinal Chemistry Department of Drug Science and Technology Via P. Giuria 9 10125 Turin, ITALY ph. +39 (0)11 6707178
This archive was generated by hypermail 2.1.6 : Thu Dec 31 2020 - 23:17:13 CST