[mpich-discuss] Preloading the libraries "LD_PRELOAD" Effect
zhouh at anl.gov
Wed Apr 22 11:44:53 CDT 2020
“LD_PRELOAD” mainly is used to tell dynamic linker to pre-bind symbols rather than to cache the loading. I don’t think it can gain you the benefits as you described.
As for tips for accelerating parallel programs, that is too broad a topic. Any tips I gave here would be just some random tips that may or may not be relevant to you. If you describe your actual applications, we may be able to give some more specific tips.
From: Kihang Youn via discuss <discuss at mpich.org>
Reply-To: "discuss at mpich.org" <discuss at mpich.org>
Date: Tuesday, April 21, 2020 at 11:26 PM
To: "discuss at mpich.org" <discuss at mpich.org>
Cc: Kihang Youn <kyoun at lenovo.com>
Subject: [mpich-discuss] Preloading the libraries "LD_PRELOAD" Effect
I'd like to know about the MPICH mpirun environment option "LD_PRELOAD".
Is the function of this option used to put the library on Cache (or RAM?) at startup and to gain benefits from multiple calls?
3. For Fortran programs, you must also modify LD_PRELOAD
Our team is looking for a way to load the library used by programs running through the "vmtouch" into the cache when performing the model, and we would like to know if it can be implemented through the "LD_PRELOAD" option.
The second question may be a lazy one.
Is there any options on tuning factor that can adjust parallel performance with MPICH?
I'm actually only familiar with using MPI because I'm a newbie and I don't know much about performance enhancement, but I'm going to organize the list of recommendable performance-related options with MPICH and test them, so I'd like to know if there's anything organized(PDF or URL or something).
Kihang Youn(윤기항) - Application Analyst | Lenovo DCG Professional Services
E-mail: kyoun at lenovo.com
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the discuss