Modeling the Productivity of HPC Systems on a Computing Center Scale

2015 ◽  
pp. 358-375 ◽  
Author(s):  
Sandra Wienke ◽  
Hristo Iliev ◽  
Dieter an Mey ◽  
Matthias S. Müller
Keyword(s):  
Computing Center

Computer algebra: 4th International Conference Materials

2021 ◽  
Keyword(s):  
Exact Solution ◽  
Computer Science ◽  
Computer Algebra ◽  
Research Center ◽  
Dorodnicyn Computing ◽  
International Conference ◽  
Federal Research ◽  
Computing Center ◽  
And Control

The international conference is organized jointly by Dorodnicyn Computing Center of Federal Research Center “Computer Science and Control” of Russian Academy of Science and Peoples’ Friendship University of Russia. The talks presented at the conference discuss actual problems of computer algebra — the discipline whose algorithms are focused on the exact solution of mathematical and applied problems using a computer.

A Remote Monitoring System Based on Measuring Instrument Cloud

2014 ◽  
Vol 1014 ◽  
pp. 525-529 ◽  
Author(s):  
Jun Zhang ◽  
Yuan Sheng Liu ◽  
Lin Xue
Keyword(s):  
Cloud Computing ◽  
Monitoring System ◽  
Environmental Parameters ◽  
Mobile Terminal ◽  
Measuring Instrument ◽  
Remote Monitoring System ◽  
Front End ◽  
Remote Lab ◽  
Computing Center ◽  
Network Equipment

A remote lab room monitoring system based on measuring instrument cloud is presented in this paper. The system consists of cloud computing center, embedded front-end acquisition hardware, mobile terminal device, and network equipment. Measuring service software system located in cloud computing center sends control commands to front-end acquisition hardware and collects acquisition data. Then processing, analysis and integration of signals are completed in the cloud computing framework. Finally, all the information can be interacted with mobile terminals by Web service. The system can monitor environmental parameters of lab rooms located in different campuses, such as temperature, humidity, light, smoke, and flooding. When environmental parameters exceed the preset thresholds, light and audio alarms will be immediately switched on and the administrator will be noticed on Web management page.

Periodic hierarchical load balancing for large supercomputers

2011 ◽  
Vol 25 (4) ◽  
pp. 371-385 ◽  
Author(s):  
Gengbin Zheng ◽  
Abhinav Bhatelé ◽  
Esteban Meneses ◽  
Laxmikant V. Kalé
Keyword(s):  
Load Balancing ◽  
Large Scale ◽  
Parallel Machines ◽  
National Laboratory ◽  
Argonne National Laboratory ◽  
Parallel Applications ◽  
Scientific Application ◽  
Computing Center ◽  
Blue Gene ◽  
Advanced Computing

Large parallel machines with hundreds of thousands of processors are becoming more prevalent. Ensuring good load balance is critical for scaling certain classes of parallel applications on even thousands of processors. Centralized load balancing algorithms suffer from scalability problems, especially on machines with a relatively small amount of memory. Fully distributed load balancing algorithms, on the other hand, tend to take longer to arrive at good solutions. In this paper, we present an automatic dynamic hierarchical load balancing method that overcomes the scalability challenges of centralized schemes and longer running times of traditional distributed schemes. Our solution overcomes these issues by creating multiple levels of load balancing domains which form a tree. This hierarchical method is demonstrated within a measurement-based load balancing framework in Charm++. We discuss techniques to deal with scalability challenges of load balancing at very large scale. We present performance data of the hierarchical load balancing method on up to 16,384 cores of Ranger (at the Texas Advanced Computing Center) and 65,536 cores of Intrepid (the Blue Gene/P at Argonne National Laboratory) for a synthetic benchmark. We also demonstrate the successful deployment of the method in a scientific application, NAMD, with results on Intrepid.

Modification of the k-epsilon scheme and its application for describing turbulence in inland water bodies

2021 ◽  
Author(s):  
Irina Soustova ◽  
Yuliya Troitskaya ◽  
Daria Gladskikh
Keyword(s):  
Prandtl Number ◽  
Turbulent Mixing ◽  
Richardson Number ◽  
Three Dimensional ◽  
Water Bodies ◽  
Inland Water ◽  
Dependent Relation ◽  
Vertical Distributions ◽  
Computing Center ◽  
Inland Water Bodies

<p>A parameterization of the Prandtl number as a function of the gradient Richardson number is proposed in order to correctly take into account stratification when calculating the thermohydrodynamic regime of inland water bodies. This parameterization allows the existence of turbulence at any values ​​of the Richardson number.</p><p>The proposed function is used to calculate the turbulent thermal conductivity coefficient in a k-epsilon mixing scheme. Modification is implemented in the three-dimensional hydrostatic model developed at the Research Computing Center of Moscow State University.</p><p>It is demonstrated that the proposed modification (in contrast to the standard scheme with a constant Prandtl number) leads to smoothing all sharp changes in vertical distributions of turbulent mixing parameters (turbulent kinetic energy, temperature and thickness of the shock layer) and imposes a Richardson number-dependent relation on the empirical constants of k-epsilon turbulent mixing scheme.</p><p>The work was supported by grants of the RF President’s Grant for Young Scientists (MK-1867.2020.5) and by the RFBR (19-05-00249, 20-05-00776). </p>

Sign in / Sign up

Export Citation Format

Share Document