Ruslan Kuchumov

• Master of Science
• St Petersburg University

Applications in high-performance computing (HPC) may not use all available computational resources, leaving some of them underutilized. By co-scheduling, i.e., running more than one application on the same computational node, it is possible to improve resource utilization and overall throughput. Some applications may have conflicting requirements o...

Efficient usage of shared high-performance computing (HPC) resources raises the problem of HPC applications co-scheduling, i.e. the problem of execution of multiple applications simultaneously on the same shared computing nodes. Each application may have different requirements for shared resources (e.g. network bandwidth or memory bus bandwidth). W...

In this paper, we report the main accomplishments obtained in the context of the CloudHPC project. Accepted in response to the BRICS Pilot Call 2016, the project gathered researchers from the Federal University of Rio Grande do Sul (UFRGS), the St. Petersburg State University (SPbSU), and Beijing Normal University (BNU). Its main objective was to i...

Applications in high-performance computing (HPC) may not use all available computational resources, leaving some of them underutilized. By co-scheduling, i.e. running more than one application on the same computational node, it is possible to improve resource utilization and overall throughput. Some applications may have conflicting requirements on...

In this paper we describe typical HPC workloads in terms of scheduling theory models. In particular, we cover machine environments that are common for high performance computing (HPC) field, possible objective functions and available jobs characteristics. We also describe resources that are required by HPC applications and how to monitor and contro...

Modern science heavy relies on the usage of information technologies (IT). It is important to organize knowledge transfer from IT specialists to non-IT and to less educated and/or skilled IT ones. Nowadays a speed of IT development (as well as achievements of the results these IT are used for) can be sufficiently increased by joining efforts and re...

In high performance computing (HPC) job schedulers usually divide resources of computing nodes into slots. Each slot can be assigned to execute only a single job from the queue. In some cases, jobs do not fully utilize all available resources from the slot which leads to internal fragmentation, wasted resources and to an increase of queue wait time...

Cloud computing has become a routine tool for scientists in many fields. The JINR cloud infrastructure provides JINR users with computational resources to perform various scientific calculations. In order to speed up achievements of scientific results the JINR cloud service for parallel applications has been developed. It consists of several compon...

Cloud computing became a routine tool for scientists in many domains. In order to speed up an achievement of scientific results a cloud service for execution of distributed applications was developed. It obliviates users from manually creating virtual cluster environment or using batch scheduler and allows them only to specify input parameters to p...

Parallel tasks work-stealing schedulers yield near-optimal tasks distribution (i.e. all CPU cores are loaded equally) and have low time, memory and inter-thread synchronizations. The key idea of work-stealing strategy is that when scheduler worker runs out of tasks for execution, it start stealing tasks from the queues of other workers. It’s been s...