scholarly journals CHAMELEON: Reactive Load Balancing for Hybrid MPI+OpenMP Task-Parallel Applications

2020 ◽  
Vol 138 ◽  
pp. 55-64 ◽  
Author(s):  
Jannis Klinkenberg ◽  
Philipp Samfass ◽  
Michael Bader ◽  
Christian Terboven ◽  
Matthias S. Müller
Keyword(s):  
Load Balancing ◽  
Parallel Applications ◽  
Task Parallel

scholarly journals Scheduling Task-parallel Applications in Dynamically Asymmetric Environments

2020 ◽  
Author(s):  
Jing Chen ◽  
Pirah Noor Soomro ◽  
Mustafa Abduljabbar ◽  
Madhavan Manivannan ◽  
Miquel Pericas
Keyword(s):  
Parallel Applications ◽  
Task Parallel

scholarly journals Characterizing and Mitigating Work Time Inflation in Task Parallel Programs

2013 ◽  
Vol 21 (3-4) ◽  
pp. 123-136 ◽  
Author(s):  
Stephen L. Olivier ◽  
Bronis R. de Supinski ◽  
Martin Schulz ◽  
Jan F. Prins
Keyword(s):  
Poor Performance ◽  
Data Access ◽  
Parallel Applications ◽  
Task Parallelism ◽  
Improve Performance ◽  
Additional Time ◽  
Work Time ◽  
Task Parallel ◽  
Time Required ◽  
Data Access Latency

Task parallelism raises the level of abstraction in shared memory parallel programming to simplify the development of complex applications. However, task parallel applications can exhibit poor performance due to thread idleness, scheduling overheads, andwork time inflation– additional time spent by threads in a multithreaded computation beyond the time required to perform the same work in a sequential computation. We identify the contributions of each factor to lost efficiency in various task parallel OpenMP applications and diagnose the causes of work time inflation in those applications. Increased data access latency can cause significant work time inflation in NUMA systems. Our locality framework for task parallel OpenMP programs mitigates this cause of work time inflation. Our extensions to the Qthreads library demonstrate that locality-aware scheduling can improve performance up to 3X compared to the Intel OpenMP task scheduler.

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.

scholarly journals Extreme-scale scripting: Opportunities for large task-parallel applications on petascale computers

2009 ◽  
Vol 180 ◽  
pp. 012046 ◽  
Author(s):  
Michael Wilde ◽  
Ioan Raicu ◽  
Allan Espinosa ◽  
Zhao Zhang ◽  
Ben Clifford ◽  
...  
Keyword(s):  
Parallel Applications ◽  
Task Parallel ◽  
Extreme Scale

Asymmetry-aware load balancing for parallel applications in single-ISA multi-core systems

2012 ◽  
Vol 13 (6) ◽  
pp. 413-427 ◽  
Author(s):  
Eunsung Kim ◽  
Hyeonsang Eom ◽  
Heon Y. Yeom
Keyword(s):  
Load Balancing ◽  
Parallel Applications

Resource-Aware Load Balancing of Parallel Applications

2009 ◽  
pp. 12-21 ◽  
Author(s):  
Eric Aubanel
Keyword(s):  
Load Balancing ◽  
Dynamic Network ◽  
Computational Grid ◽  
Parallel Applications ◽  
Computational Grids ◽  
Concurrent Execution ◽  
Processor Performance ◽  
Wide Range ◽  
Tightly Coupled ◽  
Resource Aware

The problem of load balancing parallel applications is particularly challenging on computational grids, since the characteristics of both the application and the platform must be taken into account. This chapter reviews the wide range of solutions that have been proposed. It considers tightly coupled parallel applications that can be described by an undirected graph representing concurrent execution of tasks and communication of tasks, executing on computational grids with static and dynamic network and processor performance. While a rich set of solution techniques have been proposed, there has not been of yet any performance comparisons between them. Such comparisons will require parallel benchmarks and computational grid emulators and simulators.

Sign in / Sign up

Export Citation Format

Share Document