183 Hits in 5.0 sec

Utility-based resource management in an oversubscribed energy-constrained heterogeneous environment executing parallel applications

Dylan Machovec, Bhavesh Khemka, Nirmal Kumbhare, Sudeep Pasricha, Anthony A. Maciejewski, Howard Jay Siegel, Ali Akoglu, Gregory A. Koenig, Salim Hariri, Cihan Tunc, Michael Wright, Marcia Hilton (+5 others)
2017 Parallel Computing  
(HPC) system that is oversubscribed and energy constrained.  ...  We conducted a simulation study to evaluate the performance of these heuristics and techniques in multiple energyconstrained oversubscribed HPC environments.  ...  Department of Energy.  ... 
doi:10.1016/j.parco.2017.11.005 fatcat:bzcivn22ufdilcfy6ee4ldmg7u

Energy-Constrained Dynamic Resource Allocation in a Heterogeneous Computing Environment

B. Dalton Young, Jonathan Apodaca, Luis Diego Briceno, Jay Smith, Sudeep Pasricha, Anthony A. Maciejewski, Howard Jay Siegel, Bhavesh Khemka, Shirish Bahirat, Adrian Ramirez, Yong Zou
2011 2011 40th International Conference on Parallel Processing Workshops  
We study the problem of energyconstrained dynamic allocation of tasks to a heterogeneous cluster computing environment.  ...  Energy-efficient resource allocation within clusters and data centers is important because of the growing cost of energy.  ...  In our environment, the resource management system controls the P-states of each core individually.  ... 
doi:10.1109/icppw.2011.58 dblp:conf/icppw/YoungABSPMSKBRZ11 fatcat:24zf2k5f7bdaxkd7eg3nfx6dmi

Mapping subtasks with multiple versions on an ad hoc grid

S. Shivle, P. Sugavanam, H.J. Siegel, A.A. Maciejewski, T. Banka, K. Chindam, S. Dussinger, A. Kutruff, P. Penumarthy, P. Pichumani, P. Satyasekaran, D. Sendek (+4 others)
2005 Parallel Computing  
An ad hoc grid is a heterogeneous computing system composed of mobile devices. Each computing resource is constrained in battery energy.  ...  All subtasks must be executed; to accommodate this in an oversubscribed environment, each subtask has two versions: the primary or 0167-8191/$ -see front matter Ó (J.  ...  Acknowledgements A preliminary version of portions of this material was presented at the 3rd International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Networks (HeteroPar  ... 
doi:10.1016/j.parco.2005.04.003 fatcat:oa6lg27fsfdfzio7gnudjf3nla

Zorua: Enhancing Programming Ease, Portability, and Performance in GPUs by Decoupling Programming Models from Resource Management [article]

Nandita Vijaykumar, Kevin Hsieh, Gennady Pekhimenko, Samira Khan, Ashish Shrestha, Saugata Ghose, Phillip B. Gibbons, Onur Mutlu
2018 arXiv   pre-print
This specification determines the performance of the application during execution because the corresponding on-chip hardware resources are allocated and managed purely based on this specification.  ...  utilize the resources.  ...  We thank the members of the SAFARI group for their feedback and the stimulating research environment they provide.  ... 
arXiv:1802.02573v1 fatcat:pccnx7fcsje7vja6iinjcexo5e

Energy-aware Self-Adaptation for Application Execution on Heterogeneous Parallel Architectures

Richard Kavanagh, Karim Djemame, Jorge Ejarque, Rosa Badia, David Garzia Perez
2019 IEEE Transactions on Sustainable Computing  
An additional aspect of such systems is the management of power and energy consumption.  ...  Hardware in High Performance Computing environments in recent years have increasingly become more heterogeneous in order to improve computational performance.  ...  Two executions are configured for time optimization: one without constrains and another with an energy limit of 700KJ.  ... 
doi:10.1109/tsusc.2019.2912000 fatcat:2fki22aspzeifbcyzwcfsa2uua

A Job Scheduling Strategy for Heterogeneous Multiprogrammed Systems [chapter]

Piyush Maheshwari
2004 Lecture Notes in Computer Science  
In order to utilize all or most of the available resources of a high-performance computing cluster, at least some of its nodes will have to be shared by several applications at the same time.  ...  Typically, those schedulers make their decisions based on a static strategy. In this paper, we investigate the impact if a heterogeneous scheduler allows modifications of the strategies at runtime.  ...  The scheduled jobs are executed asynchronously which allows for an energy-efficient and effective utilization of all resources.  ... 
doi:10.1007/978-3-540-24669-5_118 fatcat:fe4of7fc7zdipkf6efwj3lizfe

THOR: A Transparent Heterogeneous Open Resource framework

J. L. Vazquez-Poletti, J. Perhac, J. Ryan, A. C. Elster
2010 2010 IEEE International Conference On Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS)  
To validate our approach, THOR has been implemented on a scaled-down heterogeneous cluster within a cloud-based computational environment.  ...  While the current form of cloud-based systems is suitable for many scenarios, their evolution into a truly heterogeneous computational environments is still not fully developed.  ...  ACKNOWLEDGEMENTS This work was partially supported by the NILS mobility programme (EEA-ABEL-03-2010), the ERCIM "Alain Bensoussan" Fellowship Programme and an NTNU (RSO) Post Doc grant.  ... 
doi:10.1109/clusterwksp.2010.5613099 fatcat:il5ipe4dnnfi5ebtof2r5ds3gm

QoS-Aware scheduling in heterogeneous datacenters with paragon

Christina Delimitrou, Christos Kozyrakis
2013 ACM Transactions on Computer Systems  
The differences are more striking in oversubscribed scenarios where resource efficiency is more critical.  ...  ARQ queues applications in separate classes based on the type of resources they need and avoids long queueing delays for easy-to-satisfy workloads in highly-loaded scenarios.  ...  The results are more striking in the case of an oversubscribed workload, scenario, where efficient resource use is even more critical.  ... 
doi:10.1145/2556583 fatcat:bcdulrumbvbc3h26kucgwmfxt4

Decoupling GPU Programming Models from Resource Management for Enhanced Programming Ease, Portability, and Performance [article]

Nandita Vijaykumar, Kevin Hsieh, Gennady Pekhimenko, Samira Khan, Ashish Shrestha, Saugata Ghose, Adwait Jog, Phillip B. Gibbons, Onur Mutlu
2018 arXiv   pre-print
This specification determines the parallelism, and hence performance, of the application during execution because the corresponding on-chip hardware resources are allocated and managed based on this specification  ...  By dynamically allocating resources and carefully oversubscribing them when necessary, Zorua improves or retains the performance of applications that are already highly tuned to best utilize the resources  ...  We thank the members of the SAFARI group for their feedback and the stimulating research environment they provide.  ... 
arXiv:1805.02498v1 fatcat:nbubyfbtcnfsrkpvx6tgkphkuy

Dynamic Resource Management in Energy Constrained Heterogeneous Computing Systems Using Voltage Scaling

Jong-Kook Kim, H.J. Siegel, A.A. Maciejewski, R. Eigenmann
2008 IEEE Transactions on Parallel and Distributed Systems  
An ad hoc grid is a wireless heterogeneous computing environment without a fixed infrastructure.  ...  To maximize the performance of the system, it is essential to assign resources to tasks (match) and order the execution of tasks on each resource (schedule) in a manner that exploits the heterogeneity  ...  ENERGY CONSTRAINED ENVIRONMENT The ad hoc grid environment is controlled by a resource management system (RMS).  ... 
doi:10.1109/tpds.2008.113 fatcat:rio5u45d2ff6noabeofayhpfay

Energy-aware Self-Adaptive Middleware for Heterogeneous Parallel Architectures

Richard Kavanagh, Karim Djemame
2018 2018 Fifth International Symposium on Innovation in Information and Communication Technology (ISIICT)  
Hardware in HPC environments in recent years has become ever more heterogeneous in order to improve computational performance and as an aspect of managing power and energy constraints.  ...  In this paper we present a self-adaptation framework which includes aspects such as automated configuration, deployment and redeployment of applications to different heterogeneous infrastructure.  ...  In this paper we address these issues with a energy-aware self-adaptive framework for heterogeneous parallel architectures.  ... 
doi:10.1109/isiict.2018.8613291 fatcat:ems46dovp5cfhfbrksd3oc4gwa

Stochastic-based robust dynamic resource allocation for independent tasks in a heterogeneous computing system

Mohsen Amini Salehi, Jay Smith, Anthony A. Maciejewski, Howard Jay Siegel, Edwin K.P. Chong, Jonathan Apodaca, Luis D. Briceño, Timothy Renner, Vladimir Shestak, Joshua Ladd, Andrew Sutton, David Janovy (+4 others)
2016 Journal of Parallel and Distributed Computing  
Heterogeneous parallel and distributed computing systems frequently must operate in environments where there is uncertainty in system parameters.  ...  In such an environment, the execution time of any given task may fluctuate substantially due to factors such as the content of data to be processed.  ...  and International Conference on Parallel and Distributed Processing Techniques and Applications [44] .  ... 
doi:10.1016/j.jpdc.2016.06.008 fatcat:rrybhbvrind35mzm3sqcsukjii

An energy-efficient and error-resilient server ecosystem exceeding conservative scaling limits

Georgios Karakonstantis, Konstantinos Tovletoglou, Lev Mukhanov, Hans Vandierendonck, Dimitrios S. Nikolopoulos, Peter Lawthers, Panos Koutsovasilis, Manolis Maroudas, Christos D. Antonopoulos, Christos Kalogirou, Nikos Bellas, Spyros Lalis (+14 others)
2018 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE)  
The system software including a virtualization and resource management layer is responsible for optimizing the system operation in terms of energy or performance, while guaranteeing non-disruptive operation  ...  In this paper, we present our approach, which aims at developing a new class of micro-servers -the UniServer -that exceed the conservative energy and performance scaling boundaries by introducing novel  ...  It is responsible for creating an appropriate execution environment for VMs by manipulating the power / performance / reliability tradeoffs in an educated and safe manner.  ... 
doi:10.23919/date.2018.8342175 dblp:conf/date/KarakonstantisT18 fatcat:q7nxvds5mnhn7nv2pouokoayu4

Pilot-Data: An abstraction for distributed data

Andre Luckow, Mark Santcroos, Ashley Zebrowski, Shantenu Jha
2015 Journal of Parallel and Distributed Computing  
Our experiments utilize an implementation of Pilot-Data in conjunction with a scalable Pilot-Job (BigJob) to establish the application performance that can be enabled by the use of Pilot-Data.  ...  with compute resources, and storing, transferring, and managing large volumes of data.  ...  Pradeep Mantha (Berkeley) contributed to early associated work on Pilot-Data based applications.  ... 
doi:10.1016/j.jpdc.2014.09.009 fatcat:nyoyz4optngctljc35vuapwoom


Hartmut Kaiser, Thomas Heller, Bryce Adelstein-Lelbach, Adrian Serio, Dietmar Fey
2014 Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models - PGAS '14  
The significant increase in complexity of Exascale platforms due to energy-constrained, billion-way parallelism, with major changes to processor and memory architecture, requires new energy-efficient and  ...  We present HPX -a parallel runtime system which extends the C++11/14 standard to facilitate distributed operations, enable fine-grained constraint based parallelism, and support runtime adaptive resource  ...  We would also like to thank LSU HPC, LONI, XSEDE, ALCF, and the Gauss Center for Supercomputing. for granting us allocations for their compute resources.  ... 
doi:10.1145/2676870.2676883 dblp:conf/pgas/KaiserHASF14 fatcat:qnv2cktjufdzvo2jlsmdpw77he
« Previous Showing results 1 — 15 out of 183 results