Filters








6 Hits in 4.5 sec

Exploring the performance and mapping of HPC applications to platforms in the cloud

Abhishek Gupta, Laxmikant V. Kalé, Dejan S. Milojicic, Paolo Faraboschi, Richard Kaufmann, Verdi March, Filippo Gioachin, Chun Hui Suen, Bu-Sung Lee
2012 Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing - HPDC '12  
First, we characterize application performance on dedicated clusters and cloud to obtain application signatures.  ...  This paper presents a scheme to optimize the mapping of HPC applications to a set of hybrid dedicated and cloud resources.  ...  In the future, we plan to extend the mapping tool to also perform a dynamic adjustment of the static mapping through run-time monitoring. HPDC'12, June 18-22, 2012, Delft, The Netherlands.  ... 
doi:10.1145/2287076.2287093 dblp:conf/hpdc/GuptaKMFKMGSL12 fatcat:zniz3ulnqnaxnbbvlu2soajcla

A system-aware optimized data organization for efficient scientific analytics

Yuan Tian, Scott Klasky, Weikuan Yu, Hasan Abbasi, Bin Wang, Norbert Podhorszki, Ray Grout, Matt Wolf
2012 Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing - HPDC '12  
Large-scale scientific applications on High End Computing systems produce a large volume of highly complex datasets.  ...  In this study, we propose a system-aware optimized data organization strategy that can organize data blocks of multidimensional scientific data efficiently based on simulation output and the underlying  ...  HPDC'12, June 18-22, 2012, Delft, The Netherlands. ACM 978-1-4503-0805-2/12/06. data intensive computing as a very significant factor in scientific computing.  ... 
doi:10.1145/2287076.2287095 dblp:conf/hpdc/TianKYAWPGW12 fatcat:4r56jvwbjvevzlbnuyujkdyzfe

Leveraging renewable energy in data centers

Ricardo Bianchini
2012 Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing - HPDC '12  
Specifically, I will overview systems that match a data center's computational workload to the green energy supply.  ...  Next, I will describe some of the software and hardware that researchers are building to explore these challenges and questions.  ...  Copyright is held by the author/owner(s). HPDC'12, June 18-22, 2012, Delft, The Netherlands. ACM 978-1-4503-0805-2/12/06.  ... 
doi:10.1145/2287076.2287101 dblp:conf/hpdc/Bianchini12 fatcat:7psspyx5hzampb54ijmkvczyfe

Work stealing and persistence-based load balancers for iterative overdecomposed applications

Jonathan Lifflander, Sriram Krishnamoorthy, Laxmikant V. Kale
2012 Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing - HPDC '12  
We demonstrate low overheads and high efficiencies on the full NERSC Hopper (146,400 cores) and ALCF Intrepid systems (163,840 cores), and on up to 128,000 cores on OLCF Titan.  ...  The work to be performed is overdecomposed into tasks, enabling automatic rebalancing by the middleware.  ...  HPDC'12, June 18-22, 2012, Delft, The Netherlands. Copyright 2012 ACM 978-1-4503-0805-2/12/06 ...$10.00.  ... 
doi:10.1145/2287076.2287103 dblp:conf/hpdc/LifflanderKK12 fatcat:wchqotv6vzhtpnhh2hhuychp2u

QBox

Dimitris Skourtis, Shinpei Kato, Scott Brandt
2012 Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing - HPDC '12  
Many storage systems are shared by multiple clients with different types of workloads and performance targets.  ...  Our experimental results show that Qbox provides good isolation and achieves the target utilizations of its clients.  ...  HPDC'12, June 18-22, 2012, Delft, The Netherlands. Copyright 2012 ACM 978-1-4503-0805-2/12/06 ...$10.00.  ... 
doi:10.1145/2287076.2287087 dblp:conf/hpdc/SkourtisKB12 fatcat:atoz5h6n6ngydjvtzh6skfanvu

Understanding the effects and implications of compute node related failures in hadoop

Florin Dinu, T.S. Eugene Ng
2012 Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing - HPDC '12  
Ensuring good performance for Hadoop is paramount for the wide-range of applications built on top of it. In this paper we analyze Hadoop's behavior under failures involving compute nodes.  ...  The reason is that Hadoop focuses on extreme scalability and thus trades off possible improvements resulting from sharing failure information between tasks.  ...  HPDC'12, June 18-22, 2012, Delft, The Netherlands. Copyright 2012 ACM 978-1-4503-0805-2/12/06 ...$10.00. Figure 1 : 1 Clusters of job running times under TaskTracker failure.  ... 
doi:10.1145/2287076.2287108 dblp:conf/hpdc/DinuN12 fatcat:uyk6pw5u25etlbd5boksa3fawe