937 Hits in 11.9 sec

Tuning the performance of I/O-intensive parallel applications

Anurag Acharya, Mustafa Uysal, Robert Bennett, Assaf Mendelson, Michael Beynon, Jeff Hollingsworth, Joel Saltz, Alan Sussman
1996 Proceedings of the fourth workshop on I/O in parallel and distributed systems part of the federated computing research conference - IOPADS '96  
In this paper, we report our experience tuning the I O performance of four application programs from the areas of satellite-data processing and linear algebra.  ...  After tuning, three of the four applications achieve application-level I O rates of over 100 MB s on 16 processors.  ...  We w ould like to thank Tonjua Hines and Steve Kempler from the Earth Science Data & Information Systems Project ESDIS at NASA Goddard Space  ... 
doi:10.1145/236017.236027 dblp:conf/iopads/AcharyaUBMBHSS96 fatcat:2ljwxgb2uvdhplib3wq5zqlmim

Benefit of DDN's IME-FUSE for I/O Intensive HPC Applications [chapter]

Eugen Betke, Julian Kunkel
2018 Lecture Notes in Computer Science  
Many scientific applications are limited by I/O performance offered by parallel file systems on conventional storage systems.  ...  Finally, by utilizing a NetCDF benchmark, it estimates the performance benefit for climate applications.  ...  Acknowledgment Thanks to DDN for providing access to the IME test cluster and to Jean-Thomas Acquaviva for the support. 11/14  ... 
doi:10.1007/978-3-030-02465-9_9 fatcat:f3edktuqwjd6jdiqc6pet5ezwq

Dynamic load balancing for I/O-intensive applications on clusters

Xiao Qin, Hong Jiang, Adam Manzanares, Xiaojun Ruan, Shu Yin
2009 ACM Transactions on Storage  
Importantly, this performance improvement becomes much more pronounced when the applications are I/O-intensive.  ...  Using a set of real I/O-intensive parallel applications and synthetic parallel jobs with various I/O characteristics, we show that our proposed schemes consistently improve the performance over existing  ...  Real I/O-Intensive Parallel Applications.  ... 
doi:10.1145/1629075.1629078 fatcat:jlj5fqkof5elldzaqg5nkau7ii

Container shipping: operating system support for I/O-intensive applications

J. Pasquale, E. Anderson, P.K. Muller
1994 Computer  
Along with continual improvements in processor, memory, and bus technology, these devices have enabled I/O-intensive applications for desktop computing that require input, processing, and output of very  ...  These applications often operate on data in the form of sequences of very large images.  ...  Acknowledgments This work was supported in part by the Sequoia 2000 Project, DEC, IBM, NCR, TRW, and the National Science Foundation.  ... 
doi:10.1109/2.268890 fatcat:qnnofyvlzjffxfozeltpml2jv4

Dma-based prefetching for i/o-intensive workloads on the cell architecture

M. Mustafa Rafique, Ali R. Butt, Dimitrios S. Nikolopoulos
2008 Proceedings of the 2008 conference on Computing frontiers - CF '08  
Data and I/O intensive workloads have largely been ignored in this domain.  ...  In this paper, we take the first steps in supporting I/O intensive workloads on the Cell/BE and deriving guidelines for optimizing the execution of I/O workloads on heterogeneous architectures.  ...  This paper explores the use of the Cell/BE, arguably a dominant asymmetric multi-core processor, in I/O-intensive applications.  ... 
doi:10.1145/1366230.1366236 dblp:conf/cf/RafiqueBN08 fatcat:2fkirsdjbfe7lmrrsj7qhvtdba

Understanding Scalability and Performance Requirements of I/O-Intensive Applications on Future Multicore Servers

Shoaib Akram, Manolis Marazakis, Angelos Bilas
2012 2012 IEEE 20th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems  
These applications can achieve much of their performance with only 50% of the memory bandwidth available on modern processors.  ...  Hyper-threading is extremely effective and applications perform with in 15% of what is achieved with full cores instead of hyper-threading.  ...  ACKNOWLEDGEMENTS We thankfully acknowledge the support of the European Commission under the 7th Framework Programs through the IOLANES (FP7-ICT-248615), HiPEAC2 (FP7-ICT-217068), and SCALUS (FP7-PEOPLE-ITN  ... 
doi:10.1109/mascots.2012.29 dblp:conf/mascots/AkramMB12 fatcat:rsblms2bqvgcfggtkffqb7sohi

A hybrid local storage transfer scheme for live migration of I/O intensive workloads

Bogdan Nicolae, Franck Cappello
2012 Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing - HPDC '12  
It relies on a hybrid active push / prioritized prefetch strategy, which makes it highly resilient to rapid changes of disk state exhibited by I/O intensive workloads.  ...  consumption and 8x less performance degradation over state-of-art.  ...  Acknowledgments We thank Eugen Feller for his remarks on the usefulness of live migration in the context of power management.  ... 
doi:10.1145/2287076.2287088 dblp:conf/hpdc/NicolaeC12 fatcat:ndsi7pjl2bexrmzjyxk5esezqi

Multi-Layer Event Trace Analysis for Parallel I/O Performance Tuning

Pin Lu, Kai Shen
2007 Proceedings of the International Conference on Parallel Processing  
Our empirical case study discovered root causes for several anomalous performance behaviors of MPI-IO applications running on a parallel file system.  ...  The complexity of parallel I/O systems lies in the deep I/O stack with many software layers and concurrent I/O request handling at multiple layers.  ...  There has been extensive studies on operating system (OS) support for I/O-intensive applications, in terms of I/O prefetching [6] , scheduling [4] , and performance anomaly analysis [15] .  ... 
doi:10.1109/icpp.2007.59 dblp:conf/icpp/LuS07 fatcat:f53shuf5k5effoz6ql4mtqg5ey

Workload characterization of input/output intensive parallel applications [chapter]

Evgenia Smirni, Daniel A. Reed
1997 Lecture Notes in Computer Science  
In the paper, we present a comparative study of parallel I/O access patterns, commonly found in I/O intensive scienti c applications.  ...  Prerequisite to the development of e cient parallel le system is detailed characterization of the I/O demands of parallel applications.  ...  Acknowledgments The MESSKIT  ... 
doi:10.1007/bfb0022205 fatcat:5rxmtkbjrjf7tnpqyb4jbbslw4

Improving MapReduce performance in heterogeneous environments with adaptive task tuning

Dazhao Cheng, Jia Rao, Yanfei Guo, Xiaobo Zhou
2014 Proceedings of the 15th International Middleware Conference on - Middleware '14  
The deployment of MapReduce in datacenters and clouds present several challenges in achieving good job performance.  ...  In this paper, we find that the homogeneous configuration of tasks on heterogeneous nodes can be an important source of load imbalance and thus cause poor performance.  ...  NSF CAREER award CNS-0844983, research grants CNS-1422119, CNS-1320122 and CNS-1217979, and NSF of China research grant No.61328203.  ... 
doi:10.1145/2663165.2666089 dblp:conf/middleware/ChengRGZ14 fatcat:cv2ljujxkrexfcnkwdqaunf6xq

Experiences parallelizing, configuring, monitoring, and visualizing applications for clusters and multi-clusters [chapter]

O.J. Anshus, J.M. Bjørndalen, L.A. Bongo
2004 Advances in Parallel Computing  
Introduction A current trend in parallel and distributed computing is that compute-and I/O-intensive applications are increasingly run on cluster and multi-cluster architectures.  ...  To make it simpler to experiment with the impact different configurations can have on the performance of a parallel cluter application, we developed the PATHS system.  ...  In order to tune the performance of collective and point-to-point communication, finegrained information about the applications communication events is needed to compute how the application behaves.  ... 
doi:10.1016/s0927-5452(04)80107-2 fatcat:n4tvnaftzzhrxes4m2z5vxvfxa

Parallel I/O subsystems in massively parallel supercomputers

D.G. Feitelson, P.F. Corbett, S.J. Baylor, Hsu Yarsun
1995 IEEE Parallel & Distributed Technology Systems & Applications  
However, those applications that performed I/O throughout their whole execution (as opposed to just at the beginning and the end) averaged F/b ≈ 50, and the most I/O-intensive application had F/b ≈ 14.  ...  Admittedly, the survey focused on I/O intensive applications, but such applications do in fact exist. Thus the requirement for F/b ≈ 1 is not overly 13 aggressive.  ...  Acknowledgements Thanks to Jim Cownie from Meiko for information about the Meiko CS-2 I/O architecture and its parallel filesystem.  ... 
doi:10.1109/m-pdt.1995.414842 fatcat:kssovrnt4jhutmqjad2dlpnc7m

Boosting Application-Specific Parallel I/O Optimization Using IOSIG

Yanlong Yin, Surendra Byna, Huaiming Song, Xian-He Sun, Rajeev Thakur
2012 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012)  
The tool enables tracing parallel I/O calls of an application and analyzing the collected information to provide a clear understanding of I/O behavior of the application.  ...  We show that performance overheads of the tool in trace collection and analysis are negligible.  ...  This research was supported in part by National Science Foundation under NSF grant CCF-0621435 and CCF-0937877, and in part by the Office of Advanced Scientific Computing Research, Office of Science, U.S  ... 
doi:10.1109/ccgrid.2012.136 dblp:conf/ccgrid/YinBSST12 fatcat:phdsllr3jvasvptwkqizgbmsay

Parallel File System Analysis Through Application I/O Tracing

S. A. Wright, S. D. Hammond, S. J. Pennycook, R. F. Bird, J. A. Herdman, I. Miller, A. Vadgama, A. Bhalerao, S. A. Jarvis
2012 Computer journal  
Input/Output (I/O) operations can represent a significant proportion of the run-time of parallel scientific computing applications.  ...  In this paper, we document the design and application of the RIOT I/O toolkit (RIOT) being developed at the University of Warwick with our industrial partners at the Atomic Weapons Establishment and Sandia  ...  ACKNOWLEDGEMENTS Access to the Minerva supercomputer was provided by the Centre for Scientific Computing at the University of Warwick.  ... 
doi:10.1093/comjnl/bxs044 fatcat:hi6dl3fkdzckjnjxmzuy4e3ubu

Energy prediction for I/O intensive workflow applications

Hao Yang
This evaluation quantifies the energy savings of performance optimizations for the distributed storage system as well as the energy and performance impact of power-centric tuning techniques.  ...  Third, it demonstrates the predictor's ability to expose energy performance tradeoffs for the synthetic benchmarks and workflow applications by evaluating the accuracy of the energy consumption predictions  ...  Users have to make system provisioning, resource allocation, and configuration decisions for I/O-intensive workflow applications.  ... 
doi:10.14288/1.0166973 fatcat:haqwsxxetfd2xarpeyxpol7pe4
« Previous Showing results 1 — 15 out of 937 results