Filters








97,505 Hits in 8.7 sec

A 'cool' way of improving the reliability of HPC machines

Osman Sarood, Esteban Meneses, Laxmikant V. Kale
2013 Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '13  
Our experimental results show that we can improve the reliability of a machine by a factor of 2.3 and reduce the execution time by 12%.  ...  In this paper, we try to bridge this gap and explore the potential of combining both software and hardware aspects towards improving reliability of HPC machines.  ...  We also thank Phil Miller and Shehla Saleem Rana for their valuable help in editing and proofreading the paper.  ... 
doi:10.1145/2503210.2503228 dblp:conf/sc/SaroodMK13 fatcat:abtmdbvzjbaeffnmlebnydnsee

Improving communication performance in dense linear algebra via topology aware collectives

Edgar Solomonik, Abhinav Bhatele, James Demmel
2011 Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '11  
Using those, we model the performance of matrix multiplication and LU factorization on a hypothetical exascale architecture.  ...  Recent results have shown that topology aware mapping reduces network contention in communication-intensive kernels on massively parallel machines.  ...  This research used resources of the Argonne Leadership Computing Facility at Argonne National Laboratory, which is supported by the Office of Science of the U.S.  ... 
doi:10.1145/2063384.2063487 dblp:conf/sc/SolomonikBD11 fatcat:bd7qihwzb5bpnfoclfnquhnjvq

Using Static Code Analysis to Improve Performance of GridRPC Applications

Oleg Girko, Alexey Lastovetsky
2012 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD Forum  
and communication.  ...  The paper presents an approach to improve performance of GridRPC applications by statically analysing dynamic workflows.  ...  communication to achieve improved performance.  ... 
doi:10.1109/ipdpsw.2012.135 dblp:conf/ipps/GirkoL12 fatcat:frmfrj72rrdwtibhrlosiwmkwy

An Improved Performance Analysis Of Priority Scheduling Algorithm In Modified Ad Hoc Grid Layer

R Bhaskaran
2012 International Journal of Distributed and Parallel systems  
An improved performance analysis of priority based scheduling algorithm for the ad hoc grid layer is presented in this paper.  ...  A priority queuing model is developed to reduce the execution time of the jobs. Here, jobs to be dispatched based on priority. Execution time is one prime metric proposed for the system.  ...  The scheduling is a complex process and have focused on global scheduling dealing with clusters. They consider the communication ratio of the job.  ... 
doi:10.5121/ijdps.2012.3120 fatcat:r7btzkxzoja4bbrwh6advg3jmy

vSnoop: Improving TCP Throughput in Virtualized Environments via Acknowledgement Offload

Ardalan Kangarlou, Sahan Gamage, Ramana Rao Kompella, Dongyan Xu
2010 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis  
Virtual machine (VM) consolidation has become a common practice in clouds, Grids, and datacenters.  ...  We further show that the higher TCP throughput leads to improvement in applicationlevel performance, via experiments with a two-tier online auction application and two suites of MPI benchmarks.  ...  Fig. 3 . 3 Overview of vSnoop and its per-connection state machine.  ... 
doi:10.1109/sc.2010.57 dblp:conf/sc/KangarlouGKX10 fatcat:e5xlbuu6ejcp5ooklpga5kcgim

Performance Analysis and Improvement of HighSpeed TCP with TailDrop/RED Routers

Z. ZHANG
2005 IEICE transactions on communications  
By monitoring the changing trend of RTT, gHSTCP adapts to the traffic load by switching between two control modes, which is shown to provide significant performance improvement against traditional TCP  ...  Furthermore, it is observed that the performance of gHSTCP is limited by both TailDrop and RED/ARED routers, thus we develop a modified adaptive RED called gARED to address the problem of simultaneous  ...  Introduction Hosts (server machines) providing services that encompass data grids and storage area networks (SANs) have gigabit-level network interfaces such as gigabit ethernet.  ... 
doi:10.1093/ietcom/e88-b.6.2495 fatcat:g53x33vu5vhytno275z7oxurp4

Improving the Accuracy and Efficiency of Time-Independent Trace Replay

Frederic Desprez, George S. Markomanolis, Frederic Suter
2012 2012 SC Companion: High Performance Computing, Networking Storage and Analysis  
We propose several modifications to address these issues and analyze their impact. Results shows a clear improvement on the accuracy and efficiency with regard to the initial implementation.  ...  Finally our framework is built on top of a scalable, fast, and validated simulation kernel.  ...  The authors would also like to thanks all the members of the SIMGrid project working on the SMPI effort, and especially A. Degomme and L. Schnorr for their great help.  ... 
doi:10.1109/sc.companion.2012.64 dblp:conf/sc/DesprezMS12 fatcat:uzxzxgqi6beoxaexutn74arqqm

Wireless Machine-to-Machine Networks

Jianhua He, Yan Zhang, Zhong Fan, Hsiao-Hwa Chen, Lin Bai
2012 International Journal of Distributed Sensor Networks  
Our special thanks go to all the reviewers for their hard work in providing timely responses and constructive comments.  ...  Acknowledgments The Guest Editors would like to thank all the authors for their contributions to this special issue.  ...  The paper entitled "A performance analysis framework for WiFi/WiMAX heterogeneous metropolitan networks based on cross-layer design" by M. H.  ... 
doi:10.1155/2012/535927 fatcat:jgjhyed65rbhfos2mf7jdntoye

Wireless Machine-to-Machine Networks 2013

Jianhua He, Yan Zhang, Zhong Fan, Hsiao-Hwa Chen, Lin Bai
2014 International Journal of Distributed Sensor Networks  
as well as consumers on cost reduction and services improvement.  ...  Machine-to-machine (M2M) technology allows direct communications between machine devices through wireless and/or wired systems without human intervention, which opens unique opportunities to businesses  ...  Our special thanks go to all the reviewers for their hard work in providing timely responses and constructive comments.  ... 
doi:10.1155/2014/857139 fatcat:eyv46bo6mrduzowjrpja33wr2q

Machine-to-Machine Communications: Architectures, Standards and Applications

Min Chen
2012 KSII Transactions on Internet and Information Systems  
As a new business concept, machine-to-machine (M2M) communications are born from original telemetry technology with the intrinsic features of automatic data transmissions and measurement from remote sources  ...  Furthermore, the progress of global M2M standardization is reviewed, and some representative applications (i.e., smart home, smart grid and health care) are given to show that the M2M technologies are  ...  The rationale behind M2M communications is based on two observations: 1) a networked machine is more valuable than an isolated one; 2) when multiple machines are interconnected, more autonomous and intelligent  ... 
doi:10.3837/tiis.2012.02.002 fatcat:vur2bioyfrc5da5kjlhkukk3xy

Improving the Performance of a Large Scale Spreadsheet: A Case Study

Alaaeddin Swidan, Felienne Hermans, Ruben Koesoemowidjojo
2016 2016 IEEE 23rd International Conference on Software Analysis, Evolution, and Reengineering (SANER)  
We present the design, analysis and implementation of the solution which clearly improved the performance of the spreadsheet, with a factor of 50 in some cases.  ...  We subsequently reflect on challenges related to reverse engineering, testing and scalability.  ...  To achieve this, the HEAT provides an option for the end-users to run the model sequentially on a local machine.  ... 
doi:10.1109/saner.2016.100 dblp:conf/wcre/SwidanHK16 fatcat:5ijp4whg7bejzlvqmif3h7p4bm

Improving Fine-Grained Irregular Shared-Memory Benchmarks by Data Reordering

Y.C. Hu, A. Cox, W. Zwaenepoel
2000 ACM/IEEE SC 2000 Conference (SC'00)  
Our results on one hardware and two software shared-memory systems show that, with data reordering during initialization, the performance of these applications is improved by 12%-99% on the Origin 2000  ...  We demonstrate that data reordering can substantially improve the performance of fine-grained irregular sharedmemory benchmarks, on both hardware and software shared-memory systems.  ...  Data reordering improves the performance even on a single processor of the Origin.  ... 
doi:10.1109/sc.2000.10009 dblp:conf/sc/HuCZ00 fatcat:e5qbcd55qzcojeu4jwxiqke3va

Improving concurrency and asynchrony in multithreaded MPI applications using software offloading

Karthikeyan Vaidyanathan, Dhiraj D. Kalamkar, Kiran Pamnany, Jeff R. Hammond, Pavan Balaji, Dipankar Das, Jongsoo Park, Bálint Joó
2015 Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '15  
The central premise is that given the rapidly increasing core counts on modern systems, the improvements in MPI performance arising from dedicating a thread to drive communication outweigh the small loss  ...  Our technique requires no modification to the application, and we demonstrate significant performance improvement (up to 2X) for QCD, 1-D FFT and deep learning CNN applications.  ...  Acknowledgements We would like to thank James Dinan and Srinivas Sridharan for their useful insights on the comm-self approach used in this paper.  ... 
doi:10.1145/2807591.2807602 dblp:conf/sc/VaidyanathanKPH15 fatcat:wrza7rvf7beozlz466yli46hxa

Machine-to-Machine (M2M) Communications in Vehicular Networks

M.J. Booysen
2012 KSII Transactions on Internet and Information Systems  
This paper focuses on M2M communications in the vehicular networking context and investigates areas where M2M principles can improve vehicular networking.  ...  Since connected vehicles are essentially a network of machines that are communicating, preferably autonomously, vehicular networks can benefit a lot from M2M communications support.  ...  Acknowledgements We thank the anonymous reviewers for their constructive feedback which greatly helped us to improve the quality and presentation of this paper.  ... 
doi:10.3837/tiis.2012.02.005 fatcat:k5vkoei2izgjdd22yhw43um5lu

A first look at machine-to-machine power grid network traffic

Sang Shin Jung, David Formby, Carson Day, Raheem Beyah
2014 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm)  
In this paper, we provide a characterization of the power grid network to answer questions like the following: i) how stable is the communication based on configurations?  ...  The purpose of network traffic characterization is to explore unknown patterns in different types of network communications to help improve many aspects of the network.  ...  ACKNOWLEDGMENTS This work was partly supported by DARPA-N10AP20022 and NEETRAC.  ... 
doi:10.1109/smartgridcomm.2014.7007760 dblp:conf/smartgridcomm/JungFDB14 fatcat:h632wavgbbf37pqlyuk7boebfy
« Previous Showing results 1 — 15 out of 97,505 results