Filters








30,774 Hits in 7.4 sec

The sensitivity of communication mechanisms to bandwidth and latency

F.T. Chong, R. Barua, F. Dahlgren, J.D. Kubiatowicz, A. Agarwal
Proceedings 1998 Fourth International Symposium on High-Performance Computer Architecture  
The goal of this paper is to gain insight i n to the relative performance of communication mechanisms as bisection bandwidth and network latency vary.  ...  On machines with lower bisection bandwidth and higher network latency, however, message-passing mechanisms become important.  ...  Objective The goal of this paper is to provide insight i n to the relative e ectiveness of various communication mechanisms for several applications over a modest range of communication latencies and bandwidth  ... 
doi:10.1109/hpca.1998.650544 dblp:conf/hpca/ChongBDKA98 fatcat:ujyhskhctjhbhmitumdimbrr7u

Application-aware Congestion Mitigation for High-Performance Computing Systems [article]

Archit Patke, Saurabh Jha, Haoran Qiu, Jim Brandt, Ann Gentile, Joe Greenseid, Zbigniew Kalbarczyk, Ravishankar Iyer
2021 arXiv   pre-print
However, the impact of congestion on application runtime differs from application to application depending on their network characteristics (such as bandwidth and latency requirements).  ...  Netscope has a lower training cost and accurately estimates the impact of congestion on application runtime with a correlation between 0.7and 0.9 for common scientific applications.  ...  Bandwidth delay is given by the ratio of message size to NIC bandwidth ( msg size bandwidth ).  ... 
arXiv:2012.07755v2 fatcat:braticwr3nhsnmre7hd45rvtvq

Effects of communication latency, overhead, and bandwidth in a cluster architecture

Richard P. Martin, Amin M. Vahdat, David E. Culler, Thomas E. Anderson
1997 Proceedings of the 24th annual international symposium on Computer architecture - ISCA '97  
of these effects and (iii) an in-depth study of application sensitivity to latency, overhead, and bandwidth, quantifying application performance in response to changes in communication performance.  ...  Applications in this study are also sensitive to per-message bandwidth, but are surprisingly tolerant of increased latency and lower per-byte bandwidth.  ...  We would also like to thanks those people who provided us valuable assistance understanding the applications: Steve von Worley for P-Ray, Remzi Arpaci-Dusseau and Andrea Arpaci-Dusseau for Now-sort, Eric  ... 
doi:10.1145/264107.264146 dblp:conf/isca/MartinVCA97 fatcat:ykuhh4gpevaj5eelkd6phyxyom

Effects of communication latency, overhead, and bandwidth in a cluster architecture

Richard P. Martin, Amin M. Vahdat, David E. Culler, Thomas E. Anderson
1997 SIGARCH Computer Architecture News  
of these effects and (iii) an in-depth study of application sensitivity to latency, overhead, and bandwidth, quantifying application performance in response to changes in communication performance.  ...  Applications in this study are also sensitive to per-message bandwidth, but are surprisingly tolerant of increased latency and lower per-byte bandwidth.  ...  We would also like to thanks those people who provided us valuable assistance understanding the applications: Steve von Worley for P-Ray, Remzi Arpaci-Dusseau and Andrea Arpaci-Dusseau for Now-sort, Eric  ... 
doi:10.1145/384286.264146 fatcat:k4dkqrtb7zf2vg22mvf3u2y6ky

Designing Next Generation Clusters: Evaluation of InfiniBand DDR/QDR on Intel Computing Platforms

Hari Subramoni, Matthew Koop, Dhabaleswar K. Panda
2009 2009 17th IEEE Symposium on High Performance Interconnects  
to analyze application-level performance HotI '09 • Applications have different communication characteristics -Latency sensitive -Latency sensitive -Bandwidth (uni-directional) sensitive -Bandwidth  ...  gives up to 18% improvement in uni-directional bandwidth over HT-Intra-Socket small message latency of 0.35 us • Nehalem systems give up to 40% improvement in Intra-Node latency for Intra-Socket bandwidth  ... 
doi:10.1109/hoti.2009.24 dblp:conf/hoti/SubramoniKP09 fatcat:mwo7ecmmjfd4paplvarvhnvpwi

An efficient quality-aware memory controller for multimedia platform SoC

Kun-Bin Lee, Tzu-Chieh Lin, Chein-Wei Jen
2005 IEEE transactions on circuits and systems for video technology (Print)  
Experimental results of a digital set-top-box emulation system show that the access latency of the latency-sensitive data flows can be effectively reduced by 37%-65% and the memory bandwidths can be precisely  ...  allocated to bandwidth-sensitive data flows with a high degree of control.  ...  Due to the inherent latency limitations of the TDM on-chip communication mechanism [13] , MemMax cannot effectively provide short latency services and only has better improvement on bandwidth utilization  ... 
doi:10.1109/tcsvt.2005.846412 fatcat:izetnphxzbga7kkdtug7ptlr5a

Microbenchmark performance comparison of high-speed cluster interconnects

Jiuxing Liu, B. Chandrasekaran, Weikuan Yu, Jiesheng Wu, D. Buntinas, S. Kini, D.K. Panda, P. Wyckoff
2004 IEEE Micro  
Acknowledgments This research is supported in part by Sandia National Laboratory contract number 30505; Department of Energy grant number DE-FC02-01ER25506; and National Science Foundation grants number  ...  EIA-9986052, CCR-0204429, and CCR-0311542.  ...  Figure 3b shows the bandwidth for different queue sizes (eight and 16). We can see that VAPI is more sensitive to the value of queue size Q.  ... 
doi:10.1109/mm.2004.1268994 fatcat:2tmrx5boybgtxkvbhlmvweey3y

GPCNeT

Sudheer Chunduri, Steven Warren, Nathan Wichmann, Nicholas Wright, Taylor Groves, Peter Mendygral, Brian Austin, Jacob Balma, Krishna Kandalla, Kalyan Kumaran, Glenn Lockwood, Scott Parker
2019 Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '19  
The results show that systems of all technologies and scales are susceptible to congestion and this work motivates the need for congestion control in next-generation networks.  ...  We propose a new open-source benchmark suite called the Global Performance and Congestion Network Tests (GPCNeT) to advance the state of the practice in this area.  ...  access to Edison time and system data.  ... 
doi:10.1145/3295500.3356215 dblp:conf/sc/ChunduriGMABKKL19 fatcat:yb7ctm77xjddvlwp2dlujnnpxm

Integrating Parallel Computing Applications in an ATM Scenario [chapter]

Joan Vila-Sallent, Josep Solé-Pareta
1998 IFIP Advances in Information and Communication Technology  
The proposed mechanism relies on a modified version of the loss recovery procedure of SSCOP, which is enhanced by means of a more intensive exploitation of ATM service categories in order to reduce the  ...  For this purpose, we make use of both the UBR and ABR service categories, with ABR being only introduced in the periods of high latency.  ...  With this AAL, applications are less sensitive to the network load induced by the rest of applications sharing the ATM network, and communications achieve better latency performance.  ... 
doi:10.1007/978-0-387-35388-3_14 fatcat:rzmq4t7lorh3veqzjhzkjq2sxm

The impact of communication locality on large-scale multiprocessor performance

Kirk L. Johnson
1992 SIGARCH Computer Architecture News  
We introduce a model that characterizes application behavior with three parameters that capture computation grain, sensitivity to communication latency, and amount of locality present at execution time  ...  As multiprocessor sizes scale and computer architects turn to interconnection networks with non-uniform communication latencies, the lure of exploiting communication locality to increase performance becomes  ...  Since increases in slope indicate decreased sensitivity to communication latency, this corresponds nicely with the intuition that architectures embodying such mechanisms should be less sensitive to increasing  ... 
doi:10.1145/146628.140403 fatcat:4xy5gxdbeffchppmbeywhxkphe

On the Effects of Memory Latency and Bandwidth on Supercomputer Application Performance

Richard Murphy
2007 2007 IEEE 10th International Symposium on Workload Characterization  
This paper compares the memory performance sensitivity of both traditional and emerging HPC applications, and shows that the new codes are significantly more sensitive to memory latency and bandwidth than  ...  Specifically, the computational work of the application tends to be floating point oriented, and the decomposition of the problem two or three dimensional.  ...  To better quantify each suite's sensitivity to bandwidth and latency effects, the sensitivity must be defined.  ... 
doi:10.1109/iiswc.2007.4362179 dblp:conf/iiswc/Murphy07 fatcat:yt6zhxueibcfloc2htnaj73wwq

Energy Efficient MAC Protocols [article]

S. Hayat, N. Javaid, Z. A. Khan, A. Shareef, A. Mahmood, S. H. Bouk
2012 arXiv   pre-print
loss models for In-body, On-body and Off-body communications in WBASNs and analytically discuss that path loss is maximum in In-body communication because of low energy levels to take care of tissues  ...  MAC protocols with respect to different approaches and techniques which are used for energy minimization, traffic control mechanisms for collision avoidance are discussed.We also present a survey of path  ...  Easy to satisfy the WBANs traffic heterogeneity requirements Sensitivity Sensitive to tuning for neighborhood size and traffic rate Sensitive to clock drift Very sensitive to clock drift Performance  ... 
arXiv:1207.2567v1 fatcat:2egy4ba65nf6li3e7ghg4p57y4

The impact of communication locality on large-scale multiprocessor performance

Kirk L. Johnson
1992 Proceedings of the 19th annual international symposium on Computer architecture - ISCA '92  
We introduce a model that characterizes application behavior with three parameters that capture computation grain, sensitivity to communication latency, and amount of locality present at execution time  ...  As multiprocessor sizes scale and computer architects turn to interconnection networks with non-uniform communication latencies, the lure of exploiting communication locality to increase performance becomes  ...  Since increases in slope indicate decreased sensitivity to communication latency, this corresponds nicely with the intuition that architectures embodying such mechanisms should be less sensitive to increasing  ... 
doi:10.1145/139669.140403 dblp:conf/isca/Johnson92 fatcat:az2rz34vwncbzd5ubv7dr5yl34

A link arbitration scheme for quality of service in a latency-optimized network-on-chip

Jonas Diemer, Rolf Ernst
2009 2009 Design, Automation & Test in Europe Conference & Exhibition  
At the same time, the average latency of best effort traffic is improved compared to a simple prioritization of streaming traffic.  ...  In contrast to many existing quality of service mechanisms, our technique prioritizes best effort over guaranteed bandwidth traffic for optimal latency.  ...  The authors would like to thank the researchers at Intel Germany Research Center for their valuable input and support.  ... 
doi:10.1109/date.2009.5090730 dblp:conf/date/DiemerE09 fatcat:nfonnbpq4nd3xamtrzocqm4cni

Time-Sensitive Networking for robotics [article]

Carlos San Vicente Gutiérrez, Lander Usategui San Juan, Irati Zamalloa Ugarte, Víctor Mayoral Vilches
2018 arXiv   pre-print
We discuss some of the TSN features relevant for deterministic communications and evaluate experimentally one of the shaping mechanisms in an exemplary robotic scenario.  ...  We argue that Time-Sensitive Networking (TSN) will become the de facto standard for real-time communications in robotics.  ...  Later, because of the interest of industry, the goal was extended to define mechanisms for the time-sensitive transmission of data over Ethernet networks.  ... 
arXiv:1804.07643v2 fatcat:ahy5zdrgwffvdfv5fdw57ozepm
« Previous Showing results 1 — 15 out of 30,774 results