Fabrizio Petrini, Adolfy Hoisie, Wu-chun Feng, Richard Graham  Home/Search
Context Related
Links: ACM DBLP | lanl.gov/cic19/teams/par_arch/...top.ps Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: lanl.gov/cic19/tea...Publications (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We present an initial performance evaluation of the Quadrics interconnection network (QsNET). We describe the main hardware and software features of QsNET of relevance to the system designer and to the end user. Actual benchmarks are performed on an experimental Linux cluster. The preliminary analysis indicates that the interconnect performs remarkably well, e.g., user-level latency under 2 s and bandwidth over 300 MB/s, ecient support for collective communication patterns, and excellent... (Update)
Context of citations to this paper: More
...the communication performance of Linux and NT clusters, the Cray Origin 2000, IBM SP and Cray T3E. More recently, Petrini et al. [21] examine the performance of Quadrics networks using uni and bi directional ping benchmarks. A different school of thought adopts a more...
...SMP) This test provides information on the behavior of a single I O node when serving multiple simultaneous requests. Previous results [15] have shown that read and write operations provide no significant differences. The aggregate bandwidth plots are depicted in figure 16(a)...
Cited by: More
Symmetric Data Objects and Remote Memory Access.. - Nieplocha.. (Correct)
Micro-Benchmark Level Performance Comparison of.. - Liu.. (2003) (Correct)
An Evaluation of Current High-Performance Networks - Bell, Bonachea, Cote.. (2003) (Correct)
Similar documents (at the sentence level): More
67.9%: Performance Evaluation of the Quadrics Interconnection.. - Petrini, Hoisie, Feng.. (2001) (Correct)
23.2%: Performance Evaluation of the Quadrics Interconnection - Petrini, Coll.. (2001) (Correct)
17.6%: The Quadrics Network (QsNet): High-Performance.. - Petrini, Feng.. (2001) (Correct)
Active bibliography (related documents): More All
0.2: Scalable Collective Communication on the ASCI Q Machine - Fabrizio Petrini Juan (2003) (Correct)
0.2: Communication Performance of Wormhole Interconnection Networks - Petrini (1997) (Correct)
0.2: Latency and Bandwidth Requirements of Massively Parallel.. - Petrini (1999) (Correct)
Similar documents based on text: More All
0.8: The Quadrics Network: High Performance Clustering.. - Petrini, Feng, Hoisie, .. (2002) (Correct)
0.4: Static Allocation of Multirail Networks - Coll, Frachtenberg, Petrini.. (2001) (Correct)
0.4: Using Multirail Networks in High Performance Clusters - Coll, Frachtenberg.. (2001) (Correct)
Related documents from co-citation: More All
8: Elite Reference Manual (context) - World - 1999
8: Elan Reference Manual (context) - World - 1999
7: Fat-trees: Universal networks for hardwareefficient supercomputing (context) - Leiscerson - 1985
BibTeX entry: (Update)
Fabrizio Petrini, Adolfy Hoisie, Wu chun Feng, and Richard Graham. Performance Evaluation of the Quadrics Interconnection Network. In Workshop on Communication Architecture for Clusters (CAC '01), San Francisco, CA, April 2001. http://citeseer.ist.psu.edu/article/petrini01performance.html More
@inproceedings{ petriniperformance,
author = "Fabrizio Petrini and Adolfy Hoisie and {Wu-Chun} Feng and Richard Graham",
title = "Performance Evaluation of the Quadrics Interconnection Network",
pages = "165--165",
url = "citeseer.ist.psu.edu/article/petrini01performance.html" }
Citations (may not include all citations):462 Deadlock-Free Message Routing in Multiprocessor Interconnect.. (context) - Dally, Seitz - 1987 ACM DBLP
447 MPI - The Complete Reference (context) - Snir, Otto et al. - 1998
173 Hot-spot Contention and Combining in Multistage Interconnect.. (context) - Pster, Norton - 1985
111 Myrinet: A Gigabit-per-Second Local Area Network (context) - Boden, Cohen et al. - 1995 DBLP
30 MPI - The Complete Reference (context) - Gropp, Huss-Lederman et al. - 1998
21 Elan Reference Manual (context) - World - 1999
14 MPI-2: Extending the Message Passing Interface - Geist, Gropp et al. - 1996
14 Elite Reference Manual (context) - World - 1999
13 Elan Programming Manual (context) - World - 1999
12 Gigabit Ethernet: Technology and Applications for High Speed.. (context) - Seifert - 1998
11 trees: High Performance Networks for Massively Parallel Arch.. (context) - Petrini, Vanneschi - 1997
7 The SCI Standard and Applications of SCI (context) - Hellwagner - 1999 ACM DBLP
7 Performance Analysis of Wormhole Routed k-ary n-trees - Petrini, Vanneschi - 1998 DBLP
6 Fat-Trees: Universal Networks for Hardware Ecient Supercompu.. (context) - Leiserson - 1985
5 From HiPPI-800 to HiPPI-6400: A Changing of the Guard and Ga.. (context) - Tolmie, Boorman et al. - 1999
1 Inniband architecture tutorial (context) - Cassiday - 2000
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.c3.lanl.gov/cic19/teams/par_arch/Publications.html): More
The Performance Realities Of Massively Parallel.. - Lubeck, Simmons.. (1992) (Correct)
Performance Evaluation of the SGI Origin2000: A.. - Wasserman, Lubeck.. (Correct)
Benchmark Tests on a Silicon Graphics R8000-Based Workstation - Wasserman (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC