| |
| | Rice Computer Science: Rice Computer Science-Colloquia</u> <i>(Site not responding. Last check: 2007-10-26)</i></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> <b>Replication</b> is a key approach for scaling wide-area applications and for achieving high-performance and high-availability. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> However, because of wide-area latency and potential Internet congestion/failures, consistency overhead in a naive <b>replication</b> system may actually lead to degraded overall performance and availability relative to a centralized architecture. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> In this talk, I will discuss why system consistency is continuous rather than binary for many applications, and how these applications can significantly benefit from exploring the semantic space between strong consistency and optimistic consistency.</td></tr>
<tr><td></td><td colspan=2><font color=gray>www.cs.rice.edu /Colloquia/yu-02-04.shtml</font> (265 words)</td></tr>
</table>
</td>
</tr>
</table><body face="Arial">
<br>
<table cellpadding=0>
<tr>
<td> </td>
<td>
<table >
<tr><td> </td><td colspan=2><a href="http://www.almaden.ibm.com/cs/TSpaces/ets.html">Enterprise TSpaces - TSpaces - Computer Science Research at Almaden</a></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> By using operation <b>replication</b> between TSpaces servers in so-called <b>replication</b> groups the availability of tuples increases with the number of TSpaces servers. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> At a TSpaces server level each server is able to fully recover from a crash, that is, it is able to recover its internal state and reintegrate into the <b>replication</b> group. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> The former is archieved by dynamically increasing or decreasing the number of TSpaces servers in a <b>replication</b> group.</td></tr>
<tr><td></td><td colspan=2><font color=gray>www.almaden.ibm.com /cs/TSpaces/ets.html</font> (364 words)</td></tr>
</table>
</td>
</tr>
</table><body face="Arial">
<br>
<table cellpadding=0>
<tr>
<td> </td>
<td>
<table >
<tr><td> </td><td colspan=2><a href="http://parasol.tamu.edu/seminar/abstract.php?talk_id=211">Parasol Seminar Summer 2003 | Parasol Laboratory Intranet</a></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> It has generally been believed that this combination is hard to achieve through <b>replication</b> because of the growth of the number of conflicts. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> Conflict-aware <b>replication</b> provides near-linear throughput scaling up to a large number of <a href="/topics/Database" title="Database" class=fl>database</a> replicas for the most common workload of TPC-W. While workloads with high levels of conflicts, such as the TPC-W ordering mix, currently scale only to a lower number of replicas, early results show potential for compiler-directed scaling improvements for these workloads. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> Cristiana Amza received her Ph.D. and M.S. degrees in <b>Computer</b> <b>Science</b> from Rice University in May 2003 and 1997, respectively.</td></tr>
<tr><td></td><td colspan=2><font color=gray>parasol.tamu.edu /seminar/abstract.php?talk_id=211</font> (335 words)</td></tr>
</table>
</td>
</tr>
</table><body face="Arial">
<br>
<table cellpadding=0>
<tr>
<td> </td>
<td>
<table >
<tr><td> </td><td colspan=2><u>International Computer Science Institute Talks</u> <i>(Site not responding. Last check: 2007-10-26)</i></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> The <b>replication</b> of tasks may be desirable and explicitly performed, such as the copying of the same content to multiple network points to increase its availability and reduce expected retrieval latency. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> In other instances, the <b>replication</b> may occur out of necessity, such as when numerous independent 802.11 wireless gateways are assigned the same transmission channel because the number of gateways exceeds the number of available channels. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> In the context of this model, we present a novel, elegant, distributed algorithm that assigns tasks to nodes in a manner that is amenable to a large body of network tasking scenarios.</td></tr>
<tr><td></td><td colspan=2><font color=gray>www.icsi.berkeley.edu /talks/Rubenstein.html</font> (345 words)</td></tr>
</table>
</td>
</tr>
</table><body face="Arial">
<br>
<table cellpadding=0>
<tr>
<td> </td>
<td>
<table >
<tr><td> </td><td colspan=2><a href="http://www.research.ibm.com/compsci/project_spotlight/distributed/dsc">IBM Research | Technical Disciplines | Computer Science</a></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> For some applications it is sufficient to <b>replicate</b> using unreliable multicast technology. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> The DPS is based on our versatile <b>replication</b> infrastructure (VRI) and is configurable with respect to its delivery guarantees. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> DCS supports WebSphere components’ state <b>replication</b> requirements (e.g., http session and stateful beans) as well as the distribution and <a href="/topics/Synchronization" title="Synchronization" class=fl>synchronization</a> of WebSphere artifacts for performance, scalability, and availability.</td></tr>
<tr><td></td><td colspan=2><font color=gray>www.research.ibm.com /compsci/project_spotlight/distributed/dsc</font> (941 words)</td></tr>
</table>
</td>
</tr>
</table><body face="Arial">
<br>
<table cellpadding=0>
<tr>
<td> </td>
<td>
<table >
<tr><td> </td><td colspan=2><a href="http://www.almaden.ibm.com/software/projects/arms">IBM Research | Almaden Research Center | Computer Science</a></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> <a href="/topics/Database" title="Database" class=fl>database</a> <b>replication</b> technologies are good in terms of providing the <a href="/topics/Transaction" title="Transaction" class=fl>transaction</a> level consistency within a <a href="/topics/Database" title="Database" class=fl>database</a> where storage level <b>replication</b> technologies are good in terms of providing the I/O level data consistency across <a href="/topics/Database" title="Database" class=fl>databases</a>, files and even across set of applications on different platforms. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> Even sometimes such a complexity in managing the <b>replication</b> technologies and embedding the technology specific artifacts in the application logic makes it difficult for applications to switch from one <b>replication</b> technology to another or sometimes even upgrade the existing <b>replication</b> technology. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> So segregating the <b>replication</b> functionality embedded in various applications and providing it as an infrastructure level service that various applications can invoke specifying their high level <b>replication</b> goals is a key requirement on today’s IT infrastructures.</td></tr>
<tr><td></td><td colspan=2><font color=gray>www.almaden.ibm.com /software/projects/arms</font> (700 words)</td></tr>
</table>
</td>
</tr>
</table><body face="Arial">
<br>
<table cellpadding=0>
<tr>
<td> </td>
<td>
<table >
<tr><td> </td><td colspan=2><u>Computer Viruses [encyclopedia]</u> <i>(Site not responding. Last check: 2007-10-26)</i></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> In <b>computer</b> <b>science</b> a virus is a piece of program code that, like a biological virus, makes copies of itself and spreads by attaching itself to a host, often damaging the host in the process. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> A small percentage of viruses are the result of <b>computer</b> code that operates in an unexpected manner, but the majority of viruses are programs deliberately written to interfere with, or damage, other programs or <b>computer</b> systems. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> At bootstrap the <b>computer</b> runs the code located in the boot sector, which is replaced by virus-code.</td></tr>
<tr><td></td><td colspan=2><font color=gray>www.kosmoi.com /Computer/Security/Virus</font> (1807 words)</td></tr>
</table>
</td>
</tr>
</table><body face="Arial">
<br>
<table cellpadding=0>
<tr>
<td> </td>
<td>
<table >
<tr><td> </td><td colspan=2><a href="http://hssl.cs.jhu.edu/people.htm">Department of Computer Science</a></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> is an assistant professor in the Department of <b>Computer</b> <b>Science</b>. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> To this end, he studies data placement, <b>replication</b>, concurrency control, failure detection, and <a href="/topics/Fault_tolerance" title="Fault_tolerance" class=fl>fault tolerance</a> in the context of high-performance <b>computing</b> and wide-area <a href="/topics/Distributed-Computing" title="Distributed Computing" class=fl>distributed systems</a>. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> Anjali Prakash graduated with an MSE in <b>Computer</b> <b>Science</b> in 2004.</td></tr>
<tr><td></td><td colspan=2><font color=gray>hssl.cs.jhu.edu /people.htm</font> (536 words)</td></tr>
</table>
</td>
</tr>
</table><body face="Arial">
<br>
<table cellpadding=0>
<tr>
<td> </td>
<td>
<table >
<tr><td> </td><td colspan=2><a href="http://www.lclark.edu/dept/public/chr_ckeckscience.html">L&C Chronicle - Keck enhances computer science program</a></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> Lewis & Clark College received a $500,000 grant from the W. Keck Foundation of Los Angeles to enhance and expand the College’s <b>computer</b> <b>science</b> curriculum. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> The three-year grant enables the Department of Mathematical <b>Sciences</b> to develop new courses, to fund a new faculty position, to create a <b>computer</b> laboratory, to increase faculty-student research opportunities, to support an interdisciplinary seminar series, and to purchase <b>computers</b> to support collaboration throughout the Division of Mathematical and Natural <b>Sciences</b>. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> Possible topics include Geographical Information Systems and <b>computer</b> modeling to analyze environmental problems, <b>computer</b> simulation and <b>replication</b> of human behavior patterns in psychology, <b>computational</b> chemistry and molecular modeling, and the use of artificial <a href="/topics/Intelligence-%28trait%29" title="Intelligence %28trait%29" class=fl>intelligence</a> in international relations.</td></tr>
<tr><td></td><td colspan=2><font color=gray>www.lclark.edu /dept/public/chr_ckeckscience.html</font> (556 words)</td></tr>
</table>
</td>
</tr>
</table><body face="Arial">
<br>
<table cellpadding=0>
<tr>
<td> </td>
<td>
<table >
<tr><td> </td><td colspan=2><u>Department of Computer Science</u> <i>(Site not responding. Last check: 2007-10-26)</i></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> <b>Replication</b> of date can help enable high throughput file transfer and scalable resource storage in these scientific Grid applications that involve large data transfers. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> However, the selection of a replica can significantly influence the efficiency of a <b>replication</b> scheme. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> Many current approaches assume that a significant amount of data is available, such as network status information, log files of historical GridFtp file transfers, CPU status and predictions, etc. We propose a lightweight Instance-Based Learning (IBL) algorithm to allow efficient replica selection with much less required data.</td></tr>
<tr><td></td><td colspan=2><font color=gray>www.cs.uchicago.edu /events/273</font> (200 words)</td></tr>
</table>
</td>
</tr>
</table><body face="Arial">
<br>
<table cellpadding=0>
<tr>
<td> </td>
<td>
<table >
<tr><td> </td><td colspan=2><a href="http://www.engr.uiuc.edu/Publications/engineering_research/1998/co.html">Computer Science</a></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> The Department of <b>Computer</b> <b>Science</b> is one of the largest and oldest in the country. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> The National <b>Computational</b> <b>Science</b> Alliance (NCSA) supercomputers are a 64-processor SGI Power Challenge Array, and a 64-processor Convex/HP Exemplar, and a 128-processor Silicon Graphics Origin 2000 system along with a number of other large-scale systems. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> As part of the Caltech <b>Computational</b> Facility for Simulating the Dynamic Response of Materials, we are working closely with application and <b>computing</b> researchers at the three national laboratories (Los Alamos, Sandia, and Lawrence Livermore) to instrument and analyze the input/output behavior of large-scale applications in the Accelerated Strategic <b>Computing</b> Initiative (ASCI).</td></tr>
<tr><td></td><td colspan=2><font color=gray>www.engr.uiuc.edu /Publications/engineering_research/1998/co.html</font> (14920 words)</td></tr>
</table>
</td>
</tr>
</table><body face="Arial">
<br>
<table cellpadding=0>
<tr>
<td> </td>
<td>
<table >
<tr><td> </td><td colspan=2><u>MING LI</u> <i>(Site not responding. Last check: 2007-10-26)</i></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> The research work is to develop a highly reliable <a href="/topics/Cluster" title="Cluster" class=fl>cluster</a> management middleware for high performance <a href="/topics/Cluster" title="Cluster" class=fl>cluster</a> <b>computing</b> systems. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> a sophisticated state machine <b>replication</b> mechanism for the <a href="/topics/Cluster" title="Cluster" class=fl>cluster</a> managers and a multicast protocol for reliable and totally ordered message delivery to all the manager replicas. </td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> The objective of the project is to deploy scalable <a href="/topics/Cluster" title="Cluster" class=fl>cluster</a> <b>computing</b> technology in space.</td></tr>
<tr><td></td><td colspan=2><font color=gray>www.cs.ucla.edu /~mli</font> (498 words)</td></tr>
</table>
</td>
</tr>
</table><script language="JavaScript">
<!--
// This function displays the ad results.
// It must be defined above the script that calls show_ads.js
// to guarantee that it is defined when show_ads.js makes the call-back.
function google_ad_request_done(google_ads) {
// Proceed only if we have ads to display!
if (google_ads.length < 1 )
return;
var s = '';
// For text ads, display each ad in turn.
// In this example, each ad goes in a new row in the table.
if (google_ads[0].type == 'text') {
for(i = 0; i < 1; ++i) {
s = '<body face="Arial"><br><table cellpadding=0><tr><td> </td><td><table ><tr><td> </td><td colspan=2>' +
'<a href="' + google_ads[i].url + '" title="' + google_ads[i].visible_url + '">' + google_ads[i].line1 + '</a> <span style="font-size:10pt">';
if (google_info.feedback_url) {
s += '<a href="' + google_info.feedback_url + '" style="color:#7070F0;text-decoration:none">(Ads by Google)</a>';
} else {
s += '(Ads by Google)';
}
s += '</span></td></tr>' +
'<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td>' + '<a href="' + google_ads[i].url + '" title="' + google_ads[i].visible_url + '" style="text-decoration:none;">' + google_ads[i].line2 + ' ' + google_ads[i].line3 + '</a></td></tr>' +
'<tr><td></td><td colspan=2><font color=gray>' + '<a href="' + google_ads[i].url + '" title="' + google_ads[i].visible_url + '" style="text-decoration:none; color:gray;">' + google_ads[i].visible_url +
'</a></font></td></tr></table></td></tr></table>';
d = document.getElementById('ad' + (i + 1));
d.innerHTML = s;
d.style.display = 'block';
}
s = '';
for(i = 1; i < google_ads.length; i++) {
s += '<div class="r" style="margin-left: 14px"><table cellspacing=0 cellpadding=0><tr>' +
// '<td valign=top><img src="/images/a.gif"/ style="padding-top: 3px; padding-right: 3px"></td>' +
'<td ><a href="' + google_ads[i].url + '" title="' + google_ads[i].visible_url + '">' +
google_ads[i].line1 +
'<div style="text-decoration: none; ">' +
google_ads[i].line2 + ' ' + google_ads[i].line3 + '</div></a>' +
'<font color="gray"><a href="'+ google_ads[i].url + '" title="' + google_ads[i].visible_url + '" style="text-decoration:none; color:gray;">' + google_ads[i].visible_url +
'</a></font>' +
'</td></tr></table></div>'
}
d = document.getElementById('sky1');
d.innerHTML = s;
if(s.length > 0) {
document.getElementById('sky').style.display = 'block';
}
}
/*
<body face="Arial"><br><table cellpadding=0><tr><td> </td><td><table ><tr><td> </td><td colspan=2>
<a href=" ### GOOGLE ADS[i] URL ### "> ### GOOGLE ADS[i] VISIBLE URL ### </a></td></tr>
<tr><td valign=top><img style="margin-top:4px;" src=/images/a.gif></td><td></td><td> ### LINE 2 ### ### LINE 3 ###</td></tr>
<tr><td></td><td colspan=2><font color=gray> ### link ### </font> (sponsored link)</td></tr>
</table></td></tr></table>
*/
/*
// For an image ad, display the image; there will be only one .
if (google_ads[0].type == 'image') {
s += '<tr><td align="center">' +
'<a href="' + google_ads[0].url + '"style="text-decoration: none">' +
'<img src="' + google_ads[0].image_url +
'" height="' + google_ads[0].height +
'" width="' + google_ads[0].width +
'" border="0"></a></td></tr>';
}
// Finish up anything that needs finishing up
s += '</table>';
*/
// document.write(s);
return;
}
-->
</script>
<script language="JavaScript">
<!--
// This script sets the attributes for requesting ads.
google_ad_client = "pub-9457578638026753";
google_max_num_ads = 6;
google_feedback = "on";
google_ad_output = "js";
google_ad_channel = "844964098";
google_kw_type = "broad";
google_kw = "Replication computer science ";
google_ad_type = "text_image";
google_image_size = "728x90";
google_encoding = "latin1";
-->
</script>
<script language="JavaScript" src="http://pagead2.googlesyndication.com/pagead/show_ads.js">
</script>
<br> <p style="margin-left:30px;font-size:13px;"><b>Try your search on: <a href="http://www.qwika.com/find/Replication (computer science)">Qwika</a> (all wikis)</b></p>
<form action=http://www.factbites.com/search.php><table width="100%" cellspacing=0 cellpadding=0 border=0><tr><td background="/images/f1.gif"><table cellspacing=0 cellpadding=0 border=0 background="/images/b.gif"><tr><td><img src="/images/f2.gif" width=38 height=37 alt=" "/></td><td><table cellspacing=0 cellpadding=0 border=0><tr><td><a href="/"><img src="/images/f3.gif" width=95 height=37 alt="Factbites" border=0 /></a><img src="/images/b.gif" width=15 height=1 alt=" "/></td><td valign=bottom><input type=text size=30 name=kp><img src="/images/b.gif" width=2 height=1 alt=" " /><input type=submit value=" Find » " class=b2></td></tr></table></td></tr><tr><td> </td><td><span class=f>
<a href="http://www.factbites.com/about_us.php">About us</a> |
<a href="http://www.factbites.com/why_use_us.php">Why use us?</a> |
<a href="http://www.factbites.com/reviews.php">Reviews</a> |
<a href="http://www.factbites.com/press.php">Press</a> |
<a href="http://www.factbites.com/contact_us.php">Contact us</a>
<br />Copyright © 2005-2007 www.factbites.com Usage implies agreement with <a href=http://www.factbites.com/terms_and_conditions.php>terms</a>.</span></td></tr></table><img src="/images/b.gif" width=450 height=1 alt=" " /></td></tr></table></form>
<script src="http://www.google-analytics.com/urchin.js" type="text/javascript">
</script>
<script type="text/javascript">
_uacct = "UA-317061-4";
urchinTracker();
</script>
</body></html>
| |
