{"id":530,"date":"2013-01-09T11:16:43","date_gmt":"2013-01-09T10:16:43","guid":{"rendered":"https:\/\/project.inria.fr\/plasma-lab\/?page_id=530"},"modified":"2015-03-13T11:44:15","modified_gmt":"2015-03-13T10:44:15","slug":"igrida-experimentation","status":"publish","type":"page","link":"https:\/\/project.inria.fr\/plasma-lab\/documentation\/tutorial\/igrida-experimentation\/","title":{"rendered":"IGRIDA experimentation"},"content":{"rendered":"

<\/p>\n

Presentation<\/h3>\n

When designing Plasma Lab we wanted to be able to use a distributed version either on a small network in our team or on a bigger network like a grid.<\/p>\n

To test our distributed solution we used IGRIDA<\/a><\/strong> which is a computing cluster available to research teams at INRIA Rennes. For this experimentation we used the OAR scheduler which is in beta test phase on IGRIDA.<\/p>\n

\n

Test protocol<\/h3>\n

For our experimentation we used the Randomised dining philosophers<\/a> (Lehmann & Rabin) problem in PRISM format. We used models with number of philosophers ranging from 3 to 300<\/strong>.<\/p>\n

We have checked the property: ‘If a philosopher is hungry, then eventually some philosopher eats’ with a probability of 99% and a precision of 0.1%<\/strong> (Chernoff parameters epsilon = 0.001, delta = 0.99).\u00a0 These parameters result in more than 350000 generated traces<\/strong> for each experiments.<\/p>\n

The Plasma Lab project containing all these models and properties can be downloaded here.<\/p>\n

\n

Results<\/h3>\n

Here are the results of our experiments.<\/p>\n

\"\"<\/a>

Plasma Lab distributed algorithm performance<\/p><\/div>\n

On this figure, duration of the experimentation in milliseconds is plotted against the number of IGRIDA nodes used for our experiments. The color of a plot indicate the number of philosophers for the experiment.<\/p>\n

When multiplying the number of nodes by 2 we computed an average speedup of 1.66. The speedup increased with the complexity of the problem reaching the value of 1.79 for the 300 philosophers problem.<\/p>","protected":false},"excerpt":{"rendered":"

Presentation When designing Plasma Lab we wanted to be able to use a distributed version either on a small network in our team or on a bigger network like a grid. To test our distributed solution we used IGRIDA which is a computing cluster available to research teams at INRIA\u2026<\/p>\n

Continue reading<\/span><\/i><\/a> <\/p>\n","protected":false},"author":234,"featured_media":0,"parent":135,"menu_order":0,"comment_status":"closed","ping_status":"open","template":"","meta":{"footnotes":""},"class_list":["post-530","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/project.inria.fr\/plasma-lab\/wp-json\/wp\/v2\/pages\/530","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/project.inria.fr\/plasma-lab\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/project.inria.fr\/plasma-lab\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/plasma-lab\/wp-json\/wp\/v2\/users\/234"}],"replies":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/plasma-lab\/wp-json\/wp\/v2\/comments?post=530"}],"version-history":[{"count":14,"href":"https:\/\/project.inria.fr\/plasma-lab\/wp-json\/wp\/v2\/pages\/530\/revisions"}],"predecessor-version":[{"id":1822,"href":"https:\/\/project.inria.fr\/plasma-lab\/wp-json\/wp\/v2\/pages\/530\/revisions\/1822"}],"up":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/plasma-lab\/wp-json\/wp\/v2\/pages\/135"}],"wp:attachment":[{"href":"https:\/\/project.inria.fr\/plasma-lab\/wp-json\/wp\/v2\/media?parent=530"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}