tag:blogger.com,1999:blog-36948928.post1689036319937348978..comments2023-11-05T01:36:13.893-08:00Comments on Open Notebook: December 26th ReportJaliya Ekanayakehttp://www.blogger.com/profile/12210985278265903305noreply@blogger.comBlogger2125tag:blogger.com,1999:blog-36948928.post-91993659919903050572008-02-13T13:48:00.000-08:002008-02-13T13:48:00.000-08:00Hi Ping,Nice to hear that you are also interested ...Hi Ping,<BR/><BR/>Nice to hear that you are also interested in the same field of research.<BR/><BR/>Yes we can definitely use the MapReduce paradigm to most of the data parallel applications. Also to the interesting class of applications which can tolerate communication latencies in the range of milliseconds rather than the typical latencies(microseconds) expected in shared memory parallelization techniques.<BR/><BR/>I would like to talk with you and share my thoughts and experience with you. Please send me an email to jekanaya AT cs DOT indiana DOT edu<BR/><BR/>Thanks,<BR/>-jaliyaJaliya Ekanayakehttps://www.blogger.com/profile/12210985278265903305noreply@blogger.comtag:blogger.com,1999:blog-36948928.post-17103600001689706172008-01-30T07:24:00.000-08:002008-01-30T07:24:00.000-08:00Hi,I'm a high energy physicist turned Google softw...Hi,<BR/><BR/>I'm a high energy physicist turned Google software engineer. I'm promoting MapReduce and Google File System in the universities as part of the Google Academic Cloud Computing Initiative in Taiwan. I think it is really possible to use this paradigm in high energy physics: Monte Carlo generation, event reconstruction + splitting, skimming, or making analysis samples. I'd love to talk with you if you are interested.<BR/><BR/>cheers,<BR/>Pingpingooohttps://www.blogger.com/profile/12639061912312063141noreply@blogger.com