BEGIN:VCALENDAR VERSION:2.0 PRODID:icalendar-ruby CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260605T041824Z UID:a9a86eae-78a8-4692-b9ba-bdfba8f71f1c DTSTART;TZID=Canada/Eastern:20140115T120000 DTEND;TZID=Canada/Eastern:20140115T130000 DESCRIPTION:

This event was exported from Explora
The content provider for this event is: SHARCNET
Registration may be required for the e vent\, please visit the following URL to learn more: http://vidyo.computecanada.ca/flex.html?roomdi rect.html&\;key=Pr1GiEI51kFi

Topic: "\;Using pa rallel I/O in SHARCNET"\;
Speaker: Alex Razoumov\, SHARCNET
Webi nar link: SN-Seminars Vidyo room

With big datasets\, disk I/O o n large parallel systems can pose a significant bottleneck compared to the rest of your code'\;s workflow. Parallel filesystems have been optimiz ed to support large efficient I/O simultaneously by multiple users on mult iple nodes\, however\, contrary to popular thinking\, they do not provide "\;supercomputing"\; disk performance. In this introductory webina r I will talk about the basics of parallel filesystems\, techniques to opt imize your storage\, as well as various methods to organize parallel disk I/O. Due to the lack of time\, I will not go into the details of all possi ble methods\, but will give several examples of parallel I/O using MPI-IO (part of MPI2)\, and then will briefly talk about the strengths and limita tions of most popular higher-level parallel I/O libraries (HDF5\, NetCDF\, and ADIOS).

Need help attending a webinar? See the SHARCNET Help Wiki.

SUMMARY:Webinar "Using parallel I/O in SHARCNET" URL;VALUE=URI:http://vidyo.computecanada.ca/flex.html?roomdirect.html&key=P r1GiEI51kFi END:VEVENT END:VCALENDAR