BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20121114T180000Z
DTEND:20121114T183000Z
LOCATION:355-D
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: With the onset of extreme-scale computing, scientists are increasingly unable to save sufficient raw simulation data to persistent storage. Consequently, the community is shifting away from a post-process centric data analysis pipeline to a combination of analysis performed in-situ (on primary compute resources) and in-transit (on secondary resources using asynchronous data transfers). In this paper we summarize algorithmic developments for three common analysis techniques: topological analysis, descriptive statistics, and visualization.  We describe a resource scheduling system that supports various analysis workflows, and discuss our use of the DataSpaces and ADIOS frameworks to transfer data between in-situ and in-transit computations. We demonstrate the efficiency of our lightweight, flexible framework on the Jaguar XK6, analyzing data generated by S3D, a massively parallel turbulent combustion code. Our framework allows scientists dealing with the data deluge at extreme-scale to perform analyses at increased temporal resolutions, mitigate I/O costs, and significantly improve time to insight.
SUMMARY:Combining In-Situ and In-Transit Processing to Enable Extreme-Scale Scientific Analysis
PRIORITY:3
END:VEVENT
END:VCALENDAR
BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20121114T180000Z
DTEND:20121114T183000Z
LOCATION:355-D
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: With the onset of extreme-scale computing, scientists are increasingly unable to save sufficient raw simulation data to persistent storage. Consequently, the community is shifting away from a post-process centric data analysis pipeline to a combination of analysis performed in-situ (on primary compute resources) and in-transit (on secondary resources using asynchronous data transfers). In this paper we summarize algorithmic developments for three common analysis techniques: topological analysis, descriptive statistics, and visualization.  We describe a resource scheduling system that supports various analysis workflows, and discuss our use of the DataSpaces and ADIOS frameworks to transfer data between in-situ and in-transit computations. We demonstrate the efficiency of our lightweight, flexible framework on the Jaguar XK6, analyzing data generated by S3D, a massively parallel turbulent combustion code. Our framework allows scientists dealing with the data deluge at extreme-scale to perform analyses at increased temporal resolutions, mitigate I/O costs, and significantly improve time to insight.
SUMMARY:Combining In-Situ and In-Transit Processing to Enable Extreme-Scale Scientific Analysis
PRIORITY:3
END:VEVENT
END:VCALENDAR