BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20181221T160728Z
LOCATION:D168
DTSTART;TZID=America/Chicago:20181112T121500
DTEND;TZID=America/Chicago:20181112T122000
UID:submissions.supercomputing.org_SC18_sess140_ws_isav101@linklings.com
SUMMARY:Scheduling for In-machine Analytics: Data Size Is Important
DESCRIPTION:Workshop\nData Analytics, Data Management, Visualization, Work
 shop Reg Pass\n\nScheduling for In-machine Analytics: Data Size Is Importa
 nt\n\nHonore, Aupy, Goglin\n\nWith the goal of performing exascale computi
 ng, the importance of I/O management becomes increasingly critical to main
 tain system performance.  While the computing capacities of machines are g
 etting higher, the I/O capabilities of systems do not follow the same tren
 d.  To address this issue, the HPC community proposed new solutions such a
 s online in-machine analysis to overcome the limitations of basic post-mor
 tem data analysis where the data have to be stored on the Parallel File Sy
 stem (PFS) first to be processed later.\n\nIn this paper, we propose to st
 udy different scheduling strategies for in-machine analytics. Our goal is 
 to extract the most important features of analytics that directly determin
 e the efficiency  of scheduling strategies. To do so, we propose a memory-
 constraint modelization for in-machine\nanalysis. It automatically determi
 nes hardware resource partitioning and proposes scheduling policies for si
 mulation and analysis.  We evaluate our model through simulations and obse
 rve that it is critical to base scheduling decisions on the memory needs o
 f each analytics. We also note unexpected behaviors from which we deduce t
 hat modeling the in-machine paradigm for HPC applications requires deep un
 derstanding of task placement, data movement and hardware partitioning.
URL:https://sc18.supercomputing.org/presentation/?id=ws_isav101&sess=sess1
 40
END:VEVENT
END:VCALENDAR