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:20181221T160726Z
LOCATION:D170
DTSTART;TZID=America/Chicago:20181111T113000
DTEND;TZID=America/Chicago:20181111T115200
UID:submissions.supercomputing.org_SC18_sess149_ws_mchpc107@linklings.com
SUMMARY:Understanding Application Recomputability without Crash Consistenc
 y in Non-Volatile Memory
DESCRIPTION:Workshop\nMemory, NVRAM, Parallel Programming Languages, Libra
 ries, and Models, Workshop Reg Pass\n\nUnderstanding Application Recomputa
 bility without Crash Consistency in Non-Volatile Memory\n\nRen, Wu, Li\n\n
 Emerging non-volatile memory (NVM) is promising to be used as main memory,
  because of its good performance, density, and energy efficiency.  Leverag
 ing the non-volatility of NVM as main memory, we can recover data objects 
 and resume application computation (recomputation) after application crash
 es.  The existing work studies how to ensure that data objects stored in N
 VM can be recovered to a consistent version during system recovery, a prop
 erty referred to as crash consistency. However, enabling crash consistency
  often requires program modification and brings large runtime overhead. \n
 \nIn this paper, we use a different view to examine application recomputat
 ion in NVM. Without taking care of consistency of data objects, we aim to 
 understand if the application can be recomputable, given possible inconsis
 tent data objects in NVM. We introduce a PIN-based simulation tool, NVC, t
 o study application recomputability in NVM without crash consistency. The 
 tool allows the user to randomly trigger application crash and then perfor
 m postmortem analysis (i.e., the analysis on data consistency) on data val
 ues in caches and memory. We use NVC to study a set of applications. We re
 veal that some applications are inherently tolerant to crash consistency. 
 We perform a detailed analysis of the reasons. We study an optimization te
 chnique to accelerate the simulation performance of NVC. The technique all
 ows us to use NVC to study data-intensive applications with large data set
 s.
URL:https://sc18.supercomputing.org/presentation/?id=ws_mchpc107&sess=sess
 149
END:VEVENT
END:VCALENDAR