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:20181221T160727Z
LOCATION:D175
DTSTART;TZID=America/Chicago:20181111T171400
DTEND;TZID=America/Chicago:20181111T173000
UID:submissions.supercomputing.org_SC18_sess143_ws_drbsd111@linklings.com
SUMMARY:A Study on Checkpoints Compression for Adjoint Computation
DESCRIPTION:Workshop\nData Management, Hot Topics, Scientific Computing, W
 orkshop Reg Pass\n\nA Study on Checkpoints Compression for Adjoint Computa
 tion\n\nHou, Narayanan, Goldberg, Kukreja, Nicolae...\n\nWhen we want to u
 nderstand the sensitivity of a simulation model with respect to an input v
 alue or to optimize an objective function, the gradient usually provides a
  good hint. The adjoint state method is a widely used numerical method to 
 compute the gradient of a function. It decomposes functions into a sequenc
 e of basic operations. It performs a forward sweep to evaluate the functio
 n, followed by a backward sweep to calculate the gradient using the chain 
 rule iteratively. One limitation of the adjoint state method is that all i
 ntermediate values from the forward sweep are needed by the backward sweep
 . Usually, we keep only a portion of those values, called checkpoints, in 
 the memory because of limited space. The remaining values are either store
 d on the hard disk or recomputed from the nearest checkpoint whenever need
 ed. In this work, we seek to compress the intermediate values in order to 
 better utilize limited space in the memory and to speed the I/O when check
 pointing to the hard disk.
URL:https://sc18.supercomputing.org/presentation/?id=ws_drbsd111&sess=sess
 143
END:VEVENT
END:VCALENDAR