BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190719T085745Z
LOCATION:HG F 1
DTSTART;TZID=Europe/Stockholm:20190614T120000
DTEND;TZID=Europe/Stockholm:20190614T123000
UID:submissions.pasc-conference.org_PASC19_sess170_msa226@linklings.com
SUMMARY:Abstractions for Reasoning about Data Object Movement
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics\n\nAbs
 tractions for Reasoning about Data Object Movement\n\nHaine, Haus, Tate\n\
 nMoving data through memory has become a major performance bottleneck, wit
 h the bandwidth per FLOP decreasing and the complexity of the memory hiera
 rchy quickly outgrowing software programming environment abstractions. The
  Cray European Research Lab and our partners are addressing this concern b
 y designing a fundamental data-centric abstraction that represents user da
 ta in various forms as data objects, regardless of its current location in
  the memory system. This abstraction allows middleware to reason about dat
 a movement and dataflow inside applications and workflows. Separately we a
 re designing a memory abstraction framework including user code tiling tha
 t can lean on such data object reasoning to make decisions about memory ti
 ling and promotion. For persistent storage the same abstraction allows us 
 to move beyond configuration, application and library optimization to look
 ing at the whole workflow and to concentrate on data movement driven by de
 pendencies. We believe that being able to schedule application components 
 and coupled applications while being able to reason about their data produ
 ction, data locality, and data consumption, and accounting for the cost of
  moving data between tiers of the memory hierarchy will enable efficient e
 xecution of coupled applications in complex workflows.
END:VEVENT
END:VCALENDAR