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:20190719T085754Z
LOCATION:HG E 3
DTSTART;TZID=Europe/Stockholm:20190612T153000
DTEND;TZID=Europe/Stockholm:20190612T173000
UID:submissions.pasc-conference.org_PASC19_sess154@linklings.com
SUMMARY:MS13 - Programming Models to Enable Scalable Resilience for Extrem
 e Scale Computing Systems
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics, Emerg
 ing Application Domains, Chemistry and Materials, Climate and Weather, Phy
 sics, Solid Earth Dynamics, Life Sciences, Engineering\n\nVeloC: Very Low 
 Overhead Checkpointing System\n\nNicolae\n\nThis talk introduces VeloC, a 
 multi-level checkpoint/restart runtime for high performance computing
  applications that takes advantage of and delivers high performance and sc
 alability for modern, complex heterogeneous storage hierarchies without sa
 crificing ease of use and flexibility. First, th...\n\n-------------------
 --\nProgramming Model Design Tradeoffs of Global vs. Local Recovery for Al
 gorithm Based Fault Tolerance\n\nKolla, Teranishi, Mayo, Salloum, Armstron
 g\n\nWe present design tradeoffs between global and local recovery for alg
 orithm based fault tolerance (ABFT), and implications for programming mode
 l and runtime design. For ABFT algorithms that may rely on global agreemen
 t or a collective action (e.g. ABFT for linear system solvers that involve
  a global...\n\n---------------------\nOpen Discussion on Programming Mode
 ls to Enable Scalable Resilience\n\nTeranishi\n\nOpen discussion\n\n------
 ---------------\nFA-MPI: Using a Parallel Transactional Model of Fault Tol
 erance and Statistical Consensus for the Message Passing Interface\n\nSkje
 llum, Bangalore, Schafer, Hassani, Ghafoor\n\nWe overview FA-MPI, which di
 ffers from leading efforts like ULFM; we address the "non-blocking" functi
 onality of MPI (e.g., MPI_Ibcast). Non-blocking MPI-4 comprises a comprehe
 nsive subset of MPI; all blocking functions can be layered. We assert that
  exascale codes will emphasize non-blocking anyway...\n
END:VEVENT
END:VCALENDAR