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:20191206T142455Z
LOCATION:Booth N-230
DTSTART;TZID=Europe/Stockholm:20180626T151500
DTEND;TZID=Europe/Stockholm:20180626T154500
UID:isc_hpc_ISC High Performance 2018_sess144_proj108@linklings.com
SUMMARY:(PP23) Decimate: A Portable and Fault-Tolerant Scheduler Extension
  Efficiently Handling a Large Number of Dependent Jobs
DESCRIPTION:Project Poster\n\n(PP23) Decimate: A Portable and Fault-Tolera
 nt Scheduler Extension Efficiently Handling a Large Number of Dependent Jo
 bs\n\nKORTAS, Toye, Hoteit\n\nSimultaneously accommodating needs of our sc
 alability and capacity users on our KAUST XC-40 Shaheen II is challenging.
  To support workflows composed of a large number of jobs, KAUST Supercompu
 ting laboratory has developed Decimate to ease the submission, monitoring 
 and dynamic steering of workflows of dependent jobs. Written in Python 2.7
  and distributed under BSD 2 license and directly installable from pypi.or
 g without requiring any privileges, it extends the SLURM scheduler, transp
 arently adding prologue and epilogue to any user script and submitting the
  right job dependency that automatically add new chunks of work or relaunc
 h a job in case of a hardware, software or numerical convergence failure.\
 n\nDecimate allows a user to:\n• Submit an arbitrary number of jobs re
 gardless of limitation in the scheduling policy.\n• Manage a set of jo
 bs as a single workflow easing their submission, monitoring, deletion or r
 econfiguration.\n• Ease the definition, submission, and management of 
 jobs run on a large set of combinations of parameters.\n• Benefit from
  a centralized log file.\n• Send user-configurable mail messages at an
 y step of its execution of the workflow.\n• To evaluate the outputs of
  a job via a user-configurable shell or Python script and make a decision 
 either to stop the whole workflow, to resubmit partially the failing compo
 nents as is, or to modify it dynamically.\n\nThe proposed poster details D
 ecimate’s implementation, features and its application to a complex and ch
 allenging ocean ensemble data assimilation and forecasting workflow.\n\nPa
 sses: Conference Pass, Exhibition Pass, Clouds and Distributed Computing, 
 HPC workflows, Reliability, Scheduling, System Software & Runtime Systems\
 n\nTag: Conference Pass, Exhibition Pass, Clouds and Distributed Computing
 , HPC workflows, Reliability, Scheduling, System Software & Runtime System
 s
URL:https://2018.isc-program.com/presentation/?id=proj108&sess=sess144
END:VEVENT
END:VCALENDAR