BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20200129T163557Z
LOCATION:708
DTSTART;TZID=America/Denver:20191117T120000
DTEND;TZID=America/Denver:20191117T121500
UID:submissions.supercomputing.org_SC19_sess112_pec243@linklings.com
SUMMARY:Data-Aware and Simulation-Driven Planning of Scientific Workflows 
 on IaaS Clouds
DESCRIPTION:Workshop\n\nData-Aware and Simulation-Driven Planning of Scien
 tific Workflows on IaaS Clouds\n\nN'Takpé, Gnimassoun, Oumtanaga, Suter\n\
 nThe promise of an easy access to a virtually unlimited number of resource
 s makes Infrastructure as a Service Clouds a good candidate for the execut
 ion of data-intensive workflow applications composed of hundreds of comput
 ational tasks. Thanks to a careful execution planning, Workflow Management
  Systems can build a tailored compute infrastructure by combining a set of
  virtual machine instances. However, these applications usually rely on fi
 les to handle dependencies between tasks. A storage space shared by all vi
 rtual machines may become a bottleneck and badly impact the application ex
 ecution time. \n\nIn this paper, we propose an original data-aware plannin
 g algorithm that leverages two characteristics of a family of virtual mach
 ines instances, i.e., a large number of cores and a dedicated storage spac
 e on fast SSD drives, to improve data locality, hence reducing the amount 
 of data transfers over the network during the execution of a workflow. We 
 also propose a simulation-driven approach to solve a cost-performance opti
 mization problem and correctly dimension the virtual infrastructure onto w
 hich execute a given workflow. Experiments conducted with real application
  workflows show the benefits of the presented algorithms. The data-aware p
 lanning leads to a clear reduction of both execution time and volume of da
 ta transferred over the network while the simulation-driven approach allow
 s us to dimension the infrastructure in a reasonable time.\n\nTag: Worksho
 p Reg Pass, Extreme Scale Computing, Scalable Computing, Scientific Workfl
 ows\n\nRegistration Category: Workshop Reg Pass, Extreme Scale Computing, 
 Scalable Computing, Scientific Workflows
URL:https://sc19.supercomputing.org/presentation/?id=pec243&sess=sess112
END:VEVENT
END:VCALENDAR