BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Naiad: a timely dataflow system
DTSTART:20131008T151500
DTEND:20131008T160000
DTSTAMP:20260407T034930Z
UID:3b9bc1ce877c4eae5a4c06931b75ba038dea9d12073aeb9c728aa0b2
CATEGORIES:Conferences - Seminars
DESCRIPTION:Derek Murray\, Microsoft Research\nNaiad is a distributed syst
 em that combines the high throughput of batch processors\, the low latency
  of stream processors\, and the ability to perform iterative and increment
 al computations. These requirements raise a fundamental challenge: how to 
 coordinate execution efficiently in a computation with complex data depend
 encies.\nTo resolve this challenge\, we introduce "timely dataflow"\, whic
 h is a computational model that captures opportunities for parallelism acr
 oss a wide class of algorithms\, and gives rise to an efficient\, lightwei
 ght coordination mechanism. The resulting system is capable of such divers
 e tasks as streaming data analysis\, iterative machine learning\, and inte
 ractive graph mining. Our evaluation shows that Naiad outperforms existing
  specialized systems in their target domains.\nThis presentation is based 
 on a paper to be presented at SOSP 2013\, and is joint work with Frank McS
 herry\, Rebecca Isaacs\, Michael Isard\, Paul Barham and Martin Abadi.
LOCATION:BC 410 https://plan.epfl.ch/?room==BC%20410
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR