BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Support for Managed-Language Workloads in Warehouse-Scale Computer
 s
DTSTART:20151201T120000
DTEND:20151201T130000
DTSTAMP:20260407T134002Z
UID:2d97ba2ca7a48d29f5bee847ec43b0c43402a660085a6819341ecb22
CATEGORIES:Conferences - Seminars
DESCRIPTION:Martin Maas\, University of California\, Berkeley\nData center
  applications and frameworks such as Hadoop\, Spark and ZooKeeper are freq
 uently written in managed languages such as Java or Scala. However\, the m
 anaged language runtime systems they are running across are not primarily 
 designed for distributed data center workloads and therefore exhibit ineff
 iciencies when applied in this setting.\nAt the same time\, the design of 
 warehouse-scale computers is changing. We are expecting a shift towards ra
 ck-scale units with custom SoCs\, fast interconnects and large amounts of 
 shared memory. We believe that this trend creates opportunities to improve
  support for managed-language workloads in data centers.\nIn this talk\, I
  will present some of these challenges and opportunities. I will then show
  how we address some of the challenges in what we call a "Holistic Languag
 e Runtime System”\, a distributed language runtime that collectively man
 ages runtime services across multiple nodes. Using Garbage Collection (GC)
  as an example\, I will show how a Holistic Runtime System is effective bo
 th in reducing the impact of GC pauses on a big data workload\, and in imp
 roving GC-related tail-latencies for a latency-sensitive workload.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR