BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Tail-Latency of Microsecond-Scale Remote Procedure 
 Calls
DTSTART:20210121T101500
DTEND:20210121T110000
DTSTAMP:20260408T035156Z
UID:8ef3ae2fede36214e754ce34bb0cc0fe5f6df16bbcdd000c155dc4a8
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Prof. Edouard Bugnion - EPFL\nIC Faculty candidate\n\nAbst
 ract\nModern webscale applications\, such as a search or social networking
 \, are responsive to hundreds of millions of users by combining the resour
 ces of thousands to millions of machines to store the applications’ data
 set in these computers’ memories.  Within a datacenter\, the applicatio
 ns running on these machines communicate with very short Remote Procedure 
 Calls (RPC) that often take a few microseconds to service but must\, never
 theless\, meet tight service-level objectives expressed in terms of tail l
 atency.  \n\nThe EPFL Datacenter Systems Laboratory has studied the vari
 ous aspects that contribute to tail latency of microsecond-scale RPC withi
 n datacenters\, with contributions in both operating systems and datacente
 r networking.  \n\nResults include a protected dataplane operating syste
 m leveraging virtualization hardware to process RPC with low latency and h
 igh throughput\, complete with an associated control plane for energy prop
 ortionality and workload consolidation (IX)\; a work-conserving\, tail-tol
 erant scheduler for microsecond-scale tasks (Zygos)\; a centralized schedu
 ler\, load-balancing\, and hedging strategy for cloud deployments (LAEDGE)
 . We also developed R2P2 as a transport protocol to make RPC a first-class
  citizen in the datacenter\, which reduces overheads\, eliminates head-of-
 line blocking\, enables scalable\, in-network load balancing\, and allows 
 for the integration of consensus protocols within the transport layer for 
 scalability (HovercRaft).\n\nResults published at OSDI\, SOSP\, NSDI\, USE
 NIX ATC\, Eurosys\, SoCC\, and TOCS\, with 2 Best Paper Awards.  Joint wo
 rk with my graduate students Dr. Marios Kogias\, Dr. George Prekas\, Dr. M
 ia Primorac\, and Adrien Ghosn\, as well as colleagues Profs. Argyraki (EP
 FL)\, Belay (MIT)\, and Kozyrakis (Stanford).\n\nBio\nProf. Edouard Bugnio
 n joined EPFL in 2012\, with a teaching and research focus on datacenter s
 ystems. His areas of interest include operating systems\, datacenter infra
 structure (systems and networking)\, and computer architecture.  Before j
 oining EPFL\, he spent 18 years in the US\, at Stanford (MS ’96\, PhD 
 ’12) and co-founded two startups: VMware and Nuova Systems (acquired by 
 Cisco). He served as VMware’s first CTO and was later the VP/CTO of Cisc
 o’s Server\, Access\, and Virtualization Technology Group.\n\nProf. Bugn
 ion is an ACM Fellow and a member of the Swiss Academy of Technical Scienc
 es (SATW).  He received the ACM Systems Award  in 2009 in recognition fo
 r VMware. His paper “Disco: Running Commodity Operating Systems on Scala
 ble Multiprocessors” was entered into the ACM SIGOPS Hall of Fame Award 
 in 2008. He has won Best Paper Awards at SOSP\, OSDI and Eurosys.  He is 
 the current Scientific Director and Founder/PI of the Swiss Data Science C
 enter\, a  Swiss nation-wide initiative. He serves on the Swiss National 
 COVID-19 Scientific Task Force as the lead expert for digital technologies
 .\n\n\nMore information
LOCATION:https://epfl.zoom.us/j/89914572108?pwd=bGJGRklpY2s4QjlXTGZIWlROcG
 RLUT09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR