BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Towards Resource Efficient Cloud Computing
DTSTART:20140324T161500
DTEND:20140324T173000
DTSTAMP:20260406T172851Z
UID:0d1bddbf40f51fc3942513e54fcda31cee1ca18e80794fcd654c709f
CATEGORIES:Conferences - Seminars
DESCRIPTION:By : Christoforos Kozyrakis\, Stanford UniversityAbstract\nClo
 ud computing promises flexibility and cost effectiveness for both the user
 s and the operators of the warehouse-scale datacenters that power public a
 nd private clouds. Nevertheless\, datacenters currently operate at low uti
 lization\, greatly reducing their cost effectiveness. Moreover\, users oft
 en experience high variability in performance\, especially for the emergin
 g class of latency-critical\, data-intensive applications. The primary sou
 rce of these challenges is the poor use of physical and virtual resources 
 in large-scale datacenters.\nThis talk will show that we can greatly impro
 ve the cost effectiveness and scalability of cloud computing by focusing o
 n resource efficiency. We will show that resource efficient cluster manage
 ment (provisioning & allocation\, application co-scheduling\, and power ma
 nagement) leads to a 3x increase in datacenter utilization\, while also el
 iminating performance variability for individual application. We will also
  discuss how the use of big data techniques alleviates the complexity of m
 anaging large-scale datacenters running thousands of applications. Finally
 \, we will traverse the hardware/software stack and identify further oppor
 tunities to improve resource efficiency and build systems that can deliver
  on the potential of cloud computing.Biography\nChristos Kozyrakis is an A
 ssociate Professor of Electrical Engineering & Computer Science at Stanfor
 d University. He works on architecture\, runtime management\, system softw
 are\, and programming models for systems ranging from cellphones to wareho
 use-scale datacenters. At Berkeley\, he developed the IRAM architecture\, 
 a novel media-processor system that combined vector processing with embedd
 ed DRAM technology. At Stanford\, he co-led the Transactional Coherence an
 d Consistency (TCC) project at Stanford that developed hardware and softwa
 re mechanisms for programming with transactional memory. He also led the R
 aksha project\, that developed practical hardware support and security pol
 icies to deter high-level and low-level security attacks against deployed 
 software. Christos is currently working on hardware and software technique
 s for resource efficient cloud computing. He is also a member of the Perva
 sive Parallelism Lab at Stanford\, a multi-faculty effort to make parallel
  computing practical for the masses.\nChristos received a BS degree from t
 he University of Crete (Greece) and a PhD degree from the University of Ca
 lifornia at Berkeley (USA)\, both in Computer Science. He is the Willard R
 . and Inez Kerr Bell faculty scholar at Stanford and a senior member of th
 e ACM and the IEEE. Christos has received the NSF Career Award\, an IBM Fa
 culty Award\, the Okawa Foundation Research Grant\, and a Noyce Family Fac
 ulty Scholarship.More information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR
