BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:[Systems talk]: Accelerating Data Analytics in the Post-Moore Era
DTSTART:20240314T121500
DTEND:20240314T133000
DTSTAMP:20260407T114645Z
UID:2da2c5825e176223e207fd9f2874db3da0b41c62bccc5daa34e31e3a
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr. Yannis Chronis\, Systems Researcher at Google\nAbstract:\
 n\nHardware-software codesign is necessary for data analytics performance 
 to keep up with the demand of processing the ever growing size of collecte
 d data. Traditional data processing performance optimization techniques of
 fer diminishing returns as hardware performance scaling is slowing down. T
 owards this goal\, I will first present Castle\, a data analytics system c
 odesigned with an associative processor (AP). Castle shows that we can eff
 ectively use the large data parallelism of emerging APs to accelerate perf
 ormance by an order of magnitude. Then\, I will briefly discuss Dynamic In
 terpolation (DIP)\, a set of new algorithms for searching sorted data\, a 
 core data processing operation. DIP can improve state-of-the-art performa
 nce up to 4.8X by taking into account the diverging memory and processor s
 peeds\, also known as the Memory Wall.\n\nBio:\n\nYannis is currently a Sy
 stems Researcher at Google. He received his Ph.D. degree from the Universi
 ty of Wisconsin-Madison\, under the supervision of Jignesh M. Patel. He is
  broadly interested in hardware-software codesign for data processing and 
 adaptive\, robust and cost efficient query processing. His Ph.D. thesis fo
 cused on accelerating data analytics performance using modern and emerging
  hardware. Yanni's research has been supported by a Facebook Fellowship. 
 He also received a B.S. and M.S. on Computer Science from the University 
 of Athens\, Greece.
LOCATION:BC 410 https://plan.epfl.ch/?room==BC%20410 https://epfl.zoom.us/
 j/67482241595
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR