BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:UW-Madison-Physics-Events
BEGIN:VEVENT
SEQUENCE:0
UID:UW-Physics-Event-4118
DTSTART:20160412T170500Z
DTEND:20160412T180000Z
DTSTAMP:20260419T094645Z
LAST-MODIFIED:20161104T130855Z
LOCATION:4274 Chamberlin Hall (refreshments will be served)
SUMMARY:Data centric computing in emerging nonvolatile memory technolo
 gies\, Chaos & Complex Systems Seminar\, Jing Li\, Department of Compu
 ter Sciences
DESCRIPTION:The confluence of disruptive technologies beyond CMOS and 
 "Big Data" workloads calls for a fundamental paradigm shift from homog
 enous compute-centric system to heterogeneous data-centric system for 
 better innovation\, competition and productivity. With the objective o
 f rethinking data-centric system from ground up\, through a concrete e
 xample\, I will show how to leverage emerging memory technology such a
 s phase-change memory (PCM) to realize a new IC building block for fut
 ure data-centric system. A novel chip was designed and fabricated for 
 the first time\, blurring the boundary between computation and storage
 \, i.e.\, it can either be configured as a compute unit - a high perfo
 rmance search engine or as a storage media - storage class memory. It 
 achieves >10x area reduction compared to homogenous CMOS-based design 
 at the same technology node and reliably operates at ultra-low voltage
  down to 750mV. In the talk I will briefly highlight a few critical en
 abling techniques from material\, circuit\, architecture and algorithm
  perspectives. I will also highlight the major research activities in 
 my lab in developing collaborative software/hardware solutions to addr
 ess classical von Neumann bottlenecks.
URL:https://www.physics.wisc.edu/events/?id=4118
END:VEVENT
END:VCALENDAR