BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20181221T160742Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181113T171500
DTEND;TZID=America/Chicago:20181113T190000
UID:submissions.supercomputing.org_SC18_sess343_drs105@linklings.com
SUMMARY:In-Memory Accelerator Architectures for Machine Learning and Bioin
formatics
DESCRIPTION:Doctoral Showcase\nWorkshop Reg Pass, Tutorial Reg Pass, Tech
Program Reg Pass, Exhibits Reg Pass, Exhibits - Exhibit Hall Only Reg Pass
\n\nIn-Memory Accelerator Architectures for Machine Learning and Bioinform
atics\n\nKaplan, Ginosar\n\nMost contemporary accelerators are von Neumann
machines. With the increasing sizes of gathered and then processed data,&
nbsp; memory bandwidth is the main limiting of performance. One approach t
o mitigate the bandwidth constraint is to bring the processing units close
r to the data. This approach is known as near-data processing (ND
P). However, NDP architecture (e.g., Hybrid Memory Cube) are still inheren
tly limited because they are based on replicating the von Neumann architec
ture in memory.
My research proposes two new processing-in-stor
age architectures, where each bitcell can both store information and perfo
rm computation. The main building block of the architectures are memristor
s, an emerging memory technolgy.
The first architecture I propose, P
RinS, was applied to accelerate machine learning and large-scale DNA seque
nce alignment. Using Associative Processing, PRinS achieves massive p
arallelism. The second, RASSA, accelerates DNA long read mapping, with app
roximate Hamming distance computation and quantifying mismatch of a p
attern to voltage level.
URL:https://sc18.supercomputing.org/presentation/?id=drs105&sess=sess343
END:VEVENT
END:VCALENDAR