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:20181221T160727Z
LOCATION:D161
DTSTART;TZID=America/Chicago:20181111T161000
DTEND;TZID=America/Chicago:20181111T170000
UID:submissions.supercomputing.org_SC18_sess156_pec215@linklings.com
SUMMARY:Domain-Specific System on Chips (DSSoC)
DESCRIPTION:Workshop\nArchitectures, Heterogeneous Systems, Quantum Comput
 ing, Workshop Reg Pass\n\nDomain-Specific System on Chips (DSSoC)\n\nRonde
 au\n\nThe invention of the digital computer came about as a proof of compu
 table numbers, and so numerical processing was solved by the Turing Machin
 e that has led to the general purpose computer. These computers are good a
 t solving multiple types of problems with a single machine. However, withi
 n the scope of computable numbers are specific computational problems wher
 e purpose-built machines can solve them faster while using less energy. An
  example of this is the digital signal processor (DSP) that performs the m
 ultiply and accumulate operation important to signal processing, or the mo
 re recent development of the tensor processing unit (TPU) to compute dense
  matrix multiplies that are at the core of deep neural networks. These spe
 cialized machines solve a single problem but with optimized efficiency.\n\
 nAs a result, there exists a tension between the flexibility in general pu
 rpose processors and the efficiency of specialized processors. Domain-Spec
 ific System on Chip (DSSoC) intends to demonstrate that the tradeoff betwe
 en flexibility and efficiency is not fundamental. The program will develop
  a method for determining the right amount and type of specialization whil
 e making a system as programmable and flexible as possible. It will take a
  vertical view of integrating today’s programming environment with a goal 
 of full-stack integration. DSSoC will de-couple the programmer from the un
 derlying hardware with enough abstraction but still be able to utilize the
  hardware optimally through intelligent scheduling. DSSoC specifically tar
 gets embedded systems where the domain of applications sits at the edge an
 d near the sensor. Workloads consist of small chunks of data but often wit
 h a large number of algorithms required in the processing, meaning that hi
 gh compute power and low latency at low power are required.\n\nThis presen
 tation will explore the concepts being developed in the DSSoC program, inc
 luding an overview of the projects being funded to study the research ques
 tions and produce technology that furthers industry’s ability to effective
 ly use specialization within our SoCs.
URL:https://sc18.supercomputing.org/presentation/?id=pec215&sess=sess156
END:VEVENT
END:VCALENDAR