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:20260522T150116Z
LOCATION:D167/174
DTSTART;TZID=America/Chicago:20181111T120500
DTEND;TZID=America/Chicago:20181111T122000
UID:submissions.supercomputing.org_SC18_sess170_ws_h2rc105@linklings.com
SUMMARY:The MANGO Process for Designing and Programming Multi-Accelerator 
 Multi-FPGA Systems
DESCRIPTION:Rafael Tornero, Jose Flich, Jose Maria Martinez, and Tomás Pic
 ornell (Technical University of Valencia) and Vincenzo Scotti (University 
 of Naples Federico II)\n\nThis paper describes the approach followed in th
 e European FETHPC MANGO project to design and program systems made of mult
 iple FPGAs interconnected. The MANGO approach relies on the instantiation 
 and management of multiple generic and custom-made accelerators which can 
 be programmed to communicate each other via shared memory and through sync
 hronization registers. The paper introduces the low level architecture inc
 luding the multi-FPGA interconnect deployed, the communication protocol an
 d the architectural template-based approach to simplify the design process
 .\n\nTag: Accelerators, Heterogeneous Systems, NVRAM\n\nRegistration Categ
 ory: Workshop Reg Pass\n\n
END:VEVENT
END:VCALENDAR