BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.riscv-europe.org//eu-summit-2026//talk//9PWJCZ
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-eu-summit-2026-9PWJCZ@cfp.riscv-europe.org
DTSTART;TZID=CET:20260611T134000
DTEND;TZID=CET:20260611T135000
DESCRIPTION:Spiking Neural Networks (SNNs) offer significant energy efficie
 ncy for Edge AI\, yet their event-driven nature leads to unpredictable\, v
 ariable-length output data. In traditional heterogeneous SoCs\, this unpre
 dictability causes high CPU overhead and bus inefficiency. This paper pres
 ents a specialized Event-Adaptive DMA (EA-DMA) integrated into a RISC-V ba
 sed SoC. Unlike standard DMAs\, the proposed engine performs buffer-trigge
 red\, variable-length transfers with maximum-size clamping and hardware ba
 ckpressure for irregular SNN spike traffic. This work provides a scalable 
 solution for integrating neuromorphic accelerators into the RISC-V ecosyst
 em.
DTSTAMP:20260522T163128Z
LOCATION:Poster Island B
SUMMARY:Energy-Efficient RISC-V based neuromorphic SoC for Edge AI Applicat
 ions - wenfei
URL:https://cfp.riscv-europe.org/eu-summit-2026/talk/9PWJCZ/
END:VEVENT
END:VCALENDAR