BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.riscv-europe.org//eu-summit-2026//talk//8BXPC9
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-2026-8BXPC9@cfp.riscv-europe.org
DTSTART;TZID=CET:20260609T140000
DTEND;TZID=CET:20260609T141000
DESCRIPTION:We have previously demonstrated that it is practical to bring u
 p ExecuTorch on a low power bare metal microcontroller.  ExecuTorch is a p
 roject derived from the PyTorch AI framework for inference on embedded dev
 ices using traditional eager (“interpreted”) evaluation of AI models. 
  In this paper\, we provide a short overview of how to run ExecuTorch on a
  bare metal microcontroller.  We then illustrate the features of 32-bit RI
 SC-V [4] which make it attractive for use in edge AI applications\, using 
 the Open Hardware Foundation’s CORE-V CV32E40Pv2 microcontroller as depl
 oyed in a real world design by two of the co-authors and their colleagues 
 at <redacted>.  We have now ported IREE for the same platform.  IREE is a 
 Linux Foundation experimental project\, which uses lazy (“compiled”) e
 valuation of AI models\, with LLVM MLIR as an intermediate representation.
   We give a short overview of how to run IREE on a bare metal microcontrol
 ler\, and then assess what aspects of 32-bit RISC-V make it attractive for
  IREE.  We conclude by comparing the feasibility of using IREE instead of 
 ExecuTorch and an assessment on the performance of both when carrying out 
 AI inference.
DTSTAMP:20260522T163159Z
LOCATION:Poster Island C
SUMMARY:AI inference on bare-metal RISC-V Microcontrollers: A comparison of
  ExecuTorch and IREE/MLIR - Jeremy Bennett
URL:https://cfp.riscv-europe.org/eu-summit-2026/talk/8BXPC9/
END:VEVENT
END:VCALENDAR