BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.riscv-europe.org//eu-summit-2026//talk//MYRD9A
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-MYRD9A@cfp.riscv-europe.org
DTSTART;TZID=CET:20260611T133000
DTEND;TZID=CET:20260611T134000
DESCRIPTION:This work enables optimized\, end-to-end inference of the objec
 t detection models on RISC-V vector CPU. It includes the implementation of
  optimized pre- and post-processing pipelines as well as the enablement of
  efficient execution of the models at FP32\, FP16\, and INT8 precisions. I
 REE\, an MLIR-based compiler\, is used to compile and optimize the model. 
 Model inference on the Banana Pi BPI-F3 is profiled to identify top hotspo
 t ops and their compilation is optimized in the IREE compilation pipeline 
 either by improving vectorization or by implementing ukernels. For accurac
 y validation\, the mean Average Precision (mAP) is computed using the COCO
  validation dataset. This project is supported by the RISC-V Software Ecos
 ystem (RISE)\, and all the developed artifacts are open-source.
DTSTAMP:20260522T163251Z
LOCATION:Poster Island C
SUMMARY:Optimizing IREE Compilation and End-to-End Object Detection Pipelin
 e for RISC-V - Adeel Ahmad
URL:https://cfp.riscv-europe.org/eu-summit-2026/talk/MYRD9A/
END:VEVENT
END:VCALENDAR