BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.riscv-europe.org//eu-summit-2026//speaker//3VQGA9
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-WHFNV3@cfp.riscv-europe.org
DTSTART;TZID=CET:20260611T101500
DTEND;TZID=CET:20260611T103000
DESCRIPTION:We present Bianbu LXQt\, a user-oriented desktop environment fo
 r RISC-V platforms built on a deeply adapted LXQt software stack\, optimiz
 ed for real hardware such as SpacemiT’s K1 and K3 SoCs. Unlike straightf
 orward ports that assume x86-like hardware standardization\, this work add
 resses common RISC-V Linux challenges\, including fragmented peripheral su
 pport and the absence of a unified hardware abstraction layer. SpacemiT's 
 CPUs integrate AI-oriented instruction extensions such as IME\, enabling C
 PU-based inference without discrete GPUs or NPUs\, requiring coordinated a
 daptation across the OS and AI frameworks.\nPreserving LXQt’s lightweigh
 t design\, we redesigned the UI and interaction logic to improve responsiv
 eness and visual consistency on resource-constrained RISC-V systems. Devel
 opment was accelerated using AI-assisted tooling\, while continuous feedba
 ck from educators and early adopters guided iterative fixes for lag\, cras
 hes\, and complex configuration—letting users focus on creation\, learni
 ng\, and development rather than system tuning.\nThe full software stack i
 s open source with reproducible builds and modular components. We proved e
 ducational AI examples covering image recognition\, speech processing\, vi
 deo analysis\, and large language model inference\,  all with intuitive GU
 Is. Frameworks including ONNX Runtime\, llama.cpp\, and Ollama run reliabl
 y\, demonstrating the feasibility of RISC-V systems for AI deployment and 
 local AI development.\nThrough practical system integration\, community-dr
 iven iteration\, and accessible AI tooling\, this work shows RISC-V can de
 liver a polished\, daily-driver desktop environment—moving beyond a demo
  into a trusted open platform for developers\, educators\, and innovators.
DTSTAMP:20260522T162735Z
LOCATION:Plenary
SUMMARY:A User-Friendly and AI-Ready Desktop for RISC-V: Bianbu LXQt - Xiao
 gang Fan
URL:https://cfp.riscv-europe.org/eu-summit-2026/talk/WHFNV3/
END:VEVENT
END:VCALENDAR