BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260730T152640Z
LOCATION:Exhibit Hall
DTSTART;TZID=America/Los_Angeles:20260728T174800
DTEND;TZID=America/Los_Angeles:20260728T174800
UID:dac_DAC 2026_sess306_WIP3273@linklings.com
SUMMARY:EdgeQ‑GEMM: INT4/INT8 Mixed‑Precision GEMM Accelerator with On‑the
 ‑Fly Quantization for Accuracy–Energy Tunability in Edge AI Processors
DESCRIPTION:Chaebin Jung, Kyeongwon Lee, Hyunseok Kwak, Jongin Choi, Secha
 n Park, and Sangmin Jeon (Chung-Ang University); Hyeonguk Jang and Jae-Jin
  Lee (ETRI); and Woojoo Lee (Chung-Ang University)\n\nEdge workloads such 
 as keyword spotting and activity recognition must process continuous FP32 
 sensor data under tight power–performance–area budgets, making full-precis
 ion GEMM units impractical. EdgeQ-GEMM is a compact, processor-integrated 
 INT4/INT8 mixed-precision GEMM accelerator that performs on-the-fly quanti
 zation and computation without FP hardware. It supports two modes: adaptiv
 e mode, dynamically quantizing FP32 activations to INT4 or INT8 using a de
 sign-time QCM to expose a tunable accuracy–energy design space, and layer-
 wise mode, executing QAT/PTQ models with layer-mixed INT4/INT8 weights by 
 applying on-the-fly INT32-to-INT8 activation quantization. Implemented in 
 edge AI processors and validated via FPGA and 45nm synthesis, EdgeQ-GEMM e
 nables efficient, flexible precision adaptation for diverse workloads.\n\n
 Track: Student\n\n
END:VEVENT
END:VCALENDAR