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:20260728T171200
DTEND;TZID=America/Los_Angeles:20260728T171200
UID:dac_DAC 2026_sess306_WIP1660@linklings.com
SUMMARY:Accelerated Dynamic Voltage Drop Prediction Using a Lightweight Ma
 chine Learning Model
DESCRIPTION:Itay Yonatanov, Ido Parchomovsky, Mohamad Omari, and Freddy Ga
 bbay (The Hebrew University)\n\nAccurate dynamic voltage drop (DVD) analys
 is is increasingly critical in advanced nodes, where higher densities, low
 er voltages, and complex packaging exacerbate power delivery challenges. T
 raditional simulations are computationally expensive and typically perform
 ed late in the design cycle, risking costly redesigns. We propose a lightw
 eight ML-based DVD prediction model using multi-scale CNNs, fusion layers,
  and skip connections to capture spatial and hierarchical power grid featu
 res. The model uniquely incorporates package and grid inductance and suppo
 rts both vectorless and vector-based inputs. Evaluated on a 16 nm RISC-V c
 ore, it achieves 80-86 % accuracy with 5 mV tolerance and over 25,000× fas
 ter runtime than commercial tools.\n\nTrack: Student\n\n
END:VEVENT
END:VCALENDAR