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:20260730T152637Z
LOCATION:
DTSTART;TZID=America/Los_Angeles:20260728T124300
DTEND;TZID=America/Los_Angeles:20260728T124300
UID:dac_DAC 2026_sess315_RESEARCH962@linklings.com
SUMMARY:EnergyHDC: Intermittent Hyperdimensional Inference on Energy-Harve
 sting IoT
DESCRIPTION:YUSHENG LIU (National Yang Ming Chiao Tung University (NYCU)) 
 and Yong-Cheng Liaw and Shuo-Han Chen (National Yang Ming Chiao Tung Unive
 rsity)\n\nAmbient energy harvesting technologies offer the promise of perp
 etual operation for batteryless Internet of Things (IoT) devices; however,
  their execution is frequently halted by unpredictable power failures. Tra
 ditional methods to ensure correctness, such as software checkpointing (e.
 g., Mementos) and newer systems for deep neural networks (e.g., DynBal), a
 re burdened by substantial energy and latency overheads for progress prese
 rvation, limiting their use on ultra-low-power platforms. This paper intro
 duces EnergyHDC, an energy-aware inference system designed for intermitten
 t operation by integrating Hyperdimensional Computing (HDC). The system pa
 irs HDC's algorithmic robustness with fine-grained energy adaptation using
  three key contributions: (1) an energy-proportional checkpointing that op
 timizes preservation granularity against available energy; (2) a dimension
 -first reordering that slashes per-checkpoint storage; and (3) a priority-
 based pruning that allows for compile-time energy-accuracy trade-offs. Eva
 luated on an MSP432P401R microcontroller platform under intermittent power
 , EnergyHDC demonstrates up to 214x speedup compared to Mementos. It also 
 achieves 19.6x faster inference than DynBal under similar accuracy and rea
 listic energy-harvesting conditions. These results validate that a co-desi
 gn approach, coupling energy-aware execution with HDC's intrinsic robustne
 ss, can reframe intermittence from a system constraint into an opportunity
  for efficient edge intelligence.\n\nTopics: Quantum\n\nTrack: DES6. Quant
 um Computing, Systems\n\nSession Chairs: Hokeun Kim (Arizona State Univers
 ity); BaekGyu Kim (Daegu Gyeongbuk Institute of Science and Technology); X
 iang Chen (Peking University); Sangyeob Kim (Yonsei University); Robert M.
  Radway (University of Pennsylvania); Prashanth Mohan (University of Pitts
 burgh); Xiaoxuan Yang (University of Virginia, Stanford University); Ramti
 n Zand (University of South Carolina); Hadi Kamali (University of Central 
 Florida); Jiafeng Xie (Villanova University); Prabuddha Chakraborty (Unive
 rsity of Maine); Junichiro Kadomoto (University of Tokyo); and Yosuke Ueno
  (RIKEN)\n\n
END:VEVENT
END:VCALENDAR