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:20260402T024533Z
LOCATION:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20250623T180000
DTEND;TZID=America/Los_Angeles:20250623T190000
UID:dac_DAC 2025_sess262_RESEARCH2043@linklings.com
SUMMARY:FARM: Fast Acceleration of Random forests via in-Memory processing
DESCRIPTION:Aymen Ahmed and Valeria Bertacco (University of Michigan)\n\nA
 rtificial Intelligence (AI) has become omnipresent, influencing a multitud
 e of applications in our daily lives and expanding into a wide range of se
 nsitive applications like medical diagnosis, autonomous driving, and more.
   Many systems using Machine Learning (ML) models, e.g., neural networks, 
 function as black boxes and lack interpretability. In contrast, users are 
 increasingly seeking greater transparency in how AI-driven decisions are m
 ade.  Random Forests (RF) have arisen as a key model offering this "interp
 retability", but their limited performance is far from the needs of time-c
 ritical applications.\n\nIn this work, we design a specialized hardware so
 lution to accelerate inference tasks on RFs. We first identify data retrie
 val inefficiencies by analyzing several RF inference algorithms, then desi
 gn a processing-in-memory (PIM) architecture called FARM. FARM performs ke
 y inference tasks within the hardware's HBM memory banks, and coalesces bu
 rst memory activity to reduce unnecessary data movements. Our evaluation s
 hows that FARM delivers an average of 8.8x performance improvement, and an
  87% reduction in energy, without any loss in predictive accuracy, when co
 mpared to a state-of-the-art GPU coupled with HBM memory.\n\nTracks: DES5:
  Emerging Device and Interconnect Technologies\n\n
END:VEVENT
END:VCALENDAR