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:20240626T180033Z
LOCATION:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20240626T180000
DTEND;TZID=America/Los_Angeles:20240626T190000
UID:dac_DAC 2024_sess237_RESEARCH1188@linklings.com
SUMMARY:Accelerating DNN Execution via Weight and Data Adaptive N:M Prunin
 g
DESCRIPTION:Work-in-Progress Poster\n\nSai Qian Zhang (New York University
 ) and Thierry Tambe, Gu-Yeon Wei, and David Brooks (Harvard University)\n\
 nBalancing accuracy and hardware efficiency remains a challenge with tradi
 tional pruning methods. N:M sparsity is a recent approach offering a compr
 omise, allowing up to N non-zero weights in a group of M consecutive weigh
 ts.\nHowever, N:M pruning enforces a uniform sparsity level of $\frac{N}{M
 }$ across all layers, which does not align well sparse nature of deep neur
 al networks (DNNs). To achieve a more flexible sparsity pattern and a high
 er overall sparsity level, we present~\textit{JointNF}, a novel joint N:M 
 and structured pruning algorithm to enable fine-grained structured pruning
  with adaptive sparsity levels across the DNN layers. Moreover, we show fo
 r the first time that N:M pruning can also be applied over the input activ
 ation for further performance enhancement.\n\nTopic: AI, Autonomous System
 s, Cloud, Design, EDA, Embedded Systems, IP, Security
END:VEVENT
END:VCALENDAR