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:20230712T175213Z
LOCATION:3012\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20230712T105500
DTEND;TZID=America/Los_Angeles:20230712T111000
UID:dac_DAC 2023_sess121_RESEARCH943@linklings.com
SUMMARY:Occamy: Memory-efficient GPU Compiler for DNN Inference
DESCRIPTION:Research Manuscript\n\nJaeho Lee, Shinnung Jeong, Seungbin Son
 g, Kunwoo Kim, Heelim Choi, Youngsok Kim, and Hanjun Kim (Yonsei Universit
 y)\n\nThis work proposes Occamy, a new memory-efficient DNN compiler that 
 reduces the memory usage of a DNN model without affecting its accuracy. Fo
 r each DNN operation, Occamy analyzes dimensions of\ninput and output tens
 ors, and their liveness within the operation. Across all the operations, O
 ccamy analyzes liveness of all the tensors, generates a memory pool after 
 calculating the maximum required memory size, and schedules when and where
  to place each tensor in the memory pool. Compared to PyTorch, on an integ
 rated embedded GPU for six DNNs, Occamy reduces the memory usage by 33.75%
  while achieving the 1.365 times geomean speedup.\n\nTopic: Design\n\nKeyw
 ord: AI/ML System and Platform Design\n\nSession Chairs: Jinho Lee (Seoul 
 National University) and Lingchuan Meng (Amazon)
END:VEVENT
END:VCALENDAR