BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250626T234540Z
LOCATION:B304
DTSTART;TZID=America/New_York:20241118T154700
DTEND;TZID=America/New_York:20241118T160400
UID:submissions.supercomputing.org_SC24_sess761_ws_hppss104@linklings.com
SUMMARY:Work-in-progress: CUDA Python object models and parallelism models
DESCRIPTION:Andy Terrel (NVIDIA Corporation)\n\nToday Python developers ty
 pically access GPUs from either deep learning frameworks or tools that hav
 en't kept up with modern CUDA practices. In this work in progress update, 
 the CUDA Python team will demonstrate new interfaces using the CUDA Core C
 ompute Libraries and an updated Pythonic object model. Additionally, these
  tools are able to link to device side code with Numba and link time optim
 ization (LTO). These tools are additionally working with the new nvmath-py
 thon library that takes away much of the difficulties in picking the corre
 ctly optimized CUDA library from the Python runtime. The team is eager to 
 get early feedback and help incorporate ideas into these tools as they lau
 nch in the next year.\n\nTag: Applications and Application Frameworks, Art
 ificial Intelligence/Machine Learning, Parallel Programming Methods, Model
 s, Languages and Environments\n\nRegistration Category: Workshop Reg Pass\
 n\nSession Chairs: Sunita Chandrasekaran (University of Delaware), Sam For
 eman (Argonne National Laboratory (ANL)), Daniel Margala (Lawrence Berkele
 y National Laboratory (LBNL)), and Pete Mendygral (Cray Inc.)\n\n
END:VEVENT
END:VCALENDAR