BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250822T115805Z
LOCATION:Campussaal - Plenary Room
DTSTART;TZID=Europe/Stockholm:20250617T103000
DTEND;TZID=Europe/Stockholm:20250617T110000
UID:submissions.pasc-conference.org_PASC25_sess150_pos122@linklings.com
SUMMARY:P37 - pyGinkgo: Python Bindings for Ginkgo
DESCRIPTION:Keshvi Tuteja and Gregor Olenik (Karlsruhe Institute of Techno
 logy); Roman Mishchuk and Nicolas Venkovic (Technical University of Munich
 ); Markus Götz and Achim Streit (Karlsruhe Institute of Technology); Hartw
 ig Anzt (Technical University of Munich, University of Tennessee); and Cha
 rlotte Debus (Karlsruhe Institute of Technology)\n\nOver the past decade, 
 machine learning has achieved significant advancements, with applications 
 spanning diverse fields such as physics, medicine, economics or energy. A 
 pressing challenge in contemporary machine learning is optimizing models f
 or time and energy efficiency. One effective approach to enhance time effi
 ciency is sparsification. While contemporary machine learning libraries su
 ch as PyTorch, TensorFlow, and SciPy offer decently optimized kernels for 
 dense matrix computations, their performance for sparse matrix operations 
 often falls short. To bridge the performance gap between dense and sparse 
 computations in the Python world, we present pyGinkgo - Python bindings fo
 r the Ginkgo library. pyGinkgo enables Python users to leverage Ginkgo's a
 dvanced capabilities for performing sparse computations within Python, off
 ering significant potential for improving the performance of sparse neural
  networks and beyond. In this poster, we share initial benchmark results, 
 demonstrating pyGinkgo's potential to enhance performance in sparse matrix
  computations and hence, sparse neural networks within Python-based workfl
 ows.\n\nSession Chair: David Moxey (King's College London)\n\n
END:VEVENT
END:VCALENDAR