BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Python GPU computing (Cunumeric\, cuPy\, JAX\, Pytorch)
DTSTART:20260507T080000Z
DTEND:20260507T100000Z
DTSTAMP:20260501T121800Z
UID:indico-event-448@events.hpc-portal.eu
DESCRIPTION:How to use GPU to speed up computing with Python ? In this web
 inar we will study possibles senarios to guide you to the library which fi
 t your needs. We will see basic principle of each of them\, and the Gray S
 cott summer school will give a deeper vision of their use. We will present
  them by level of integration :\n\nfor high level : Nvidia CuNumeric\, Int
 el DPNP\, JAX\, and PyTorch allow to keep practically the same code as the
  CPU version\nfor intermediate level : CuPy library provides access to adv
 anced digital functionnalities\, but needs specific code for the GPU\nfor 
 low level : PyCUDA and Numba for GPU provide basic functionnalities on tab
 les.\n\nWe will also present associated profiling tools.\n \nWhat are Gra
 y Scott Thursdays?\nGray Scott Thursdays are a unique series of 18 live we
 binars\, held every Thursday leading up to the Gray Scott School 2026. Eac
 h session is presented by our expert professors and provides an early dive
  into the key topics of High-Performance Computing\, including:\nCPU/GPU a
 rchitectures\, memory management\, profiling\, testing\, and modern progra
 mming languages such as C++\, Fortran\, Julia and Python… and much more!
 \nThese webinars are a perfect opportunity to get a head start\, learn dir
 ectly from the instructors\, and familiarize yourself with the tools\, lib
 raries\, and methods that will be used during the intensive on-site traini
 ng.\n\nhttps://events.hpc-portal.eu/event/448/
URL:https://events.hpc-portal.eu/event/448/
END:VEVENT
END:VCALENDAR