BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//programme.europython.eu//europython-2026//talk//JSLSHM
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-europython-2026-JSLSHM@programme.europython.eu
DTSTART;TZID=CET:20260716T120500
DTEND;TZID=CET:20260716T123500
DESCRIPTION:GPU programming can be scary\, but doesn't need to be! Did you 
 know you can access the full performance of CUDA purely in Python? With th
 e full CUDA Python stack\, you have a friendly interface to get you starte
 d with GPU acceleration.\n\nIn this example-driven talk\, we'll begin with
  a general discussion of the CUDA model and how to manage accelerator devi
 ces in Python with cuda.core. Next\, we'll teach you how to create arrays 
 and launch work with CuPy. Then\, you'll learn how to customize parallel a
 lgorithms with cuda.compute and write your own kernels that leverage coope
 rative algorithms with cuda.coop\, and integrate seamlessly with accelerat
 ed libraries such as cuBLAS and cuDNN.\n\nWe'll look at a variety of paral
 lel examples\, from counting words\, to implementing softmax and row-wise 
 reductions.\n\nBy the time the talk is over\, you'll be ready to start acc
 elerating your Python code with GPUs!
DTSTAMP:20260524T130633Z
LOCATION:Chamber Hall A (S3A)
SUMMARY:GPU Programming in Pure Python - Bryce Adelstein Lelbach
URL:https://programme.europython.eu/europython-2026/talk/JSLSHM/
END:VEVENT
END:VCALENDAR