BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Accelerating Massive Data Processing in Python with Heat
DTSTART:20261109T090000Z
DTEND:20261109T140000Z
DTSTAMP:20261030T093500Z
UID:indico-event-541@events.hpc-portal.eu
CONTACT:c.comito@fz-juelich.de
DESCRIPTION:You can participate in this course either online or on-site at
  JSC. The course will be held in English.\nCourse Content:\nThis hands-on 
 tutorial introduces the Heat library\, which is designed to scale Python
 -based array computing and data science workflows to distributed and GPU-a
 ccelerated environments. Heat offers a familiar NumPy-like API while distr
 ibuting memory-intensive operations using PyTorch and mpi4py.\nTopics cove
 red include:\n\nHeat Fundamentals: Get started with distributed arrays (D
 NDarrays)\, distributed I/O\, data decomposition schemes\, and array opera
 tions.\nKey Functionalities: Explore the multi-node linear algebra\, stat
 istics\, signal processing\, and machine learning capabilities.\nDIY Devel
 opment: Learn how to use Heat's infrastructure to build your own multi-no
 de\, multi-GPU capable research applications.\n\nPrerequisites:\nParticipa
 nts should have a laptop and experience with Python and its scientific eco
 system (e.g. NumPy\, SciPy). A basic understanding of MPI is helpful but n
 ot required.\nA personal institutional email address (university/research 
 institution\, government agency\, organisation\, or company) is required t
 o register for JSC training courses. If you don't have an institutional em
 ail address\, please get in touch with the contact person for this course.
 \nTarget Audience:\nResearchers and Research Software Engineers (RSEs) wor
 king with large datasets that exceed the memory of a single machine.\nHPC 
 practitioners that support these scientists or that may be interested in s
 upporting them in the future are also welcome.\nLanguage:\nThe course will
  be held in English.\nDuration:\n1 half day\nDates:\n9 November 2026\, 10:
 00-15:00 each day\nVenue:\nHybrid: You can participate either online or on
 -site at the Jülich Supercomputing Centre\, Building 16.3\, Room 211 (Tra
 ining Room 2).\nNumber of Participants:\nMaximum 20\nInstructors:\nKai Kra
 jsek\, Thomas Saupe\, Claudia Comito (JSC)Juan Pedro Muriedas (KIT)\n\nhtt
 ps://events.hpc-portal.eu/event/541/
LOCATION:Online und am Jülich Supercomputing Centre (JSC)
URL:https://events.hpc-portal.eu/event/541/
END:VEVENT
END:VCALENDAR