BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260705T122140Z
UID:336dd2aa-7ff8-4f0f-b888-678dd1191ece
DTSTART:20201210T070500Z
DTEND:20201211T160000Z
DESCRIPTION:This course will be delivered as an ONLINE COURSE (using Zoom) 
 for remote participation.\n\nREGISTRATION is strictly NECESSARY since the 
 details to access the online course will be provided to the registered and
  accepted attendees only. Registration follows the "first come – first s
 erved" principle. For the online course we can take a maximum of 40 person
 s. Additional registrations will be added to a waiting list.\n\nFurthermor
 e\, accepted participants will be contacted a few days before the course a
 nd asked to do a short PRE-ASSIGNMENT that has to be completed before the 
 course starts.\n\nThe HANDS-ON LABS will be done on VSC-3\, all participan
 ts will get a training user account at the VSC for the duration of the cou
 rse.\n\nOverview\n\nCUDA is the standard API for code development targetin
 g the GPU and a number of impressive examples have already been given in d
 iverse areas from particle physics to computational biology. CUDA allows s
 imple extensions of standard C/C++/Fortran code with GPU-specific function
 s. In this way thousands of cores available on the GPU can be leveraged to
  work in parallel and thus carry out significant fractions of the computat
 ional workload on the device rather than the CPU. There is also a vast set
  of auxiliary tools available to the developer including libraries\, code 
 templates\, building blocks\, analysis tools\, developmental frameworks an
 d in general a vivid community making up the CUDA Developer Zone. It is of
 ten for this multifaceted support environment that the interested beginner
  is feeling overwhelmed and unsettled about which particular first steps s
 hould best be taken to gain a straightforward introduction into the subjec
 t. For exactly this reason the present course is offering a systematic ste
 p-by-step introduction into GPU computing from the perspective of the newc
 omer. Basic design principles will be established\, central programming te
 chniques acquired and a number of state-of-the-art workflows examined that
  efficiently employ the GPU and are frequently used in scientific computin
 g.\n\nThis course provides lectures\, demos\, and hands-on labs.\n\nThis c
 ourse is a PRACE training event. It is organized by the VSC Research Cente
 r\, TU Wien.\n\nAgenda &amp\; Content (tentative)\n\n1st day – 10 Decemb
 er 2020\n\n\n	Basic design principles\, getting started with simple CUDA r
 outines\, mastering the CUDA environment\;\n	Memory Hierarchy with a focus
  on CUDA managed unified memory\;\n	Practical exercise: all the pitfalls o
 ne can run into when porting a dummy code to CUDA.\n\n\n08:45 - 09:00   
  join online\n09:00 - 13:00    lectures and hands-on labs (with breaks: 
 10:45-11:00)\n13:00 - 14:00    lunch break\n14:00 - 17:00    lectures 
 and hands-on labs (with breaks: 15:20-15:35)\n\n2nd day – 11 December 20
 20\n\n\n	Selected examples to demonstrate CUDA capabilities and GPU operat
 ion\, e.g.\, bandwidthTest\, simpleAssert\, simpleStreams\, etc.\;\n	CUDA 
 libraries\, CUBLAS\, CUSolver\, considering numerical precision\, gaining 
 insight into the runtime\;\n	Practical exercise: CUDA in everyday life (of
  a scientist).\n\n\n08:45 - 09:00    join online\n09:00 - 13:00    lec
 tures and hands-on labs (with breaks: 10:45-11:00)\n13:00 - 14:00    lun
 ch break\n14:00 - 17:00    lectures and hands-on labs (with breaks: 15:2
 0-15:35)\nhttps://events.prace-ri.eu/event/1078/
SUMMARY:[ONLINE] CUDA 4 Dummies @ VSC Vienna
URL;VALUE=URI:https://events.prace-ri.eu/event/1078/
END:VEVENT
END:VCALENDAR