BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260708T110553Z
UID:d9e2820b-366d-4f87-b1b4-9715c67f0d48
DTSTART:20190401T070000Z
DTEND:20190403T160000Z
DESCRIPTION:This course gives an overview of the most relevant GPGPU comput
 ing techniques to accelerate computationally demanding tasks on HPC hetero
 geneous architectures based on GPUs.\n\nThe course will start with an arch
 itectural overview of modern GPU based heterogeneous architectures\, focus
 ing on its computing power versus data movement needs. The course will cov
 er both a high level (pragma-based) programming approach with OpenACC for 
 a fast porting startup\, and lower level approaches based on nVIDIA CUDA a
 nd OpenCL programming languages for finer grained computational intensive 
 tasks. A particular attention will be given on performance tuning and tech
 niques to overcome common data movement bottlenecks and patterns.\n\nTopic
 s:\n\nOverview of architectural trends of GPUs in HPC. GPGPU parallel prog
 ramming in heterogeneous architectures. Basis of OpenACC\, CUDA and OpenCL
  programming.\n\nSkills:\nBy the end of the course\, students will be able
  to:\n\n\n	understand the strengths and weaknesses of GPUs as accelerators
 \n	program GPU accelerated applications using both higher and lower level 
 programming approaches\n	overcome problems and bottlenecks regarding data 
 movement between host and device memories\n	make best use of independent e
 xecution queues for concurrent computing/data-movement operations\n\n\nTar
 get Audience: \nResearchers and programmers interested in porting scientif
 ic applications or use efficient post-process and data-analysis techniques
  in modern heterogeneous HPC architectures.\n\nPrerequisites: \n\nA basic 
 knowledge of C or Fortran is mandatory. Programming and Linux or Unix. A b
 asic knowledge of any parallel programming technique/paradigm is recommend
 ed.\n\nGrant:\nThe lunch for the three days will be offered to all the par
 ticipants and some grants are available. The only requirement to be eligib
 le is to be not funded by your institution to attend the course and to wor
 k or live in an institute outside the Roma area. The grant  will be 300 e
 uros for students working and living outside Italy and 150 euros for stude
 nts working and living in Italy (outside Roma). Some documentation will be
  required and the grant will be paid only after a certified presence of mi
 nimum 80% of the lectures.\n\nFurther information about how to request the
  grant\, will be provided at the confirmation of the course: about 3 weeks
  before the starting date.\n\nCoordinating Teacher: Dr. L.Ferraro\n\n \nh
 ttps://events.prace-ri.eu/event/830/
SUMMARY:Programming paradigms for GPU devices@Cineca
URL;VALUE=URI:https://events.prace-ri.eu/event/830/
END:VEVENT
END:VCALENDAR