BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260707T112352Z
UID:16269e0d-c426-4252-a580-2816e06e07f3
DTSTART:20220329T080000Z
DTEND:20220329T133000Z
DESCRIPTION:####About the course\n\nThe [Scientific Computing group at the 
 IT department (UiB)](https://wiki.uib.no/hpcdoc/index.php/Main_Page) in co
 llaboration with [NRIS (Norwegian Research Infrastructure Services)](https
 ://www.sigma2.no/nris) is offering a one day hands-on physical course for 
 Introductory GPU Programming with OpenACC.\n\nThe course is designed for b
 eginners in GPU-programming and who want to get familiar with available di
 rectives programming models with a special focus on the OpenACC offloading
 . The course does not require any basic knowledge in GPU-programming\, but
  it is a requirement that the user has some basic programming experience w
 ith either Fortran or C. The course aims at providing an overview of the O
 penACC model and guiding users towards its optimal use. The course will fa
 miliarise the users with the most needed constructs\, clauses and runtime 
 library routines via some practical numerical applications. The applicatio
 ns include solving partial differential equations\, matrix multiplication\
 , integration etc.\nPrerequisites\n\n####The participants are expected to 
 have\n\n* Basic programming experience with either Fortran or C\n* Basic L
 inux terminal experience\n\nThe course does not require any basic knowledg
 e in GPU-programming\nExpected Outcome of the course\n\n####By the end of 
 this training course\, the participants should be able to:\n\n* Recognise 
 the necessity of GPU-programming.\n* Define different available programmin
 g models.\n* Get an overview of the GPU-architectures and compilers suppor
 ting OpenACC.\n* Determine the role of different constructs\, clauses\, an
 d runtime library routines.\n* Compile and interpret the compiler flags an
 d feedback messages.\n* Use appropriate constructs and clauses to offload 
 compute regions to the GPU device.\n* Select and map regions of a code wit
 h the use of data locality concepts.\n* Implement OpenACC on simple numeri
 cal models.\n* Do code-profiling using NVIDIA Nsight Systems.\n\n####Regis
 tration\n\nPlease register [here](https://skjemaker.app.uib.no/view.php?id
 =12165532) We have limited capacity of 30 participants. Registration close
 s on *24th March*. The course is free of charge and is organised by the Sc
 ientific Computing group at UiB IT department in collaboration with NRIS (
 Norwegian Research Infrastructure Services). We do not provide travel cost
 s. 
LOCATION:Spaces - Bergen\, Media City Bergen Seminar 2 (57702.110) 
SUMMARY:Introduction to GPU Programming with OpenACC
URL;VALUE=URI:https://wiki.uib.no/hpcdoc/index.php/Introduction_to_GPU_Prog
 ramming_with_OpenACC
END:VEVENT
END:VCALENDAR