Agenda (all days):

     09:00 - 13:00   lectures and hands-on labs (with breaks: 11:00-11:15)
     13:00 - 14:00   lunch break
     14:00 - 17:00   lectures and hands-on labs (with breaks: 15:15-15:30)

Lunch is not included (self pay) – nearest restaurant is the Mensa (1st floor, yellow area) Mensa-Menu

First day:

  • Basic design principles, getting started with simple CUDA routines, mastering the CUDA environment;
  • Memory Hierarchy with a focus on CUDA managed unified memory;
  • Practical exercise: all the pitfalls one can run into when porting a dummy code to CUDA.

Opens external link in new windowSlides part 1

Opens external link in new windowSlides part 2

Opens external link in new windowTutorial 1

Second day:

  • Selected examples to demonstrate CUDA capabilities and GPU operation, e.g., bandwidthTest, simpleAssert, simpleStreams, etc.;
  • CUDA libraries, CUBLAS, CUSolver, considering numerical precision, gaining insight into the runtime;
  • Practical exercise: CUDA in everyday life (of a scientist).

Opens external link in new windowSlides part 3

Opens external link in new windowSlides part 4

Opens external link in new windowTutorial 2

 

Hands-on:

Please open a terminal (xterm) and connect to vsc3:

ssh -X training@vsc3.vsc.ac.at

mkdir PC###     [ at first login, create your own directory (shared account) - PC### = number of your PC ]

salloc -J PC### -N 1 -p gpu_gtx1080single --qos gpu_gtx1080single     [ allocate a gpu node ]

srun hostname                                                                                          [ get the name of your node ]

ssh -X <hostname>                                                                                  [ connect to your node ]

cd PC###                                                                                                  [ always work in your own directory ]

module load cuda/9.1.85                                                                          [ load a cuda module ]

cp ~training/tmp.tar.gz ./                                                                           [ copy the exercises ]

tar -xvzf tmp.tar.gz                                                                                    [ unpack the exercises ]