2021

Parallel programming on GPU with CUDA

by Olivier Mattelaer (UCLouvain/CISM)

Europe/Brussels
VINCI: salle DAO (comodal (louvain-la-neuve or remote))

VINCI: salle DAO

comodal (louvain-la-neuve or remote)

Join Zoom Meeting https://cern.zoom.us/j/68165517034?pwd=bllaeUZlNFlZZmh5RVYrVytudnJTQT09 Meeting ID: 681 6551 7034 Passcode: 257128 Join by SIP 68165517034@188.185.118.153 68165517034@188.184.110.70 Join by H.323 188.185.118.153 188.184.110.70 Meeting ID: 681 6551 7034 Passcode: 257128
Description

Cuda is the most common way to code GPU application from scratch develloped by NVidia, it allows to push NVidia GPU to the maximum of their possibilities

Contents:

  • Basic of GPU hardware
  • Basic of programming with CUDA
  • using nsight to profile your code

 

Prerequisite:

  • Being able to use SSH with private keys 
  • Being familiar with a text editor 
  • Mastering the Linux command line and the GNU utilities (mkdir, cp, scp, etc.)
  • Basic knowledge of C

Type: Hands-on
Target audience: Rookie programmer
Must: This session is a nice-to-have for those who need to develop highly parallel scientific software.

Organized by

UCLouvain/CISM

Registration
Participants
11 / 60
Surveys
Quality Survey