2nd GPU Hackathon at CESGA
Take advantage of Parallware Trainer to learn parallel programming using OpenMP and OpenACC technologies.
OVERVIEW NEWSROOM FAQ AGENDA COMMITTEE TERMS & CONDITIONS
OVERVIEW
⚐ March 5 – 9, 2018.
☞ Registration deadline: February 11, 2018
◎ International scope
♔ Prize: NVIDIA GeForce GTX 1080Ti (Sponsored by NVIDIA)
ⅈ More information: training@appentra.com
⚲ CESGA, Santiago de Compostela, Spain
NEWSROOM
VIDEOS
SOCIAL MEDIA
BLOG
CESGAHACK18 Experience, the 2nd GPU Hackathon
Announcing the CESGAHACK 18 Participants
From CesgaHack17 to SC17: A Success Story With Parallware Trainer
FAQ
1. HACKATHON GOAL
The goal of this hackathon is to accelerate the execution of simulation applications coded by developers with no experience in parallel programming. Our goal is to help you in doing more science and less coding using OpenMP and OpenACC technologies. Your outcome of the hackathon will be either an OpenMP/OpenACC-enabled application or a clear roadmap of how to get there.
2. DO I NEED PREVIOUS EXPERIENCE IN GPU PROGRAMMING?
No, you do not need any experience in parallel programming and GPUs. Our goal is to get the most out this hackathon by working on your code 95% of the time, and sharing experience with expert mentors in optimization, parallelization and execution of simulation programs. We will use Parallware Trainer to help you identify the parallel patterns of your code, and to learn how to implement those patterns efficiently with OpenMP/OpenACC.
3. WHAT TEAMS ARE WE LOOKING FOR?
The ideal team has 2 developers, one expert in the simulation code and one newbie in simulation and parallel programming. The ideal simulation application is a sequential code or a MPI code written in C/C++ or Fortran.
4. HOW HIGH IS THE FEE?
Participation in the training event is free of charge. The meeting room and lunches, as well as access to the supercomputers throughout the event, are offered by participating sites.
5. WILL THERE BE PRIZES?
The jury will evaluate the participants and the winners will take a NVIDIAGeForce GTX 1080Ti ! (sponsored by NVIDIA).
6. HOW IS THE SELECTION PROCESS?
We will contact the contact person of each submission to have a better understanding of the team goals, strengths and weaknesses. Selected teams will receive suggestions of how to better prepare the hackathon (e.g, create a miniapp, learn the basics of OpenMP/OpenACC). Non-selected teams will receive feedback to improve the proposal for future GPU Hackathons.
7. WHAT HAPPENS AFTER THE HACKATHON?
We seek to establish a collaborative relationship with your team to create success stories that can be published during the months following the hackathon. We will advertise them in specialized media and channels. We want to increase the impact of our work!
8. WHO CAN I CONTACT FOR MORE INFORMATION OR QUESTIONS?
Please contact training@appentra.com for questions.
9. WHERE IS THE VENUE OF THESE HACKATHONS?
At the Supercomputing Center of Galicia in Santiago de Compostela (Spain)
AGENDA
Monday, March 5
09:00 – 09:30 Welcome & Registration
10:00 – 13:00 Hands-on session: Get started & Find your hotspots.
– Milestones/roadmap & Effort Logs
– Git Version Control System
– Profiling
13:00 – 14:00 Lunch
14:00 – 16:00 Hands-on session
– Measuring performance
16:00 – 18:00 Presentations of team’s projects
Tuesday, March 6
09:00 – 10:45 Session 1
10:45 – 11:15 Break
11:15 – 13:00 Hands-on session: Go from sequential to parallel with your hotspots.
– Understand your code
13:00 – 14:00 Lunch
14:00 – 15:30 Session 3
15:30 – 16:00 Break
16:00 – 18:00 Daily reports on team’s progress
Wednesday, March 7
09:30 -13:00 Hands-on session: Go from sequential to parallel with your hotspots.
– Introduce parallelism: OpenMP and OpenACC
13:00 – 14:00 Lunch
14:00 – 15:30 Session 3
15:30 – 16:00 Break
16:00 – 18:00 Presentations of team’s progress
20:30 – 22:30 Networking dinner in a restaurant (Sharing the expenses)
Thursday, March 8
09:00 – 10:45 Hands-on session
– Parallware Trainer
– Usage of supercomputer Finis Terrae II
10:45 – 11:15 Break
11:15 – 13:00 Session 2
13:00 – 14:00 Lunch
14:00 – 15:30 Session 3
15:30 – 16:00 Break
16:00 – 18:00 Session 4
Friday, March 9
09:00 – 11:00 Feedback and preparation of final presentations
11:00 – 11:30 Break
11:30 – 13:30 Final presentations on achievements and future roadmap
13:30 – 14:00 Close the event
COMMITTEE
Co-organized by
Centro de Supercomputación de Galicia (CESGA)
Appentra Solutions
Sponsors
