CodeCamp

Due to the varied group of participants it has been decided that the first day will focus on CUDA python and the second day on C/C++ with OpenACC.

The CUDA python program

will follow the standard NVIDIA one day course “Fundamentals of Accelerated Computing with CUDA Python”. This course explores how to use Numba—the just-in-time, type-specializing Python function compiler—to accelerate Python programs to run on massively parallel NVIDIA GPUs. You’ll learn how to:

• Use Numba to compile CUDA kernels from NumPy universal functions (ufuncs).
• Use Numba to create and launch custom CUDA kernels.
• Apply key GPU memory management techniques.

Upon completion, you’ll be able to use Numba to compile and launch CUDA kernels to accelerate your Python applications on NVIDIA GPUs.

The OpenACC program

will follow the Linux Academy “Introduction to OpenACC – NVIDIA OpenACC Online Lab” .

OpenACC.org, Amazon Web Services, NVIDIA, and Linux Academy have organized the Introduction to OpenACC lab. This lab consists of three instructor-led classes that include interactive lectures, dedicated Q&A sessions, and hands-on exercises. The lab covers analyzing performance, parallelizing, and optimizing code.

Experience programming in C, C++, or Fortran is helpful but not required. You do not need any prior experience with OpenACC directives or GPU programming to complete this lab.

Day 1

10:00 am Introduction to CUDA with Numba

12:30 pm Lunch

13:30 pm Custom CUDA Kernels in Python with Numba

15:30 pm Multidimensional Grids and Shared Memory for CUDA Python with Numba

19:30 Evening Meal

Day 2

09:00 am Introduction to OpenACC – NVIDIA OpenACC Online Lab

12:30 Lunch

13:30 pm Participants work on their codes

16:30 pm Feedback

17:00 pm The End

Who will attend

There will be a mix of local/DiRAC researchers, supported by a NVidia trainer. All you need is a laptop and a willingness to learn.

Venue

The hackathon is located in the beautiful city of Durham at the Ogden Centre, Durham University, South Road DH1 3LE. The event will be held in room OCW017.

Accommodation

DiRAC will support any DiRAC researchers wishing to attend this even by paying for their accommodation. Individuals will pay for the room themselves and then claim the cost back. DiRAC will only accept accommodation and breakfast costs from the approved hotel below:

travelodge Durham

Staying at this venue is highly preferred, since it maximises networking opportunities and ensure all participants can get the most out of the event.

Travel & Meals

Participants are expected to cover their travel.

Taxi

As sponsor NVidia has agreed to cover the costs of all meals during this event.

Important dates

• 22nd November application deadline.
• 25th November successful applicants will get a n email confirming there place at the event.
• 11th December Event Welcome

Contact

If you need any addition information, please do not hesitate to contact DiRAC’s Training Manager: Richard Regan.

• Tel: 0191 3343632
• email: richard.regan@durham.ac.uk

What is CodeCamp

CodeCamp is an opportunity for the novice user to enhance their skill set and practice these new skills with their own code. During the event there will be dedicated instructor lead periods, where participants will work on specific examples that highlight aspects of GPU development.

Why GPUs

GPUs give researchers access to high volume data processing capability, due to having thousands of cores, and specialized hardware enabling fast tensor processing.

Learn how to accelerate and optimize existing C/C++ CPU-only applications to leverage the power of GPUs using the most essential CUDA techniques and the Nsight Systems profiler.

Prerequisites: Basic C/C++ competency including familiarity with variable types, loops, conditional statements, functions, and array manipulations.

Where is the Event

This March, DiRAC is holding a GPU CodeCamp in Durham on the 17th.

How do I Get involved

If you are interested in participating please complete the form below

send it to richard.regan@durham.ac.uk. your application form need to be received by Sunday the 2nd of March. All successful applicants will be notified a few days after receiving the application.