Home // SnT // News & E... // Workshop - NVIDIA Fundamentals of Accelerated Computing with CUDA Python

Workshop - NVIDIA Fundamentals of Accelerated Computing with CUDA Python

twitter linkedin facebook google+ email this page
Add to calendar
Speaker: Dr Georgios Varisteas (University of Luxembourg)
Event date: Friday, 30 August 2019 09:00 am - 06:00 pm
Place: Room E004
JFK Building
29 Avenue J.F. Kennedy
L-1855 Kirchberg

Please register online here

Registration deadline: 28 August 2019

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.

This workshop is fully hands-on with multiple coding exercises, thus previous Python experience would be beneficial. However, CUDA is covered entirely by the material; attendees that have never used CUDA before will gain everything required to be immediately productive with CUDA Python, while more experienced CUDA developers will have an opportunity to focus on and experiment with the more advanced features that maximize performance.

All participants will receive access to the NVIDIA DLI cloud infrastructure as well as the official DLI training material for at least 3 months. Thus, you will be able to continue or revise the course on your own pace after the end of this workshop. Thus, anyone can attend and complete the workshop with even minimal prior experience. NVIDIA provides completion certificates after successful assessment of certain deliverables.
Every concept is delivered with an initial lecture, then demonstrated with hands-on exercises. During these exercises, participants are guided to implement the lectured techniques but are also free to experiment and expand using the NVIDIA computing cloud infrastructure.

Seating is limited to 40 and prior registration is required by NVIDIA to reserve sufficient hardware resources in their cloud. Please reserve your place by Wednesday, 28 August. Lunch will not be provided.

The workshop will be given by Dr Georgios Varisteas, Research Associate in the SEDAN Research Group, and a certified NVIDIA DLI instructor.