Optimizing NVIDIA GPUs with C++

The Copenhagen C/C++ meetup group presents:

Bryce Adelstein Lelbach and Conor Hoekstra!

On Friday September 19, 2025, Bryce Adelstein Lelbach and Conor Hoekstra from NVIDIA will be speaking at an event hosted by the Copenhagen C/C++ Meetup group.

Introduction
Bryce and Conor need very little introduction in the world of C++. Both are distinguished members of the C++ community. Bryce chaired the C++ Library Evolution and Conor is a former member of the Canadian C++ Committee. Both work at NVIDIA and have a long history with language design and C++.
Bryce is a Principal Architect at NVIDIA, where he founded the Core C++ Compute Libraries team and now leads the Vanguard Programming group that drives NVIDIA's roadmap for programming languages, compilers and libraries. He is also a long-time organizer and former program chair for a number of conferences.
Conor is a Research Scientist at NVIDIA working on parallel array programming models and languages. He is also the founder and organizer of the Programming Languages Virtual Meetup, he has a YouTube channel (code_report) and is the host of three podcasts, one of them which he co-hosts with Bryce: Algorithms + Data Structures = Programs (ADSP, adspthepodcast.com).

They will present on getting the most out of our GPUs with C++ without the requirement of writing custom kernels or manually managing storage for everything! Through this talk you will:

Learn to evaluate when you should use a CUDA library versus writing your own kernel.

• Explore popular CUDA C++ libraries such as Thrust, CUB, and libcu++.
• Understand how you can easily compose different CUDA libraries and your own custom CUDA C++ code together.
• Build intuition about the performance implications of CUDA libraries.
• You'll leave confident about how to select the best tool for the job to accelerate your C++ applications for your unique use cases.

Come learn about the libraries and techniques that make writing CUDA C++ code easier and more performant. Through examples, we'll explore all aspects of writing modern C++ software for GPUs, including heterogeneous memory management, algorithm design, and synchronization.

Agenda
17:00 Intro and welcome
17.15 First part of the talk
18.20(-ish) cold drinks and refreshments
19.00 Second Talk part of the talk
20.00(-ish) Mingling and networking
21.00 Thanks for tonight

The practical stuff

This is a free event, but we expect it to be quite popular! So please only sign up if you can participate! Also, if you sign up but are prevented from coming after all, please de-register and leave your seat to the next person in line.

Date: Friday 19 September 2025 – 17.00-21.00

Address: Symbion, Fruebjergvej 3, 2100 Copenhagen Ø

Parking a public transportation: There is free and ample parking right behind the building. Please register your license plate at the entrance. If you are coming by train, nearest station is Ryparken (10-15 minutes walk).

The event is cohosted by TeqLink and Symbion.

Questions about the event? Reach out to Nina Jensen from teqlink

Questions about the content? Reach out to c/c++ organizer Jens Schønberg.