Developer Voices

GPUs, from Simulation to Encryption (with Agnès Leroy)

Sep 18, 2024

In this engaging discussion, Agnès Leroy, a seasoned GPU programmer and optimizer, dives into the expansive capabilities of GPU technology beyond graphics. She shares her transition from studying mechanics to programming simulations for hydroelectric power and even dental applications. The conversation highlights fascinating topics like fluid dynamics, fully homomorphic encryption, and strategies for optimizing cryptography using GPU acceleration. Agnès also addresses the challenges of moving from C++ to Rust, emphasizing the importance of memory safety in programming.

01:03:48

Creator website

Episode guests

Agnès Leroy

AI Summary

AI Chapters

Episode notes

Podcast summary created with Snipd AI

Quick takeaways

GPU programming excels in handling massive parallelism, unlocking diverse applications beyond graphics such as scientific simulations and cryptographic processes.

Fully homomorphic encryption allows computations on encrypted data without exposing sensitive information, presenting challenges and opportunities for performance optimization especially on GPUs.

Advancements in programming languages like Rust could enhance GPU programming by simplifying memory management, making development more efficient and error-resistant.

Deep dives

Understanding GPU Programming

GPU programming is characterized by its ability to handle tasks with massive parallelism, distinguishing it from traditional CPU programming. While GPUs may not serve as general-purpose processors, their design caters to specific tasks, maximizing speed and efficiency. This unique capability opens a diverse array of applications beyond graphics programming, including scientific simulations and complex encryptions. The potential for innovation in this area is significant, particularly for those who understand the intricacies of GPU architecture and optimal coding techniques.

Intro

2min

From Mechanics to Dentistry: A Career Journey

4min

Fluid Dynamics: Bridging Classical Mechanics and GPU Technology

18min

Optimizing GPU Programming with C++ and CUDA

13min

Unveiling Fully Homomorphic Encryption

15min

Navigating the Challenges of Race Conditions and Debugging

2min

Optimizing Cryptography with GPU Acceleration

5min

The Shift from C++ to Rust: A Programmer's Perspective

4min

This week we take a look at what you can do with a GPU when you get away from just using it to draw polygons. Agnès Leroy has spent most of her career programming, optimizing and converting programs to run on that oh-so-curious piece of specialised processing hardware, and we go through all the places that journey has taken her. From simulating the flow of fluids in hydroelectric powerstations, to figuring out how to make a new approach to encryption run fast enough to make it practical…

–

Become a Developer Voices supporter! https://patreon.com/DeveloperVoices

A Fully Homomorphic Encryption Scheme (pdf): https://crypto.stanford.edu/craig/craig-thesis.pdf

CUDA platform: https://developer.nvidia.com/cuda-zone

Rust-CUDA: https://github.com/Rust-GPU/Rust-CUDA

And in case anyone was wondering, A List of Hydroelectric Power Stations in France: https://en.wikipedia.org/wiki/Category:Hydroelectric_power_stations_in_France

–

Kris on Mastodon: http://mastodon.social/@krisajenkins

Kris on LinkedIn: https://www.linkedin.com/in/krisjenkins/

Kris on Twitter: https://twitter.com/krisajenkins