Back To Schedule
Monday, November 14 • 9:30am - 12:30pm
Online Training Lab: Solving GPU Audio Processing Challenges, Parallelizing DSP Algorithms and Executing for Real-Time and Offline Rendering

Log in to save this to your schedule, view media, leave feedback and see who's attending!

GPU based audio processing has long been considered something of a unicorn in both the Pro Audio industry as well as the GPU industry. The potential for utilizing a GPU’s parallel architecture is both exciting and elusive, due to the number of computer science issues related to working with sequential DSP algorithm design and the fundamental differences between MIMD and SIMD devices. Now possible, GPU-processed audio can offer processing power for any audio application that is orders of magnitude greater than CPU counterparts; fulfilling a cross-industry need that has quickly arisen as digital media content adopts AI, ML, Cloud-based collaboration, virtual modeling, simulated acoustics and immersive audio (to name a few). The state of research had previously concluded that because of heavy latencies and a myriad of computer science issues, DSP on GPUs was just not possible nor preferable. Recognizing the need to create a viable, low-level standard and framework for Real-Time professional GPU audio processing, GPU AUDIO INC set out to solve these fundamental problems.

The purpose of this workshop is to give you a hands-on experience for what GPU Audio processing solves, and what it can mean for your software and the future of audio. It is a taste of the GPU Audio SDK coming soon.

In this course you will learn about the fundamental problems solved by the new GPU Audio standard, go deeper into our core technology, and learn how to incorporate Real-Time/low latency DSP algorithms into your projects. You will participate in a deep-dive hands-on tutorial in building a simple processor, implementing your own IIR processor, measure performance and playback, and “take home” the code to build an FIR processor. All made possible by the GPU Audio Scheduler. 

Familiarity with DSP algorithms and designs
Familiarity with modern SWE tools (IDEs, Git, CI/CD)

** This Training Lab is generously supported by NVIDIA & the Deep Learning Institute **

avatar for Rumen Angelov

Rumen Angelov

Plugin Development Team Lead, GPU Audio
I've completed my education in Music And Audio Technology at the Bournemouth University, Dorset. Primarily experienced in audio plugin development for both Microsoft and Apple operating systems and the major plugin formats. Briefly worked on audio processing for proprietary ARM-based... Read More →
avatar for Andres Ezequiel Viso

Andres Ezequiel Viso

Product Manager, Braingines SA / GPU Audio Inc
I studied Computer Science at the University of Buenos Aires and received my PhD on semantics for functional programming languages. I did a posdoc at Inria, France, in the context of the Software Heritage project, developing the provenance index for the SWH Archive. My interest vary... Read More →

Monday November 14, 2022 9:30am - 12:30pm GMT
3) CMD 10 South Pl, London EC2M 7EB, UK