AMD is trying to tackle the same audio problems as targeted by Nvidia's VRWorks Audio. The aim according to the brief is to:

“Create a scalable AMD technology that enables full real-time dynamic physics-based audio acoustics rendering, leveraging the powerful resources of AMD GPU Compute."

In other words, it will give immersive audio alongside VR headsets and allow audio to catch up a bit with graphics.

Writing in the GPU Open blog, Carl Wakeland, a Fellow Design Engineer at AMD, said that the 2D screen had resulted in sound never really getting a look in. Some games had bought in 3D audio as a novelty but this could be a distraction. But head-mounted display "changes everything."

AMD TrueAudio Next is a significant step towards making environmental sound rendering closer to real-world acoustics with the modelling of the physics that propagate sound – AKA auralisation.

The new AMD TrueAudio Next library is a high-performance, OpenCL-based real-time math acceleration library for audio, with special emphasis on GPU compute acceleration. But it is not perfect yet, although the fact it has real-time GPU compute backing it up it is pretty good, apparently.

Wakeland says that two primary algorithms need to be catered for - time-varying convolution (in the audio processing component) and ray-tracing (in the propagation component).

"On AMD Radeon GPUs, ray-tracing can be accelerated using AMD’s open-source FireRays library, and time-varying real-time convolution can be accelerated with the AMD TrueAudio Next library."

AMD uses a new 'CU Reservation' feature to reserve some CUs for audio, as necessary, and the use of asynchronous compute.