Hacker News new | ask | show | jobs
by Gh0stRAT 915 days ago
IIRC people were already converting their data into texture maps and writing their SIMD instructions as shaders operating on those textures before Nvidia released CUDA.
3 comments

^ exactly.

What people find contentious is this claim that they specifically did it for ML/AI. That's not why they invested the way they did.

I remember some DAWs supporting pluggins to run PCM over GPU back in the early 00s.

It was hugely experimental but does demonstrate that the idea of a GPUs being used for compute isn’t a recent one.

Ah yeah there was an article on HN about that a couple years ago. GPGPU before Cuda, now onto a treasure hunt ...