> Nvidia was already investing heavily
that sounds very interesting, can you link/share/describe some details on it? how much did they invest? how? into CUDA? what else?
that sounds very interesting, can you link/share/describe some details on it? how much did they invest? how? into CUDA? what else?
CUDA 1.0 was released in 2007:
* https://insidehpc.com/2007/07/nvidia-releases-cuda-10/
* https://developer.nvidia.com/cuda-toolkit-archive
From SIGGRAPH 2007, "GPU computing with NVIDIA CUDA":
* https://dl.acm.org/doi/10.1145/1281500.1281647
"NVIDIA: The Era of the Personal Supercomputing":
* https://www.nvidia.com/content/events/siggraph_2007/supercom...
Before AI/ML was hot, and before even the Bitcoin paper was released. NVidia was investigating/experimenting/investing in the concept before there was any kind of 'killer app' for it.
Later on they acquired PGI, which thanks to PTX, had C, C++ and Fortran compilers, thus adding Fortran into the mix.
Followed along by all the IDE, graphical debuggers tooling and library ecosystem.
Meanwhile Intel and AMD were doing who knows what at Khronos stuck in their "C is good enough" mentality, and barely released useful developer experiences.
I am curious about your PaaS because we were analyzing that business for fun first. A small thread here in HN: https://news.ycombinator.com/item?id=39329764
Here's an old tutorial video of the product: https://youtu.be/V2q9hVdi80w
We were doing cool things and on the cutting edge but ultimately couldn't make a business out of it and weren't talking to the right people.