Great interview.
Alluding to software stack when it comes to competition.
You can build the world’s best fricking everything-anything chip, you stick it into the computer, what will you accelerate? Absolutely nothing . Isn’t that right? Accelerated computing is insanely hard. And the reason for that is Moore’s law is insanely good.
To do better than that, you have to go full stack, you have to go domain by domain, and you are going to have to develop a lot of software. You are going to be working on a lot of solvers, hacking away at it like we are. And then of course, after almost 25 years, the architecture becomes trusted everywhere. And so this is where we feel quite privileged. But nonetheless, the ultimate competitor is doing nothing and waiting for Moore’s Law. We are a $10 billion datacenter business, which is maybe five percent of datacenters. That’s another way of saying that 95 percent of datacenters are all CPUs. And that’s the competition.
I have to mention here that AMD does not really have a stack/API like CUDA (widely used/preferrred - moat). They currently have translators for it. They have ROCm and HIP on top of it as a translator. NVIDIA controls this API. AMD is running behind them. This is a challenge that AMD is yet to solve.
HIP is a C++ Runtime API and Kernel Language that allows developers to create portable applications for AMD and NVIDIA GPUs from single source code.
So, nvda is currently at another level when it comes to platform. With omniverse, it will make another leap in its software stack.