High Performance Computing Quotes

What we're really trying to do is have heterogeneous systems really become the foundation of our computing going forward. And that's the idea that you make every processor and every accelerator a peer processor.

We see incredible opportunity to solve some of the biggest social challenges we have by combining high-performance computing and AI - such as climate change and more.

If you believe that the mobile phone is the next supercomputer, which I do, you can imagine a datacenter that is modeled after, literally, hundreds or thousands or millions of mobile phones. They won't have screens on them, but there'll be millions of lightweight mobile-phone processors in the datacenter.

A state-of-the-art calculation requires 100 hours of CPU time on the state-of-the-art computer, independent of the decade.

Traditional computing is always going to be a part of AMD's business, but our technology can go further.

I just bought a Mac to help me design the next Cray.

Why is it that I notice so many brilliant scientists using Macs for their personal computers; why does the Lawrence Livermore & Berkeley Labs buy millions of dollars worth of Macs?

There was a project at Lawrence Livermore National Labs where many years ago they went down this path for scripting and controlling very large numerical calculations.

VR is going to become something mainstream, but it's not going to happen right away. You just don't have the horsepower to make it happen on a device, much less a cheap enough and comfortable enough device that a normal consumer is going to want to have.

The 65,536 processors were inside the Connection Machine.

Nvidia's CEO, Jen-Hsun Huang, is an engineer and a chip designer. He cofounded Nvidia and still runs it like a startup.

I think that that multiplatform development is what's on the mind of most high-end PC developers now... this is really the first time in the industry's history that we've had console machines that can handle all that PC developers can deliver.

The notion of what we're trying to do at AMD is about bringing out great technology, great products.

Briefly, to program it requires an absolute understanding of how all 65,536 processors are interconnected.

The Connection Machines owned by the United States government laboratories were made available to me because they were considered impossible to program and there was no great demand for them at that time.

At its core, HP has the best technologists on the planet Earth.

We've announced an Oracle Virtual Compute Appliance, a bunch of low-cost commodity servers running Linux, integrated in our case, with InfiniBand - connected with InfiniBand vs. the traditional Ethernet.

Compounding the cost, most mapping software is processor-intense.

I get the biggest enjoyment from the random and unexpected places. Linux on cellphones or refrigerators, just because it's so not what I envisioned it. Or on supercomputers.

The workstation-class machines built by Sun and others opened up new worlds for hackers.

The Connection Machine was the most powerful supercomputer in the world. It is a complex supercomputer and it will take forever to completely describe how it works.

We're approaching being able to do a billion billion calculations per second, and that's the - that's the objective of our national labs. We're still not there. But with hundreds of millions of calculations per second.

If 80,000,000 polygons per second is reality, what happens to you when you live in a world 160,000,000?