Archives for nvidia

Is Intel the new Intel?

The race for A.I. is not just about software, it’s about hardware too. As explained earlier running software that ‘learns’ requires a different architecture than traditional software. Many companies (including Intel) are trying to become the “Intel inside” of A.I.

1. A new hope
Chris Malachowsky (co-founder of Nvidia) was one of the first to see the nascent market for so-called graphics processor units, or GPUs. These chips, typically sold as cards that video gamers plug into a PC’s motherboard, provide ultrafast 3-D graphics. Marketed under testosterone-drenched labels like “GeForce GTX 1080,” these cards can cost up to $1,200, and two decades later they still produce more than half of Nvidia’s $5 billion in revenues.

And it’s not just the gaming industry that is craving for GPU’s. According to Forbes, there are an estimated 3,000 AI startups worldwide, and many of them are building on Nvidia’s platform. They’re using Nvidia’s GPUs to put AI into apps for trading stocks, shopping online and navigating drones. Read More

> Read full Is Intel the new Intel? post

The architecture behind A.I.

Talking about hardware is like comparing a bicycle with a 4×4. When you are in the city a bike will do just fine, but when you need to get across some rough terrain you’ll prefer a 4×4. The same goes for A.I. It requires a different set-up than the your ordinary web application. Let’s look at the two most promising trends.

1. CPU, GPU, NPU and TPU?
Today’s computers can be traced back at least to Blaise Pascal’s 1642 mechanical calculator. It’s descendant is the traditional Central Processing Unit (CPU) that does most of the computing in your laptops, desktop pc’s and your phone, but it wasn’t designed to deal with large datasets as needed with for example machine learning.

Now let’s look at the Graphics Processing Units. The GPU’s advanced capabilities were originally used primarily for 3D game rendering. But now those capabilities are being harnessed more broadly to accelerate computational workloads in areas such as financial modeling, cutting-edge scientific research and oil and gas exploration. Read More

> Read full The architecture behind A.I. post