Covering Super Computing 17.

Brought to you by Intel.

(techno music)

Hey, welcome back, everybody.

Jeff Frick here with theCUBE.

We're in Denver, Colorado at

the Super Computing Conference 2017.

About 12 thousand people, talking

about the outer edges of computing.

It's pretty amazing.

The keynote was huge.

The square kilometer array, a new

vocabulary word I learned today.

It's pretty exciting times,

and we're excited to have our next guest.

He's Bill Jenkins.

He's a Product Line Manager for AI on FPGAs at Intel.

Bill, welcome.

Thank you very much for having me.

Nice to meet you, and nice to talk to you today.

So you're right in the middle of this machine-learning

AI storm, which we keep hearing more and more about.

Kind of the next generation of big data, if you will.

That's right.

It's the most dynamic industry I've seen

since the telecom industry back in the 90s.

It's evolving every day, every month.

Intel's been making some announcements.

Using this combination of software programming and FPGAs

on the acceleration stack to get more

performance out of the data center.

Did I get that right?

Sure, yeah, yeah.

Pretty exciting.

The use of both hardware, as well as software on top of it,

to open up the solution stack, open up the ecosystem.

What of those things are you working on specifically?

I really build first the enabling technology that brings

the FPGA into that Intel ecosystem.

Where Intel is trying to provide that solution

from top to bottom to deliver AI products.

>> Jeff: Right.

Into that market.

FPGAs are a key piece of that because we provide a different

way to accelerate those machine-learning and AI workloads.

Where we can be an offload engine to a CPU.

We can be inline analytics to offload the system,

and get higher performance that way.

We tie into that overall Intel

ecosystem of tools and products.

Right.

So that's a pretty interesting piece because

the real-time streaming data is all the rage now, right?

Not in batch.

You want to get it now.

So how do you get it in?

How do you get it written to the database?

How do you get it into the micro-processor?

That's a really, really important piece.

That's different than even two years ago.

You didn't really hear much about real-time.

I think it's, like I said, it's evolving quite a bit.

Now, a lot of people deal with training.

It's the science behind it.

The data scientists work to figure out what topologies

they want to deploy and how they want to deploy 'em.

But now, people are building products around it.

>> Jeff: Right.

And once they start deploying these technologies

into products, they realize that they don't want to

compensate for limitations in hardware.

They want to work around them.

A lot of this evolution that we're building is to try to

find ways to more efficiently do that compute.

What we call inferencing, the actual deployed

machine-learning scoring, as they will.

>> Jeff: Right.

In a product, it's all about how

quickly can I get the data out.

It's not about waiting two seconds to start the processing.

You know, in an autonomous-driven car where

someone's crossing the road, I'm not waiting

two seconds to figure out it's a person.

Right, right.

I need it right away.

So I need to be able to do that with video feeds,

right off a disk drive, from the ethernet data coming in.

I want to do that directly in line, so that my processor

can do what it's good at, and we offload that processor

to get better system performance.

Right.

And then on the machine-learning

specifically, 'cause that is all the rage.

And it is learning.

So there is a real-time aspect to it.

You talked about autonomous vehicles.

But there's also continuous learning over time,

that's not necessarily dependent on learning immediately.

Right.

But continuous improvement over time.

What are some of the unique challenges in machine-learning?

And what are some of the ways that

you guys are trying to address those?

Once you've trained the network,

people always have to go back and retrain.

They say okay, I've got a good accuracy,

but I want better performance.

Then they start lowering the precision,

and they say well, today we're at 32-bit, maybe 16-bit.

Then they start looking into eight.

But the problem is, their accuracy drops.

So they retrain that into eight topology, that network,

to get the performance benefit,

but with the higher accuracy.

The flexibility of FPGA actually allows people to take

that network at 32-bit, with the 32-bit trained weights,

but deploy it in lower precision.

So we can abstract away the fact that the hardware's

so flexible, we can do what we call

floating point 11-bit floating point.

Or even 8-bit floating point.

Even here today at the show, we've got a binary and ternary

demo, showcasing the flexibility that the FPGA can provide

today with that building block piece

of hardware that the FPGA can be.

And really provide, not only the topologies that

people are trying to build today, but tomorrow.

>> Jeff: Right.

Future proofing their hardware.

But then the precisions that they may want to do.

So that they don't have to retrain.

They can get less than a 1% accuracy loss, but they can

lower that precision to get all the performance benefits

of that data scientist's work to

come up with a new architecture.

Right.

But it's interesting 'cause there's trade-offs, right?

>> Bill: Sure.

There's no optimum solution.

It's optimum as to what you're trying to optimize for.

>> Bill: Right.

So really, the ability to change the ability to continue

to work on those learning algorithms,

to be able to change your priority, is pretty key.

Yeah, a lot of times today, you want this.

So this has been the mantra of the FPGA for 30 plus years.

You deploy it today, and it works fine.

Maybe you build an ASIC out of it.

But what you want tomorrow is going to be different.

So maybe if it's changing so rapidly,

you build the ASIC because there's runway to that.

But if there isn't, you may just say, I have the FPGA,

I can just reprogram it to do what's

the next architecture, the next methodology.

Right.

So it gives you that future proofing.

That capability to sustain different topologies.

Different architectures, different precisions.

To kind of keep people going with the same piece of hardware.

Without having to say, spin up a new ASIC every year.

>> Jeff: Right, right.

Which, even then, it's so dynamic it's probably faster

then, every year, the way things are going today.

So the other thing you mentioned is topography,

and it's not the same topography you mentioned,

but this whole idea of edge.

Sure.

So moving more and more compute,

and store, and smarts to the edge.

'Cause there's just not going to be time, you mentioned

autonomous vehicles, a lot of applications

to get everything back up into the cloud.

Back into the data center.

You guys are pushing this technology,

not only in the data center, but progressively

closer and closer to the edge.

Absolutely.

The data center has a need.

It's always going to be there, but they're getting big.

The amount of data that we're trying

to process every day is growing.

I always say that the telecom industry

started the Information Age.

Well, the Information Age has done

a great job of collecting a lot of data.

We have to process that.

If you think about where, maybe I'll

allude back to autonomous vehicles.

You're talking about thousands of

gigabytes, per day, of data generated.

Smart factories.

Exabytes of data generated a day.

What are you going to do with all that?

It has to be processed.

We need that compute in the data center.

But we have to start pushing it out into the edge,

where I start thinking, well even

a show like this, I want security.

So, I want to do real-time weapons detection, right?

Security prevention.

I want to do smart city applications.

Just monitoring how traffic moves through a mall,

so that I can control lighting and heating.

All of these things at the edge, in the camera,

that's deployed on the street.

In the camera that's deployed in a mall.

All of that, we want to make those smarter,

so that we can do more compute.

To offload the amount of data that needs

to be sent back to the data center.

>> Jeff: Right.

As much as possible.

Relevant data gets sent back.

No shortage of demand for compute

store networking, is there?

No, no.

It's really a heterogeneous world, right?

We need all the different compute.

We need all the different aspects of

transmission of the data with 5G.

We need disk space to store it.

>> Jeff: Right.

We need cooling to cool it.

It's really becoming a heterogeneous world.

All right, well, I'm going to give you the last word.

I can't believe we're in November of 2017.

Yeah.

Which is bananas.

What are you working on for 2018?

What are some of your priorities?

If we talk a year from now, what

are we going to be talking about?

Intel's acquired a lot of companies

over the past couple years now on AI.

You're seeing a lot of merging of

the FPGA into that ecosystem.

We've got the Nervana.

We've got Movidius.

We've got Mobileye acquisitions.

Saffron Technologies.

All of these things, when the FPGA is kind of a key piece

of that because it gives you that flexibility

of the hardware, to extend those pieces.

You're going to see a lot more stuff in the cloud.

A lot more stuff with partners next year.

And really enabling that edge to data center compute,

with things like binary neural networks,

ternary neural networks.

All the different next generation of topologies

to kind of keep that leading edge flexibility

that the FPGA can provide for people's products tomorrow.

>> Jeff: Exciting times.

Yeah, great.

All right, Bill Jenkins.

There's a lot going on in computing.

If you're not getting your computer science

degree, kids, think about it again.