[Joker]

Forget dual-core and quad-core processors: A semiconductor company promises to pack 100 cores into a processor that can be used in applications that require hefty computing punch, like video conferencing, wireless base stations and networking. By comparison, Intel’s latest chips are expected to have just eight cores.

“This is a general-purpose chip that can run off-the-shelf programs almost unmodified,” says Anant Agarwal, chief technical officer of Tilera, the company that is making the 100-core chip. “And we can do that while offering at least four times the compute performance of an Intel Nehalem-Ex, while burning a third of the power as a Nehalem.”

The 100-core processor, fabricated using 40-nanometer technology, is expected to be available early next year.

In a bid to beat Moore’s law (which states number of transistors on a chip doubles every two years), chip makers are trying to either increase clock speed or add more cores to a processor. But cranking up the clock speed has its limitations, says Will Strauss, principal analyst with research and consulting firm Forward Concepts.

“You can’t just keep increasing the clock speed so the only way to expand processor power is to increase the number of cores, which is what everyone is trying to do now,” he says. “It’s the direction of the future.”

In fact, Intel’s research labs are already working on a similar idea. Last year, Intel showed a prototype of a 80-core processor. The company has promised to bring that to consumers in about five years.

Tilera, a start-up that was spun out of the Massachusetts Institute of Technology, started in 2007. It says its product will be available in the next few months, which means the company, if successful, will have gone from zero to shipping a powerful chip in just about three years — a very fast time frame in the semiconductor world. That’s because it has created a chip architecture that removes the challenges present in Intel’s x86 design.

As the number of cores on a chip multiplies, a major challenge is how to connect the chip to memory without choking up the processor. That’s why Agarwal says Tilera has used a mesh network architecture. It eliminates the “on-chip bus interconnect,” a central intersection found in most multi-core CPUs through which information must flow through to get between the cores of a chip. That central interconnect presents bandwidth issues of its own, and also forces engineers to limit the number of cores on a chip to avoid information gridlock.

http://www.wired.com/gadgetlab/2009/...era-100-cores/

[elevating]

I sure hope there working on better cooling technology, the tighter you make it the hotter it will get.

[ak21]

Interesting, though I don't think it will be usable, since you have to worry about the amount of power that thing is going to take up, amount of cooling it gets, and all of that stuff.

[EvilMonkey]

I will believe it when I see it.
Startups come out with these kinds of claims all the time, then you never here of them again.

[Wren Akula]

CUDA flavored CPU?
If so, "# core proc" no longer means jack.

[Frankie V]

Wow bucket fill rendering is getting close to real time.

[~Hazdaz~]

Who cares how many cores a CPU has when the software doesn't fully take advantage of it.

Software (both OS and apps) are ridiculously behind the times - right now even 8 cores are not being fully utilized, now imagine a whole order of magnitude more cores to just sit there idling.

Sure, this start-up says they have found a way around all that, but I have little faith that we will ever see a chip from them, let alone one that fully delivers on their promises. At best someone like AMD or Intel will simply buy them outright, or license their tech and make chips from it.

[TF242]

Originally Posted by EvilMonkey

I will believe it when I see it.
Startups come out with these kinds of claims all the time, then you never here of them again.

Why? Intel has a working 80 core demo model for over a year now.

Originally Posted by ~Hazdaz~

Who cares how many cores a CPU has when the software doesn't fully take advantage of it.

Software (both OS and apps) are ridiculously behind the times - right now even 8 cores are not being fully utilized, now imagine a whole order of magnitude more cores to just sit there idling.

Sure, this start-up says they have found a way around all that, but I have little faith that we will ever see a chip from them, let alone one that fully delivers on their promises. At best someone like AMD or Intel will simply buy them outright, or license their tech and make chips from it.

That is why Intel is tossing millions of dollars at universities to develop a new programming language soon. Like real soon. Usually it takes over a decade to develop a language like C++ etc, the new programming language will make multi-core programming easier. Think about it the core number is the only way Intel can make customers upgrade their processors right now, and if the software isn't supporting the number of cores they put out, nobody will upgrade. So they know that this is an emergency situation for them and invest in University research all over the world to get that new programming language out the door sooner than later.

[skalawag]

These guys are about 3 miles from my house. I'll just ask them for a tour tomorrow and come back and answer any questions... like where the heck are they getting the cash for a foundry?

In all seriousness, this isn't exactly a brand new start-up. From their bio, they've been around since 2005, shipped their first product two years ago and have gone through a third round of funding. If no VC believed in their prospects, the money would have dried up a while ago.

...

[skalawag]

These guys are about 3 miles from my house. I'll just ask them for a tour tomorrow and come back and answer any questions... like where the heck are they getting the cash for a foundry?

In all seriousness, this isn't exactly a brand new start-up. From their bio, they've been around since 2005, shipped their first product two years ago and have gone through a third round of funding. If no VC believed in their prospects, the money would have dried up a while ago.

...