Why Intel's Nehalem Is Important

Everybody's all atwitter about Intel's branding move, which will see its new Nehalem -- that's the code name --- desktop processors hit the market with a "Core i7" identifier. Can you keep this naming stuff straight? I certainly can't. Nope, what's important isn't the branding -- it's the technology inside Intel's upcoming, 45-nm processor family. Here's the deal.

Alexander Wolfe, Contributor

August 12, 2008

3 Min Read

Everybody's all atwitter about Intel's branding move, which will see its new Nehalem -- that's the code name --- desktop processors hit the market with a "Core i7" identifier. Can you keep this naming stuff straight? I certainly can't. Nope, what's important isn't the branding -- it's the technology inside Intel's upcoming, 45-nm processor family. Here's the deal.The two most important facts about the Nehalem family is that the processors are manufactured in 45-nm and that they have an updated architecture. Let's take those one at a time. What's 45-nm and why is it important? That number refers to the size of the physical features etched into the chip's silicon.

Small feature size enables lower-power operation. Intel's previous generation was 65-nm. Long story short, on 45-nm chips, you can switch gates on and off faster, and typically using lower voltage (which equates to less power, because power equals voltage times current) than you can on 65-nm designs.

Why is power dissipation such a big deal? Well, it's the reason Intel shifted from designing ever-faster single-core processors, and started on the road to dual- and quad-core design four years ago. That was when Intel saw that single-core chips running faster than 3 GHz would have pushed power dissipation as high as 150 W. Not good, especially with customers' increased concerns about paying for data-center electricity and cooling costs.

OK, so that's the really short version. If you want a deeper dive into the issues behind power-dissipation and the move to multicore processing, listen to my podcast with Intel Senior Fellow Mark Bohr.

The podcast is located here.

The second salient fact about Nehalem is its updated architecture. Intel launched its first 45-nm family with Penryn, which is its current most-advanced generation. Nehalem will take this to the next level. Intel will detail the Nehalem architecture next week at its Intel Developer Forum in San Francisco.

For now, Intel has publicly stated that the first Nehalem processors "will be in production in Q4 and feature a unique mix of performance and energy efficiency." (The first Nehalems will be high-end desktop quad cores.)

One big thing I do know is that Nehalem will likely have an on-die memory controller. It also will feature something called the QuickPath point-to-point interconnect. Both these features will boost performance by reducing memory access times and enable the chip to route data faster.

Here are some slides from Intel showing its Nehalem road map. The first slide is for desktop processors, the second shows the server road map.

Nehalem desktop roadmap. (Click picture to enlarge.)


Nehalem server roadmap. (Click picture to enlarge.)


Nehalem's features. (Click picture to enlarge.)

Please leave your comments below or e-mail them to me directly at [email protected].

Like this blog? Subscribe to its RSS feed, here.

For a mobile experience, follow my daily observations on Twitter.

Check out my tech videos on this YouTube channel.

About the Author(s)

Alexander Wolfe

Contributor

Alexander Wolfe is a former editor for InformationWeek.

Never Miss a Beat: Get a snapshot of the issues affecting the IT industry straight to your inbox.

You May Also Like


More Insights