Thursday, December 21, 2006

A peek at Intel's upcoming roadmap

by Jon Stokes

A peek at Intel's upcoming roadmap

Two new rumors offer a peek at what's in the cards for Intel in 2007 and 2008. First up is a rumor from HKPEC that fleshes out the picture of the bottom end of Intel's lineup that has been emerging over the past few months. Specifically, we can now add more details of single-core Merom-based parts to what we've already heard about the single-core Conroe-L.

Previously, news had leaked out about a Merom-based Celeron M 520, which is supposed to be launched in January. (The brains of the rumored MacBook Thin, perhaps?) The new rumor brings news of a Celeron M 523 (933MHz) that will come out later in the year. This part, like the other Merom-based single core parts, is a 65nm Socket M part with a TDP of 5W.

Also fitting those same socket and TDP specs are two other Merom-based parts that will go under the "Core 2 Solo" moniker. These will sport higher clockspeeds and be sold under the U2100 (1.2GHz) and U2200 (1.06GHz) names. The Core 2 Solo parts are also due out in Q3 of 2007.

The news that these parts will be branded as "Core 2 Solo" makes me wonder if there's any truth to previously reported rumors that the single-core Conroe-L will be sold under the venerable Pentium brand name. Why would Intel revive the Pentium brand for single-core Conroe, while shipping single-core Meroms under the Core 2 Solo and Celeron brands?

In other Intel rumor news, VR-zone claims to have seen a roadmap that puts Intel past the 4GHz barrier in 2008. The chip that will break the barrier is allegedly the quad-core Bloomfield processor. Bloomfield has long been rumored to be a 45nm design that will use Intel's long-delayed common systems interconnect (CSI)—an answer to coherent HyperTransport that will also host the Itanium product family. Bloomfield is also a true quad-core part, in that all four cores sit on the same die and share an L2 cache.

I don't think that the 4GHz rumor sounds particularly implausible, given current clockspeeds on the 65nm process. However, I do wonder about part of the rumor that says they'll do it in the 130W power envelope.

(c) www.arstechnica.com

No comments:

Tag Cloud