News 

Codenamed Penryn, the latest revision of the Core 2 processor line is more than an architectural tweak. It's the first CPU to be based on the most advanced fabrication ever developed: the 45nm process.

This is down 30% from the 65nm process that Core 2 has been based on since its launch. Intel has chosen to remain on the dual, dual-core design with two dies in the same physical package, rather than the "native" quad-core approach that AMD has pioneered with its Barcelona designs.

The basic architecture of the new parts remains the same as the current Core 2 generation. Aside from the new fabrication process though, there are design tweaks and enhancements.

Performance-wise the main boost is given by a fairly prosaic addition: an increase in Level 2 cache from the 8MB in current quad-core parts - 4MB for each pair of cores - up to a new total of 12MB. This is shared in the same way, with 6MB per pair of cores.

When they're launched on 12 November, the cheaper Core 2 Quad and dual-core Core 2 Duo chips based on the new architecture will all feature the same boost, of either 6MB Level 2 cache for the dual-core or 12MB for the quad-core parts.

Our test CPU was the top-end quad-core Core 2 Extreme QX9650, running at 3GHz. Bus speed and preferred chipset are identical to the current top-end part, the Core 2 Extreme QX6850, with a 1,333MHz front-side bus running on either a P35 or X38 chipset-based board. That allowed us to undertake a direct, clock-for-clock comparison on performance between the previous part at the same clock speed.

Clock-for-clock comparison

Penryn is the "tock" in Intel's much-vaunted new

ADVERTISEMENT

"tick-tock" design strategy. The idea is that every 18 months or so, it begins production of an existing architecture on a new fabrication process (the tick) and then 18 months after that brings in a brand-new microarchitecture based on the new fabrication process (the tock). This lets Intel squeeze more life out of existing designs and perfect the new fabbing process before adding the extra complication of a new architecture.

From our results based on the clock-for-clock comparison, it's clear that Intel is right to be moving to a new architecture in the next year or so, as the performance increase offered by the new 45nm Penryn is marginal.

Against the 3GHz QX6850, percentage performance improvement is never anywhere near double figures. The extra cache and some instruction-pipeline tweaks give the QX6950 only around a 6% overall boost against the 6850 in our most CPU-bound test, the 3d studio Max render, with a time-to-first-frame of 30 seconds against 32 seconds for the older part. Overall, our application benchmarks moved from 2.19 to 2.28. Definitely faster, but only by 4% overall.

Where the new part does score over the old is in power consumption. The less thirsty 45nm transistors contribute to a stonking 50W lower power drain under full load, with our test rig consuming a maximum of 210W with the QX6850 against just 160W with the QX9650 fitted.

As well as the extra cache and refinements to the instruction pipeline, the new parts also introduce SSE4 instruction extensions. However, as the number of instructions encompassed by SSE gets larger, they also get more specialised and even Intel itself has trouble coming up with concrete examples of where they'll be useful, beyond video motion-prediction (used in encoding) and specialised 3D maths that could be useful in 3D rendering applications (but not games, where all 3D calculations are now performed by the GPU).

The message from these results is that if you have a current-generation quad-core CPU you won't gain much performance by upgrading, although you'll almost certainly get a more overclockable part. The first-generation Penryn is by no means a disaster, but big performance gains will only come once the higher-clocked parts that 45nm will allow are released.