Wednesday, August 5, 2009

Best Gaming CPUs For The Money: July 2009

Our First Gaming CPU for the Money Article

I approached writing an article about the best CPUs for the money with a great deal of caution. I write the Best Gaming Graphics Cards for the Money monthly piece and it's pretty straightforward—graphics cards are used to get higher frame rates in games, so all I really have to look at is the price/performance ratio in games and come up with what I think are the best buys. There are a lot more variables, but at the root it comes down to game performance and entry price.

On the other hand, a CPU can be used for a great many things. Anything and everything done on a PC is at least somewhat dependent on CPU performance, including writing documents, image editing, games, database queries, Internet use, server apps, scientific calculations...the list goes on and on. In truth, it's nearly impossible to make recommendations that will apply universally in light of the many different usage models that exist.

We therefore have to focus on a particular aspect of CPU performance that we can better measure, compare, and assess. Why not gaming? People are interested in the best graphics card they can get to game, so it stands to reason that they're also interested in the best gaming CPU their money can buy.

This still leaves us with the task of measuring CPU gaming performance versus price to come up with results on which we can base recommendations. With CPUs, this is a little tricky, as certain games favor multiple cores, clock speed, cache, and even a specific architecture.

How Many CPU Cores Do You Need?

A few months ago, we looked into the effectiveness of using different numbers of CPU cores with various types of software. We received a lot of good feedback from that article, and there were some interesting suggestions from the community that we've taken to heart in this follow-up.

Primarily, there was a concern that part one might have been flawed technically, as the Core 2 Quad Q6600 we used in our testing does not share all 8 MB of its L2 cache between its four CPU cores. Intel's Q6600 instead has two separate 4 MB cache repositories, each shared between one pair of CPU cores. This means the quad- and triple-core results would have demonstrated the CPUs utilizing 8 MB of total cache, while the dual- and single-core results show that they were likely benefiting from 4 MB. Indeed, the benchmarks may have been reflecting the difference in L2 cache availability more than performance attributable to enabled processing cores.