RSS Feed

HCW Tech Blog

For the latest info on computer hardware, tech, news, video games, software tips, and Linux, check out our new improved front page: HCW Tech Blog

Reviewed by: Carl Nelson [08.07.06]
Manufactured by: Intel



By now I'm pretty sure it's clear; processors have far less influence on gaming performance than the video card. At this point, it's a much better idea to spend more money on a high end video card, and get a slower CPU, if your primary purpose is to play video games.

That said, there can be some minor changes in performance, depending on the CPU used. Furthermore, games are coming out with more complex AI, physics, pathfinding, and other effects that will tax the CPU more than ever before. At that point, it will be time for us to redo the way we test video games, because 'canned' benchmarks won't take things like AI and physics into consideration.

The one test we have that will push the CPU over anything else is the latest version of 3dMark. Here is what they say in their whitepaper regarding the CPU test:

Both CPU tests use our new game engine, and rely on AI, physics and game logic to generate a multi-threaded workload that can be distributed on multiple processors, cores or even on a single processor. Ageia PhysX library and D* Lite path finding AI algorithm are produce demanding CPU loads. Tests are run in a fixed frame rate of 2FPS for more equal CPU loading. Resolution is locked to 640x480 to decrease GFX influence of performance. The shader profile is locked to 2_0 and no dynamic shadows are used. The D* Lite AI algorithm generates unit path requests in a dynamic path finding grid, where each unit represents a moving obstacle, and paths sync back at 200ms-600ms intervals. The complexity of the path request fulfillment varies; the dynamic re-planning algorithm can re-use the state of previous searches. The Ageia physics uses 87 units and their rigid bodies at 20ms physics steps. Professional reviewers can disable a second CPU or other core of either a virtual or physical dual core system for comparable results regardless of the number of cores or CPUs.

In other words, they attempt to eliminate the video card from influencing the test, and make the CPU work harder than it ever would in a real game. This should give us a better idea of how each CPU would act in future games with more advanced physics (notwithstanding hardware like AGEIA's Phys-X adapter, of course, but it's not like anyone actually bought one of those).

In all our gaming tests, we're using a GeForce 6800 GT 256 MB.

Here are the results from the 3dMark 06 CPU test:

According to 3DMark, it shouldn't matter whether you get a Core 2 Duo or Athlon64 X2 processor. A far cry from previous gaming tests, where any AMD chip would absolutely obliterate whatever Intel had to offer.

This is how each CPU factored in the final 3dMark score:

As you can see, while the higher clocked Core 2 Duos were quite a bit faster than the E6400 and X2 4600+ in the CPU test, it's all tied up in the end. Expect to see this in the rest of the gaming tests.

Real World Games

Quality settings for each test were set to try to make the video card as little of a factor as possible, while keeping some realism. In other words, if you had our test systems, these are most likely the settings you'd use (trying to get an average 50-60 FPS or so).

The only game that felt any impact from the CPU was Far Cry, which shouldn't be a surprize to anyone. What might be surprizing is that the AMD processor was the one to take the hit! Not only has Intel caught up with AMD in gaming performance, they have bypassed them in a couple tests.

Next Page: (SYSMark 2004 SE)