Core i7 vs. Phenom II X2 vs. X4 scaling performance analysis
Unreal Tournament 3 (UT3)
Unreal Tournament 3 (UT3) is the fourth game in the Unreal Tournament series. UT3 is a first-person shooter and online multiplayer video game by Epic Games. Unreal Tournament 3 provides a good balance between image quality and performance, rendering complex scenes well even on lower-end PCs. Of course, on high-end graphics cards you can really turn up the detail. UT3 is primarily an online multiplayer title offering several game modes and it also includes an offline single-player game with a campaign.
For our tests, we used the very latest game patch for Unreal Tournament 3. The game doesn’t have a built-in benchmarking tool, so we used FRAPS and did a fly-by of a chosen level. Here we note that performance numbers reported are a bit higher than compared to in-game. The map we use is called “Containment” and it is one of the most demanding of the fly-bys. Our tests were run at resolutions of 2560 x 1600 and 1920 x 1200 with UT3’s in-game graphics options set to their maximum values.
One drawback of the way the UT3 engine is designed is that there is no support for anti-aliasing built in. We forced 8xAA for in each vendor’s control panel; 8xQ for Nvidia to match AMD Graphics’ 8xAA settings. We record a demo in the game and a set number of frames are saved in a file for playback. When playing back the demo, the game engine then renders the frames as quickly as possible, which is why you will often see it playing it back more quickly than you would actually play the game.
Here is Containment Demo, first at 2560×1600:
Now at 1920×1200:
Now we test at 1680×1050:
First of all, we notice that at our highest resolution pairing HD 5870 CrossFire with the Core i7-920, it scales with clockspeed, but paired with the Phenom II 955 X4, it does not; at lower resolutions, the X4 scales with clockspeed but not as dramatically. Our Phenom 550 X2 simply cannot keep up with our CrossFired HD 5870s at the highest resolution and they struggle with framerates at the lower resolutions once the CPU’s core speed drops below 3.6 GHz. Our single GPUs demonstrate much closer results with less performance difference between Core i7 920 and the dual-core Phenom although the Phenom dual-core really loses framerates when paired with a HD 5870 and underclocked; on the other hand, paired with a GTX 480, the dual-core Phenom II provides satisfactory framerates at all three speeds that we tested it at.
Flat-out amazing!!! I’ve never seen anything so epic like this. So, there was not any microstuttering in any of the above games, where the “measured” 40 fps appeared to look more like “perceived” 25 fps? I guess microstuttering is not noticeable if the measured fps is above 70-80, since half of this (45 fps) would still appear to be relatively smooth. Anything below 30 fps becomes really noticeable, so were there ever 40-50 fps instances with 2x 5870 CF that felt like 25fps or so? I’ll take your word for it, if you were actually watching 10,000 hours worth of benchmarking, ha (just kidding, don’t shoot my head off)!
Surprised there are not more comments. For a single video card it does look like a dual core is more than enough. Sure there are a few games that take advantage of four cores, but the fact remains they remain in the minority.
Bobert, I’ve been saying the same thing for months now.
Wow, very thorough and detailed article. It’s one thing to test CPU performance using a single video card, but it must take some brawn to do it for three different video configurations.
There’s so much data here to look at in so many ways. I suppose if you would have included an SLI setup we would then be able to determine how CPU speed affects SLI vs. Crossfire. If I’m looking at this data right, though, it seems Crossfire sees benefits from quad cores more than single video cards do.
Far Cry 2 seems to be a good example of this. Also Far Cry 2 shows interesting relationships between CPU and the GTX 480. The single HD 5870 doesn’t really react to CPU speed and cores the same way dual 5870s and the GTX 480 do. That’s pretty interesting.
So well done. If I only had one suggestion is that I would like to see GTA4 benched, mainly because I own it and good, thorough, and updated benchmarks of it are not easy to come by.:)
Concerning the Far Cry 2 numbers, despite being beaten with faster processors, the HD 5870 paired with the 2.6 dual core is actually outperforming the Crossfire and Nvidia setup. That’s what I find a bit interesting here.
AWESOME REVIEW.
This is EXACTLY what review websites ARE NOT putting out.
A non GPU-bottlenecked review showing how i7 really does have a significant gaming lead over Phenom II.
God you’d be surprised how many AMD fanboys still believe (and spread rumors) that Phenom II is plenty for 5870 crossfire. Psh. Plenty on today’s games maybe, but that is due to the PC gaming community being SNARED by the noob console community and their half a decade old setups.
Ok I’m ranting.
Two Thumbs!!
Raidur means it shows how Phenom II bottlenecks 5870 crossfire.
Everyone knows i7 is faster in games.
PS. I’m not Raidur.
PSS. I’m Raidur.
PSSS. Or am I?
Awesome review GJ.
Please let me know if you’re looking for a article writer for your
site. You have some really good articles and I believe I
would be a good asset. If you ever want to take some of the load off, I’d love to
write some material for your blog in exchange for a link back
to mine. Please shoot me an email if interested.
Thank you!