Spring IDF 2006 Conroe Preview: Intel Regains the Performance Crown
by Anand Lal Shimpi on March 7, 2006 3:58 PM EST- Posted in
- Trade Shows
Gaming Performance
The one area where AMD has been the clear leader for years has been in gaming performance - Conroe changes everything.
Updated: In Don MacDonald's keynote he also provided us with another reference point for Conroe's performance, this time under Call of Duty 2. We have no idea what settings they ran at but the results we saw were Conroe at 111 fps and a Pentium Extreme Edition 3.73GHz scoring 90 fps. But the most interesting gaming tests are below:
First off we've got Quake 4 running the 1.0.5.0 patch at 1280 x 1024 with High Quality settings. The only demo available was Intel's own demo but nothing looked out of the ordinary with the recording. We tested with both r_useSMP enabled and disabled, first the SMP disabled numbers. Updated: The Quake 4 scores have been updated as mentioned in our follow-up article.
With SMP disabled, Conroe holds a 25% performance advantage over the 2.8GHz Athlon 64 X2. Enabling SMP provides a similar 24% performance advantage.
Next up is a Half Life 2 Lost Coast demo, once more an Intel supplied demo but there's only so much you can do to a demo recording to make it favor one CPU maker over another:
Conroe's performance advantage extends to 31% under Half Life 2, talk about a complete role reversal here.
We finish off this page with Unreal Tournament 2004 and a 20% performance advantage for Conroe.
Facebook
Twitter
RSS
220 Comments
View All Comments
AndreasM - Wednesday, March 8, 2006 - link
I agree, the EE will be at least a thousand times faster... :)
But I wouldn't be so hasty to count AMD out just yet, they'd have to be pretty dumb to not prepare for the day when Intel comes out with a better architecture. The AM2 cpus that were tested were of a very early revision, final performance will likely be much higher. Anyways, excellent news, hopefully the Athlon X2 prices will drop to more reasonable levels in the near future. :)
photoguy99 - Wednesday, March 8, 2006 - link
I don't think AMD is dumb, in fact they've done an amamzing job catching a giant sleeping and capitalizing on it with great CPU designs. Also agree that AMD is obviously working like crazy to make K9 as great as possile.The problem is it's just too big of a leap to make in a race where deep pockets really do give an advantage.
Also while power effieciency has become more important to becoming a performance leader, remember Intel has actually been ahead of AMD in power efficiency since the first Pentium M - they just haven't been able to move it to the desktop until now.
Yes, it's early to speculate - but at this early date my speculation is a reversal in stock prices which I'm predicting on my blog so it's http://spaces.msn.com/techrelease/blog/cns!59F693F...">http://spaces.msn.com/techrelease/blog/cns!59F693F...down for the record.
Avalon - Tuesday, March 7, 2006 - link
For those of you doubting the validity of the benchmarks, Anand ran the FEAR in game demo that is supplied with the game, not Intel. You know what the best part is? They benched FEAR, arguably one of the most *GPU* limited games out there, at 12x10, and gained ~30% performance gains with just a *CPU* switch. Incredible!I was going to be jumping to an X2 3800+ 35w and AM2 setup when that came out in a few months, but forget that. I am completely sold on Conroe. I haven't used an Intel since...1998...jeesh. Welcome back blue.
Sunrise089 - Tuesday, March 7, 2006 - link
I don't doubt that the results are great for Intel, but people shouldn't expect these kinds of gains when gaming. Look at what Intel did - they supplied a fast processor, so no one could claim AMD wasn't able to show their best. Then they supplied a very fast GPU pair, putting the bottleneck on the CPU. They then ran it at a resolution no one in their right mind would use with this hardware. Anyone who can spent $1,000 on video cards and another $1,000 on a CPU will not use a $350 1280x1024 LCD. They will be running on a 1920x1200 Dell2405 or the like, where those X1900s won't be able to push those kind of frame-rates. In that sort of a configuration, Intel would still win, but rather than 120fps versus 180fps type of scores, it will be more like 50fps versus 55fps, unless the game is REALLY CPU limited. Not many games are at the kind of resolutions people with $4000 PCs tend to game at.Leper Messiah - Tuesday, March 7, 2006 - link
Seriously, if these benches are true, My next computer will have a conroe. It remains to be seen however...Diasper - Tuesday, March 7, 2006 - link
Obviously there's a bit of contention here because the setup was controlled by Intel BUT what is possible is to set up a similiar testbed to see if the figures are in the right approximate ballpark. Tests you could run would be both on FEAR and encoding (assuming you have the same file).I would suggest Anandtech do this just because not many people have a FX-60 or so to overclock and a X1900 Crossfire setup. Besides following up on it would be good for this website and its reputation.
StriderGT - Tuesday, March 7, 2006 - link
Excellent point, in order for one to trust intel's results they should be REPRODUCABLE at least as far as the athlon64 X2 is concerned. Anand could and SHOULD provide us with this valuable insight!Questar - Tuesday, March 7, 2006 - link
Ummm...You realize NONE of Anand's tests have ever been reproducable?StriderGT - Tuesday, March 7, 2006 - link
I do not know whether I should bother answering to someone who posts like an intel PR representative....Do you understand why Anand reviews have detailed CONFIGURATION data before the results???
Use your brain plz
PS Before you start ranting about the impossible exact same configuration of intel's test down to the HDD bla bla read the original post about the ballpark. And remember this is a HW enthusiasts site, there are lots of people around here who know what they are talking about....
Questar - Tuesday, March 7, 2006 - link
Okay, show me one web site that has ever independently reproduced Anand's results.To the best of my knowlege, none of the files that Anand uses for benchmarking are available to the public.
There may be lots of people around here that know what they are talking about. Think, and someday you may be one of them.