Conroe Performance Preview Follow-Up
by Anand Lal Shimpi on March 9, 2006 9:30 AM EST- Posted in
- Trade Shows
The Benchmark Issue
Although we mentioned that there’s not much you can do to make a timedemo really favor one CPU architecture over another, you all demanded that we try with one of our demos. We put our Quake 4 demo file on a USB drive and copied it over to the Conroe and Athlon 64 FX-60 systems that Intel had setup. Note that the version of Quake 4 installed was 1.0.5.0 which is newer than what we test with in our CPU reviews, so you can’t directly compare the numbers to previous AnandTech results but at least we’d be able to see if Intel’s Quake 4 demo was somehow giving Conroe the unfair advantage.
We re-ran Intel’s Quake 4 demo to confirm our initial results. Much to our surprise, we actually short-changed Intel the first time around. We noted that Conroe held a 28% performance advantage over the 2.8GHz Athlon 64 FX-60 with SMP disabled, but with it enabled the performance advantage shrunk to 15%. We re-tested and confirmed our suspicions that Conroe’s Quake 4 performance with SMP enabled was more in line at a 24% advantage:
But what we’re really interested in is how Conroe performed in the very same Quake 4 demo that has been favoring AMD processors in all of our CPU reviews. We loaded up our Quake 4 demo and had at it:
With SMP enabled we see that Conroe holds an even larger 31% performance advantage and with it disabled, the unreleased CPU was 29% faster. If anything, Intel’s own demo was a little more conservative on Conroe and definitely not optimized to make AMD look bad.
Facebook
Twitter
RSS
96 Comments
View All Comments
RichUK - Thursday, March 9, 2006 - link
Good read good read. Thanks for the honesty and accuracy on the updates.MrKaz - Thursday, March 9, 2006 - link
Intel road map says Q4. Not Q3.And 6 months from now is Q4 not Q3.
AMD new K8 will boast performance by 10%. If .65nm boost the frequency of new K8 since .13 » .09 doesn’t seem to do pretty much on that aspect.
Then we will have some good war.
Don’t forget that this processor when working in single core have a huge L2 (4MB) vs the only 1MB from AMD. That boost the performance a lot in many applications. So the difference in Quake4, ... is amazing but not that much.
MrKaz - Thursday, March 9, 2006 - link
Sorry i mean that 6 months from now is still Q3, but intel road map says Q4.Von Matrices - Thursday, March 9, 2006 - link
Didn't that CPU have 2MB L2 and not 4MB L2?Anemone - Thursday, March 9, 2006 - link
If 20% improvement on Athlon the P4 is officially last, last, last years news, and a dog./bye P4
Anemone - Thursday, March 9, 2006 - link
You are really top rate reviewers. Check and recheck, and always forthright about things that needed correcting. Kudos!PrinceGaz - Thursday, March 9, 2006 - link
Thanks for this follow-up article, it covers pretty much every question that was raised except one. In the original article you mention "the ATI graphics driver was modified to recognize the Conroe CPU but that driver was loaded on both AMD and Intel systems". Have you any information on why it needed modifying and what was changed, and whether the changes would have any effect on the AMD system (either positive or negative).Chadder007 - Thursday, March 9, 2006 - link
I think its because they needed to change the drivers to recognize the dual core capabilities of the Conroe, since they are multithreaded capable now from ATI.redbone75 - Thursday, March 9, 2006 - link
One thing I haven't really noticed many people talking about in all of this Conroe stuff is the price to performance ratio Conroe brings. If it were released now, Conroe would offer a significant increase in performance over AMD's top offering at half the price ($540? for Conroe 2.66 and $1000+ for an FX60 right now). Sure, AMD will reduce the prices of it's processors once Intel launches the Core line and AM2 is ramping up, but I doubt it will be significant enough to entice unbiased buyers away from Conroe if it is the superior performing chip. I personally have favored Intel's chips over AMD's simply because I'm not a heavy gamer and didn't need the insane frame rates, and before dual core chips arrived I've always found my computing experience to be a little smoother b/c of hyperthreading (I've built several AMD systems for clients and friends). With the advent of dual core chips, I was eventually going to build a new system around an X2, but then when looking at the great overclockability of the Presler core and the lower price I kinda balked at that switch. Maybe others will do the same with AMD vs. Conroe: AMD might lower their prices such that buyers will go for it and simply overclock to close the performance deficit. But, then again we did just see an overclocked FX60 get bested by Conroe, at least according to current data (had to throw that in there lest the might of the fanboys smote me where I sit). Oh, well, I could be wrong, but that's my human right:-)dysonlu - Sunday, March 12, 2006 - link
Intel will charge a premium for it. You can mark my word. It's simply naive to expect the new chip to offer both the best performance AND the best value.Boy, people can so easily get carried away, being too optimistic and enthusiastic.