Does AM2's Performance Make Sense?
Assuming for a moment that the performance we're seeing here today is representative of what AMD will show off in 2 months, does it make sense? AMD has effectively doubled their memory bandwidth but they've seen virtually no increase in performance, other than in some very isolated situations.
If you'll remember back to the introduction of AMD's Revision E core, we did an article about how the new core brought support four new memory dividers allowing you to run at speeds up to DDR500 without overclocking your CPU or the rest of your system. In that article we looked at the overall performance benefit of DDR-500 over DDR-400 on a Socket-939 platform in a variety of situations. A recap of our performance results is below:
| Benchmark | Socket-939 (DDR-400) | Socket-939 (DDR-480) | % Advantage (DDR-480) |
| Multimedia Winstone 2004 | 41.9 | 42.7 | 2% |
| 3dsmax 6 | 2.78 | 2.80 | 1% |
| DivX 6.0 | 50.6 fps | 53.2 fps | 5% |
| WME9 | 4.22 fps | 4.28 fps | 1% |
| Quake 3 (10x7) | 121.9 fps | 127.2 fps | 4% |
| ScienceMark 2.0 (Bandwidth)* | 5378 MB/s | 5851 MB/s | 9% |
As you can see, given almost a 9% increase in memory bandwidth, we saw similarly small increases in overall performance. It would seem that the Athlon 64, at its current clock speeds, just simply isn't starved enough for memory bandwidth to benefit from an increase in bandwidth. You'll also see that the areas where faster DDR memory helped back then are pretty much the areas where DDR2-800 is showing gains today.
Based on our results from back then, if a 9% increase in memory bandwidth doesn't increase performance tremendously, then the 35% increase in bandwidth we see with DDR2-800 on AM2 shouldn't yield any more of a performance increase. Or simply put, yes, our AM2 performance numbers make sense.
Facebook
Twitter
RSS
107 Comments
View All Comments
AdamK47 3DS - Monday, April 10, 2006 - link
Conroe WILL perform better than AM2 no matter how much spin people try to put on it.bob661 - Monday, April 10, 2006 - link
How can you say this when there are exactly NO shipping Conroe parts? I THINK that Conroe will be competitive but even that opinion is speculation at best. YOU won't know shit about Conroe until it shows up at Newegg!Shintai - Monday, April 10, 2006 - link
If your logic applies, then he wont know anything about Conroe until he got it at home and working. So get over it, even the ES samples out in the wild kicks AMD so hard. The only question was if AM2 would bring extra performance to compete against Conroe, and it surely didn´t. Conroe prices also leaves AMD in the utter dust along with performance. 300$ Conroe E6600 chip or a 1200$ FX62? And the E6600 will be faster in most situations. You gotta be some extreme hardcore fanboi not to go Conroe.bob661 - Monday, April 10, 2006 - link
There's nothing to get over, asswipe. You nor he knows for sure how Conroe performs, period! You can fanboi me all you want. Facts are facts. When they ship and there are 3rd party benchmarks on 3rd party machines tested, then we'll all know for sure how they'll perform. Puff, puff, pass man, puff, puff pass.Shintai - Monday, April 10, 2006 - link
http://vic.expreview.com/read.php?1">http://vic.expreview.com/read.php?1http://vic.expreview.com/read.php?2">http://vic.expreview.com/read.php?2
http://vic.expreview.com/read.php?3">http://vic.expreview.com/read.php?3
http://vic.expreview.com/read.php?4">http://vic.expreview.com/read.php?4
Now cry me a river again and keep whining over something new.
AnnonymousCoward - Monday, April 10, 2006 - link
That's the crappiest website ever! I think a modem is hosting it. Plus it's retarded how the pictures shrink after they're loaded.Furen - Monday, April 10, 2006 - link
I wouldn't compare the pricing quite yet. AMD's AM2 pricing is for May 5th while Conroe's is for launch day... whenever that happens (and before you say June/July, Intel itself said that it would launch as close to the beginning of Q3 as possible but did not commit to an early Q3 launch).Another thing, I have yet to see an E6600 being tested in "most situations", so until I see so, I'll say that your assumption that this is true is a bit irresponsible and fanboyish. Especially so if you consider that neither of the two CPUs (AM2 K8s and Conroes) can be bought quite yet, so convincing someone that one is a better deal is a bit premature. Personally, I think that AMD is going to get its ass handed to it by Conroe but I wouldn't go our of my way to swear it.
redbone75 - Monday, April 10, 2006 - link
Wow. Only twenty posts until someone put up something about Conroe performance. In case you haven't been reading AM2 news or even read the article, AM2 is supposed to launch in June and here we are in April with a preview that, for the most part, is pretty disappointing for anyone that had high hopes for a Conroe challenger. This is just like when Intel migrated to DDR2: it wasn't really necessary but it will give AMD experience for when they can really use it. However, I'm thinking it won't take AMD as long to see more noticeable performance gains with DDR2 than Intel. Regarding Conroe, any way you call it the chip is going to kick some serious @$$, especially if Intel doesn't have any problems ramping up the clock speed. Also, Conroe is still several months away, so unlike AMD, Intel still has some time to tweak the chip for even more performance for its scheduled launch time (won't say date because there is none yet), so who is to say that the current performance claims are bogus. Even if they are now, which I seriously doubt, there just might be enough time for Intel to live up to the hype anyway.MrKaz - Monday, April 10, 2006 - link
I'm not sure,but I think anandtech tested it at 533Mhz again, or
the processor is locked at 533Mhz.
Why did anandtech do the test only at 800Mhz?
Why didn’t test 533Mhz and 667Mhz DDR2 modules?
Because looking at those numbers:
-DDR2 533 will achive less bandwidth than DDR400?
-The latency of DDR2 is lower than DDR1?!?!
-Is the processor already full, so doesn’t need more bandwidth, and only at (theorical) 4GHz and beyond will use it?
defter - Monday, April 10, 2006 - link
At higher speeds yes. Of course 3-4-3 @ 400MHz (DDR2-800) will offer lower latency than 2-2-2 @ 200MHz (DDR1-400).