AMD Socket-AM2: Same Performance, Faster Memory, Lower Power
by Anand Lal Shimpi on May 23, 2006 12:14 PM EST- Posted in
- CPUs
The Odd Multiplier Issue
Another item that was working against the Athlon 64 X2 5000+ on the previous page was the fact that it used an odd clock multiplier, in this case 13.0, in order to achieve its 2.6GHz clock speed. The problem with odd clock multipliers on AM2 CPUs is that the memory controller actually runs at DDR2-742 instead of DDR2-800. AM2 CPUs with even clock multipliers can run at DDR2-800 without any problems, and the reason why is pretty simple.
Below is the equation for calculating the memory speed of any Athlon 64 processor:
Reference Clock * Clock Multiplier = CPU Frequency
CPU Frequency / Memory Divisor = Memory Frequency
AMD only supports integer memory divisors, but let's start out by looking at how an AM2 CPU with an even clock multiplier fits the equation. For example, an Athlon 64 X2 4800+ runs at 2.4GHz and supports DDR2-800.
200MHz Reference Clock * 12x Clock Multiplier = 2400MHz CPU Frequency
2400MHz CPU Frequency / 6 = 400MHz DDR2-800 Memory Frequency
No problems, right? Now let's see how an odd clock multiplier changes things:
200MHz Reference Clock * 13x Clock Muliplier = 2600MHz CPU Frequency
2600MHz CPU Frequency / 6 = 433MHz DDR2-866 Memory Frequency
2600MHz CPU Frequency / 7 = 371MHz DDR2-742 Memory Frequency
See a problem? Because we can only use integer memory dividers, the only options for memory speed on a CPU with an odd clock multiplier are DDR2-866 or DDR2-742. Since AMD can't run above DDR2-800 spec, the only option is to underclock the memory to DDR2-742. This wasn't a problem on Socket-939 CPUs because DDR-400 ran at a 200MHz frequency, which you could always obtain by dividing the CPU clock frequency by an integer (since AMD never supported half multipliers). In fact, you simply used the same integer as the CPU multiplier. With DDR2-800, you need a 400MHz clock frequency, which you can only generate if you have an even CPU clock multiplier.
The problem gets even more complicated when you take into account the fact that Semprons and single-core Athlon 64s only support DDR2-667, which also has a similar issue.
While we haven't seen any significant downside to only running at DDR2-742 vs. DDR2-800, it is something to keep in mind when deciding what CPU to purchase. If you want your memory controller running at DDR2-800, you may want to stay away from the odd clock multiplier CPUs (X2 5000+, 4400+ and 4200+).
Facebook
Twitter
RSS
83 Comments
View All Comments
Slappi - Thursday, May 25, 2006 - link
That is the real question.Very biased these last few months.
I sure hope Conroe can cook dinner and clean my house because if it can't someone has some explaining to do.
lewisc - Thursday, May 25, 2006 - link
How was that review at all biased? AM2 showed very very small improvements over socket 939, Anand said so. Is it biased because the result was not what you wanted? How you could possibly suggest buying a a new platform that has hardly any improvement over a predecessor is beyond me.Slappi - Thursday, May 25, 2006 - link
Just all his talk about Intel the last few months has been really biased. Not necessarily this article.Just my opinion and I really like this site it just seems like someone is being taken care of.
I could be wrong.
clnee55 - Friday, May 26, 2006 - link
I agree in the last few months, AMD has shown that it doesn't have anything ready to compete with Conroe. I certainly can trust Anand's analysis. Your conspiracy theory is full of it.By the way, just how much AMD stock do you own?
EdisonStarfire - Thursday, May 25, 2006 - link
I've owned AMD systems since 1998 starting with an Athlon 600 OEM. I've built several other AMD systems since then. Sure, there is a slight chance Intel had some influence on their test systems anand tested but from seeing other pre-release samples around the web I think its just a case of Intel finally waking up and building a good cpu. I hope AMD has a good answer but if they don't and fooled themselves into thinking Intel didn't have the resources or need to build something (like alot of fanboys do) then they were kidding themselves badly. If the Core 2 Duo chips are the best out when its time to dump my X2 4400 then thats what I will be buying. I know AMD is limited in resources but the Dothan should have been a sign of what was coming and made some revisions with the AM2 release. Let's hope the deerhound cores improvements add about 20% IPC so can keep some good competition going between the two companies.in short... I don't think Anand is being biased about anything. Just my 2 cents.
Thatguy97 - Friday, May 1, 2015 - link
well it sure did and amds dyingThatguy97 - Tuesday, December 27, 2016 - link
Ayyyyy things looking upThatguy97 - Sunday, June 28, 2020 - link
Ayyy AMD is in the lead nowpeternelson - Wednesday, May 24, 2006 - link
I am interested in the changes from 939 to AM2/940 and opteron/940 and SocketF/1207
I would like detailed PINOUTS for these.
eg how many pins are GND, how many power / core power, how many ddr, how many ddr2, how many hypertransport links.
Ideally full pinout not just summary by group function.
Is this information available anywhere or would I have to/my company have to sign an NDA with AMD to obtain it?
ultraCODE - Wednesday, May 24, 2006 - link
Have anyone managed to benchmark new AM2 platform with RightMark RMMA? It shows the real peak speed (I don't trust crappy Sandra) for mem. read/write. Any results highly appreciated. Thanks in advance!Best wishes,
uC