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
mino - Tuesday, May 23, 2006 - link
2 options:1) Quad-core K8 (on 65nm)
2) High-speed 65nm DC's(improbable)
BTW what I understand FX-64 is on the way in a few months(july-august). Seems rev. F cores could handle 3.0, just 125W TDP may be the issue.
peternelson - Tuesday, May 23, 2006 - link
Well, I don't think it's a QUAD CORE K8 (aka "Deerhound") because that is not due until late 2007.
And dualcore K8L is not until 1H/2007.
We need to choose something happening THIS year.
mino - Wednesday, May 24, 2006 - link
Actually AMD can made Quad-core CPU's even on 90nm if they need to. The core will be huge, yields poor but IMHO 2.2G Quad at 90nm is possible within 125W TDP.Also AFAIK AMD has delayed 65nm at least for a quarter intentionally since what they need now is capacity on 90nm. They could not afford any (even short-term) production reduction at this moment. Provided in 3Q/06 FAB 36 is up and running at 10k starts the could afford to dedicate some of them for some high-end opterons and FX's.
Furen - Wednesday, May 24, 2006 - link
http://img.clubic.com/photo/00119525.jpg">http://img.clubic.com/photo/00119525.jpgLook at that and tell me how you can possibly fit twice that (90nm dual-core) in one package. Dual-core CPUs are huge to begin with, doubling the number of cores would probably require a pretty big drop in L2 sizes (think 256KB per core...). AMD still is production limited and designing a quad-core chip without going to 65nm would pretty much doom it to being a VERY low-volume part. Heck, Intel's Conroe is huge as well, it's just on a smaller process (the 160sq. mm die size would correspond to something like 300+sq. mm on the 90nm process).
jones377 - Tuesday, May 23, 2006 - link
It's called Socket FGriswold - Tuesday, May 23, 2006 - link
I dont think so. Socket F isnt really a "secret" nor a stopgap solution.peternelson - Tuesday, May 23, 2006 - link
I think we hear more about socket F in June and it launches July.But that's not what this is alluding to.
There was an announcement of a roadmap change from Q1/2007 to DECEMBER 2006.
If I remember right it was two AM2 processors on 65 nanometre process.
jones377 - Tuesday, May 23, 2006 - link
Perhaps not, but it's coming out at around that timeframe. Anything else and we would have gotten wind of it long ago.mlittl3 - Tuesday, May 23, 2006 - link
A couple of things before I give my guess about the stopgap solution...1) K8L as state above WILL HAVE microarchitectural improvements. This has been all over the internet.
2) AMD's processor pricing page states that the X2 5000+ and FX-62 will be available for both 939 and AM2. I don't know if they messed up but if not, it looks like 939 users can upgrade yet again.
Okay, here's my guess for the stopgap solution...drum roll...L3 cache. I think AMD will release a 2.8 revised FX-62 with L3 cache or an ahead of schedule 3.0 GHz FX-64 with L3 cache. Just my guess.
AllYourBaseAreBelong2Us - Tuesday, May 23, 2006 - link
The stopgap solution is the 65nm process that will allow AMD to ramp up the speed a bit more and get better TDP ratings.