Affordable Dual Core from AMD: Athlon 64 X2 3800+
by Anand Lal Shimpi on August 1, 2005 9:36 AM EST- Posted in
- CPUs
Power Comparison: Manchester vs. Toledo
In our first review of the Athlon 64 X2, we were astounded by the fact that the fastest Athlon 64 X2, thanks to its cool running 90nm process, consumed less power than any single core Pentium 4 processor, not to mention all of the dual core models.We also noted that a dual core Athlon 64 X2 processor used less power than a single core 130nm Athlon 64, once again a testament to AMD's transition to 90nm.
This time around, we're interested in the power consumption benefits of the new Manchester core. AMD says the core drops the maximum power consumption from 110W down to 89W, but what is that in the real world?
In order to find out, we performed one simple test; we clocked an Athlon 64 X2 4200+ based on the old Toledo core at 2.0GHz, the same clock speed as the X2 3800+, and measured the total power consumption of the system. We then swapped out the Toledo based X2 for a new Manchester based X2 to see, clock for clock, what the tangible decrease in power consumption was.
Remember, we're only looking at total system power consumption - obviously CPU power consumption will be a lot lower, but with identical system specifications, the CPU's impact on power consumption should be the major variable that we're measuring here.
Clock for clock, there's no tangible reduction in power consumption courtesy of the new Manchester core. But given how cool the Toledo based Athlon 64 X2s were already running, we're not too disappointed that there isn't more to talk about here. After all, the biggest advantage of the Manchester core is the cost reduction...
109 Comments
View All Comments
masher - Tuesday, August 2, 2005 - link
> "It is the core itself that increases the cost."True enough-- but a die twice as large shouldn't be over twice the cost...unless your defect rate is pretty high. With a high defect rate, a double-sized die doesn't mean half the yield..it means 1/3 or less.
Intel's dual-core dies are twice as large as their single cores...AMDs are a bit smaller due to the already-embedded HT glue. If the defect rates were anywhere close, then AMD should be able to sell dual-core chips for a smaller premium than Intel. Since they aren't (which likely means can't), we must assume they're still having a fairly high defect rate.
SDA - Tuesday, August 2, 2005 - link
They could also just be charging a premium for the hot new thing. I suspect some of it has to do with AMD wanting to be known as high-end.. when people see Athlons in budget PCs all the time, Athlon becomes associated with budget.Defect rate works too, though. I'm just throwing out other possibilities. Either way, I think we can agree that the CPUs don't cost more because of slick interconnect technology.
krisia - Tuesday, August 2, 2005 - link
Hmmm, hasn't AMD said they've planned for dual core all along and already had tech in their single core chips to support it? So, now they decide to charge for the tech? The thing anand fails to mention is that 40% more money for 10-20% performance gain is not a "clear choice". The choice is much less clear in fact, if you consider you can't buy a X2 3800 yet...SDA - Tuesday, August 2, 2005 - link
40%? The X2 3800+ is supposed to cost $354, but the D 830 is $318 at NewEgg. That looks like a 10% price increase for a 10-20% performance increase AND a cooler processor. Seems like a fairly easy decision to me.If you are suggesting that the inability to perform basic arithmetic is a reason to get the Pentium D, I concur. ;)
krisia - Tuesday, August 2, 2005 - link
If you did the math, then you'd know I was referring to the entry price for the D820. Which is the value entry into dual core? No?SDA - Tuesday, August 2, 2005 - link
The AT review deals with the D 830, not the D 820. You used the numbers from the review and made your remark in the comments section of said review, and yet you feel it's obvious that you're referring to an unreviewed product even if you don't explicitly state such?Let's leave that behind us, though. There is a very simple flaw in your comparison: you're comparing SYSTEM performance differences to PROCESSOR price differences. How about comparing the build prices of an X2 3800+ to a comparably equipped (same amount of memory, same non-core components, all of that) D 820 system, then looking at the performance difference?
If you're too lazy to do the math (and in fairness, it's a PITA to add up components just for the sake of an argument) I'll just explain it simply: it's an 8-15% price boost for 10-20% better performance and a considerably cooler-running processor (and thus, if you plan the system properly, a quieter system).
Before you get defensive, I'm not trying to say that your 820 was a poor choice. I'm certain that you made the perfect choice for your situation. However, it is clear that the 3800+ is a good value in its intended niche.
krisia - Tuesday, August 2, 2005 - link
Ok, the OP didn't reference the anandtech article, only the Pentium D lineup.It's just fun sometimes to do the unconventional or unpopular. :)
SDA - Tuesday, August 2, 2005 - link
I bet it is. Just try to think everything out ahead of time so you don't end up unable to counter the last argument against your "unconventional or unpopular" view.Amplifier - Tuesday, August 2, 2005 - link
First!Hacp - Tuesday, August 2, 2005 - link
I just read toms article and it had alot of synthetic benchmarks and very few real world benchmarks............... Except the ones that favor Intel........