Slashdot Mirror
AMD 90nm Evaluated
muyuubyou writes "The Tech Report has measured the new 90nm A64 3500+ against its 130nm counterpart and a Pentium 4 3.6Ghz 90nm.
AMD looks way ahead in the 90nm process especially when it comes to power consumption.
Note these are consumptions for the entire system including GeForce 6800 GTs and hefty PSUs. RTFineShortArticle for more detail on the configuration.
Leaving the PC on overnight is probably not a good idea with these new Pentium 4s."
That's impressive. Of course, since it's total system wattage, it'd be nice to have some information about disk usage over the period of time, etc.
I like, though, that the 130nm Athlon 64 is still better than the 90nm P4. It might just be time to buy another desktop.
It' snot going to make THAT much of a difference on your electric bill.
Now what I want to see is an analysis of the possible benefits to notebooks, specifically in extending battery life. Intel's Centrino seems to be doing fairly well in that department, but where is AMD's response?
There's a Mercedes gap too. I want one and can't afford one, but it's not government's job to do anything about it.
With every computing consuming more and more power, its looking like we will need a wind turbine or solar PV array for anyone to run a decent sized network of computers at home.
Anyone currently doing this? I'm thinking of installing a turbine, but unsure of where to start out.
IntechHosting - Free domain, 2GB, PHP, £4.95/$8.95
Can someone elighten me on this? Is there a reason why the SpeedStep and other power-saving methods that are used in most laptops can't be adapted to desktop systems?
The old joke is that all CPUs sleep at the same speed, but after seeing the power consumption graph on this site, it's obvious that "power-hungry CPU" doesn't just mean high heat during gaming. This suckers are hungry even while doing nothing at all
--
Free gmail invites
They found that the Prescott P4, with its emphasis on Mhz, puts out a lot of heat in spite of its 90 nm architecture. The new 90 nm AMD 64 is cooler and uses less energy than the 130 nm version. Great.
But what about performance? The new 90 nm Pentium M processors, the one with the funky names, aren't doing as well in terms of performance scalability because of electron leakage issues. Any such concerns here? How fast can the 90 nm Athlon 64 core go before it dies?
A NYC lawyer blogs. http://www.chuangblog.com/
As the proud owner of an old-school Duron, my computer isn't a problem. However, living in a bachelor pad which happens to be filled with geeks, we have a cable modem.
This makes our house faster than our friends' houses. So their computers migrate there also. And the bastards never remember to turn them off...
Having five or six power-hungry gaming systems around explains much about our recent power bills.
"We have to go forth and crush every world view that doesn't believe in tolerance and free speech." - David Brin
now I won't need to heat my house in the winter.
Buy an Intel Prescott based system if you live in the Artic Circle ...
Looking at the data in the article, would I be mad in assuming that a 90nm 3500+ uses around 23W in idle mode?
Assuming power supply is 75% efficient:
112W * 0.75 = 84W getting to system
179W * 0.75 = 134W (130nm under load, near TDP of 89W, let's assume 84W)
134W - 84W = 58W Mobo, Gfx, IDE, etc power consumption
84W - 58W = 26W
26W * 0.9 (motherboard VRM efficiency) = 23W
I suppose that system power usage also drops in idle mode though as well.
Yes, these figures are extremely dodgy and vague and aren't worth much more than the speculation they are. It looks like the 3.4GHz P4 uses over 100W under load though - that is shockingly high.
Well, in my book, power consumption is not a huge issue if there is proper cooling. Under normal and even high use conditions, the unit is designed to take the heat, and my server room needs a bit more heat anyway. Why shouldn't I leave it on? My units have good cooling, and since I run my boxes under normal server configuration, i'M not "overclocking".... Heat? No issue.
"Who are in control, they are not in control of anything - they don't even control themselves!" - Glen Beck
It used to be that I thought Intel and MS were in bed together (well they were), now I'm beginning to think Linus has signed on - Linux and KDE need all the processor power they can get -- my apologies to the Yoper crowd -- I know they can't even see the boot screen on a 33 Mhz machine.
Pull Start.
vk.
151Watts at iddle. No I'm not a tool, maybe you are?
Just the editors putting their comments in the story/headline. Nothing new.
Let's not forget that 2 light bulbs take the same amount of energy. Ever fall asleep with the television on?
I believe we're still at 16c/kwh in southern California.
So, that's eight cents an hour.
Now let's say you and your wife each have one. Fuck, that's nuts. And the reality is that I use three PCs by myself. Our house has six. There's no way we can upgrade to something like this.
The ambient temperature in his office was 85 degrees F? I'm breaking a sweat at 72F. When the A/C turns off in our office over the weekend the ambient climbs to about 85 and all of my servers fans are on overdrive. I wonder if that had anything to do with the power consumption in this test, I'm curious to see what the diference is at a more normal operating temperature, say 69 degrees F.
(B) + (D) + (B) + (D) = (K) + (&)
they'd bill this as a "feature." Buy the processor and we'll bundle the radiator for free. Remember, supplies are limited, so hurry before winter approaches.
A friend of mine, an overclocking expert (inventor of the "Goldfinger devices" if anyone remembers those) said that the new shrunk cores overclock to around 3GHz if you can get your FSB high enough (though this won't be an issue with the FX chips, which aren't clock-locked).
To those paying attention, 2.2GHz in an Athlon64 can generally outperform a 3.4GHz PentiumIV, so this is a big deal.
Computer Science is no more about computers than astronomy is about telescopes. --E. W. Dijkstra
Very nice...Intel had some serious competition. Im interested to see how they will respond.
What's that the power Consumtion vs. Performance difference between Amds and Intels equivalent?
Could Amd become the chouce of server administrators?
The ambient temperature in my office was about 85F/29C,
The *ambient* temp was 85F? Lord, I'd hate to think how much I'd be sweating in an 85 degree office with limited air movement...
This magazine writer works at a place that can't afford air conditioning? Or does he have so many computers in there that he's just cooking himself voluntarily?!?
What *does* roast-geek smell like?
the relative difference between the 90nm processors (defined as the difference divided by the average) in power consumptions is huge, and pretty consistent: 30% at idle, and then 43%, 45% and 44% for the other tests. These are huge numbers !
Turn off the monitor numbskull! Even if the computer doesn't run "sleep mode" its using much less than that. A couple of 100 watt light bulbs will cost more to run. If you want to save electricity run the hairdryer less, or any appliance that's MEANT to create heat.
151W (idle) * 12 hours * 360 days * 15c/unit = $100 a year extra on your electricity bill BEFORE you factor in the power used in your A/C to remove that heat.
If you are nice and do Folding or SETI or RC72 or whatever it is now, then you're looking at $150 at least.
If you are in an office, you can see how the costs could rapidly ramp up!
That link is to a 40K 3DMark'01 run. Here's the setup at 3.6GHz.
Belief is the currency of delusion.
I get it now.
It was Intel. They're the ones. Bush is owned by Intel. Huh.
How about this?
Excellent. Just plain excellent. So, who's going P4 hunting? I'm bringing my Winchester... are you? :D
One of the 187.
Intel was simply too arrogant to recognize what the market wanted. AMD is now smoking them, caught Intel with their pants down!
My company has 30 PCs, all of them running AMD. I will never buy Intel again!
The P4 system he was running was running at about 150 watts at idle.
Now, if you are running an A/C unit then you will not only have to consider the 150W your computer is using, but also the power that your A/C is using to fight the heat that it produces.
100% of the power used in the PC becomes heat (I think). So that is 150 W of heat. Your A/C, however is not 100% efficient. I really have no idea what the numbers are there. But it can't be more than 100% efficient so that is another 150 Watts (at least)
So your 150W computer is costing you 300W at the least.
Now, if you on the other hand live up north, then it looks much better. The heat produced will actually help your heating system, so that it doesn't have to run as much. My physics knowledge is a bit rusty, but I think you can say that if your heating system is based on electricity then it will cost you nothing extra to run your PC.
Please let me know if/where I'm wrong.
The Internet is full. Go Away!!!
The ambient temperature in my office was about 85F/29C
If the ambient temperature in my office were that high I'd be looking furiously for a lower-power chip, too.
"Provided by the management for your protection."
andrew@twisted:~$ grep rate /proc/acpi/battery/BAT0/state
present rate: 19983 mW
Hooray for laptops! The absolute low-end (not sleeping) load for this machine seems to be about 12W; I don't think I've seen it go over 35.
and of the 151 watts at idle, how many are directly responsible to the idle cpu? How many are responsible for a leaky PS? How many are responsible for every other component in that pc? To say say not to leave it in is obserd, NO one build a SERVER with a 90mm P4 or Zeon. Gimme a break Chris
The problem is, it doesn't use 100 watts more than AMD. The difference at idle is 40 watts.
The 6800GT in their test-bed sucks more power than any CPU they're testing.
And who knows how the various motherboards being tested are affecting the measurements. They aren't even from the same maker (Asus vs Abit). Odd that they take a top tier manufacturer for the AMD tests (Asus), and a manufacturer known for shit (Abit) for the Intel.
Not only that, they have the intel running DDR2 533 vs DDR 400 on the AMD - the memory alone counts for A LOT of the power usage, especially in the mpeg encoding tests.
The AMD rigs use an AGP card, the Intel rigs PCI-E. How does the faster Intel bus affect power usage?
The AMD probably does use less power. I just hate lies and horseshit motivated by some hardon people have for the "underdog".
What was preventing them from taking some accurate measurements?
I don't need no instructions to know how to rock!!!!
The PC is not 100% efficient in turning the electricity into heat. A portion of that energy is actually used to knock electrons around inside the unit.
Recently, I took some "at-the-wall" measurements of various systems in my computing room. My router is a dual-CPU system, using Pentium 133's. I always thought I was probably being wasteful in the electrical department, but when I measured it, the entire machine, under load, only drew 47 watts of power. I was pretty surprised.
My file server, a P3/650 with 4x120 gig drives and a 3ware card (running SETI) drew 85 watts. And my primary machine, under full gaming load, drew 270+ watts from the wall *without* a monitor. Yikes.
steve
Oh, you're not stuck, you're just unable to let go of the onion rings.
Not intending to flame here, but it came out that way. It sounds like your problem is that you're a pussy. Lay down the law. Tell them to stop leeching your cable. Next time they leave them on all night, be sure to install some nasty malware and unplug their computers, and tell them to stop bringing them to your house to leech your bandwidth. or help pay your power bills.
steve
Oh, you're not stuck, you're just unable to let go of the onion rings.
I used to think that, but going back over my thermo I've realized that you can get more than 100% efficiency out of a heater. It's true that heat from computers costs you less in the winter (since it helps then and hurts during the summer), but modern heating systems are more efficient than that analysis indicates ... or so I think. I could be wrong.
:)
The key is the phrase "heat pump".
Modern heat pumps, I believe, are nothing but refrigerators run backwards. For a simple analysis, consider your kitchen freezer: let's make up some numbers and say that it removes heat at a rate of 200 watts from the inside. Now, that heat has to wind up on the outside, so you wind up with 200 watts of heat being pushed outside.
This is impossible, of course: it takes extra energy to force heat to flow "uphill". Let's say the freezer has to spend 150 watts to run the compressor and the other gadgetry required to make those 200 watts of heat flow from cool to warm. All that energy eventually turns into heat, too, and you may as well push it to the outside.
So, you're burning 150 watts of electricity, removing 200 watts of heat from the fridge, and throwing those 200 watts of heat *plus* the 150 that your compressor generated into the ambient air. This is why freezers are so hot in the rear!
Now, consider a freezer run backwards, where the "cold end" is the outside air and the "ambient end" is the thing you're trying to heat. Poof, you put 150 watts of power in, and you get 350 watts of heat. We're not violating conservation of energy, of course, since the air around the heat pump on the outside has *lost* 200 watts of heat.
I think this is why we use electric heat at all. You might say that burning coal or natural gas to create power and then using that power to heat homes has an extra, inefficient conversion step in there -- since you could just burn the coal or gas.
But it's hard to make a natural-gas powered heat pump. All you can do with the natural gas in your home, really, is burn it and blow the heat inside. That's 100 watts of heat for every 100 watt-equivalents of gas burned. But, with a heat pump, you can get 80 watts of electricity out of those 100 watt-equivalents of gas, then use those 80 watts to run a heat pump--which will give you more than 100 watts of heat.
I think, anyway.
Just as an FYI, I've had a few durons, and they have tended to be among the more power-hungry and hot systems I've run.
Durons really aren't all that efficient... not as powerful in output as compared to an Athlon, sure, but that doesn't mean that less output doesn't mean input is generally lower (just less efficient).
You are looking at the heat pump wrong.
But it can't be more than 100% efficient so that is another 150 Watts (at least)
In theory the heat pump might be more than 100% efficient, the way you are looking at it.
I might create a heat pump that only uses 5 watts for every 10 watts of heat it moves. Think of something like water cooling, which in effect is a sort of heat pump. You might spend 10 watts moving water around which is carrying 70 watts of heat from the CPU to the radiator... etc.
Anyway, your point is correct, you just have to be careful talking about percentage efficiencies with heat pumps.
I've had enough abrasive sigs. Kittens are cute and fuzzy.
I believe most A/C units or heat pumps are capable of rejecting many kW of input heat load for every kW of power required by the refrigerant compressor.
[b.belong('us') for b in bases if b.owner() == 'you']
The one place where your figures aren't quite right is in the air conditioning department. An air conditioner, being a heat pump, just needs to move the heat from one spot to another, and the "typical" phase-change A/C unit is fairly efficient at it.
To put some figures on it, an air conditioner with an EER of 12 means that it can move 12,000 BTUs with 1000 watt-hours of electricity.
Now, 12,000 BTUs is equivalent to 3516 watt-hours of heat. So for every 3,516 watts of heat generation, you'll be expending 1,000 watts to move that heat to the outside of your building. And that's with an EER of 12, some units exist with EERs as high as 17.
So, for every 150 watts of power your computer is using, figure 40 to 60 watts for your A/C.
On the other hand, were you using a peltier device for cooling, you'd be in bad shape. If the EER figure were applied to them, it would be less than 1. For example, to move 30 watts of heat across a peltier, you'd need to apply approximately 45 watts of heat to it - meaning you'd be removing 30 watts from the cold side, but you'd need to remove 75(!) watts from the hot side.
steve
Oh, you're not stuck, you're just unable to let go of the onion rings.
It won't cost you nothing, but it will cost you less. Assuming of course that your furnace is a more efficient heater than your PC. Which makes sense, your furnace is designed for it. Fans and coolant systems on a PC are designed to dissapate heat, but some of that electrical energy is actually going into making your calcualtions, pumping sound through the speakers, and lighting up your display.
The power saving methods are designed to cut the ACTIVE power use of the chip - the power that is dissipated by the transistors flipping from 0 to 1 (and 1 to 0). The challenge, as we shrink geometries (I work next to a semi fab) is that the LEAKAGE power (the power being dissipated to heat just from putting power on the chip) is growing relatively fast (in % of total power).
This is one reason why IBM and others have moved to a Silicon-on-Insulator process - it reduces the amount of leakage power. Other methods for doing this include actually powering down certain portions of the chip so that they aren't drawing power even if they aren't switching. IBM calls them voltage islands. The challenge is the tradeoff to time in powering those sections of the chip back up again.
These developments are part of a natural evolution in the semiconductor industry to deal with the heat creation of semiconductors. I'm not saying we're winning, but it's getting some focus and there are methods of keeping it from getting totally out of control (at least in the near future)
If I were you, I'd make sure your friends buy you beer/soda and pizza at least periodically... heh. Most of my friends would just do that because they're cool like that, though.
My blog. Good stuff (when I remember to update it). Read it.
This seems a poor comparison between the AMD CPUs. Given they have taken a 130 nm chip and underclocked it, that means the chip is capable of higher clock speeds and therefore has "hotter" (from a speed sense) transistors as we used to say at AMD (used to work there). Since the transistors can deliver more current when on (leading to the higher clock speeds), by definition (subthreshold slope is limited by physics to ~60 mV/dec of current) they will "leak" more in the off state than transistors that don't supply so much current (and therefore run slower). I wish they had had equally rated (by AMD) chips to remove this uncertainty, although everyone seems to be focusing on the difference between the Intel and AMD boxes (which opens up a world of concerns....is it the motherboard under load increasing its demand, they have different memory systems which could contribute when stressed, is the PCI-E bus not as efficient as the (assumed) AGP, etc.).
I was a little surprised at what you said, so I checked the math. At 7 cents per kilowatt-hour, the cost is $6.64/month:That's approximately $1 per penny of cost per KW-Hour.
It is true that a desktop computer, with monitor off, draws a little over 1 Amp at 120 Volts, or approximately 130 Watts. I tested with an AC clip-on ammeter. This depends on the CPU, of course. I tested with a 2.2 GHz Athlon. (My meter did not measure RMS values, which means that it may be inaccurate for unusual waveforms. My meter is not particularly accurate at that low current. Does anyone have a more accurate meter?)
The conclusion is that it is better to put a computer in Standby when it is not in use. In Windows, I use Wizmo for that. A problem with that is that some computers don't recover from Standby very well. Hibernation works better, but Windows XP even has trouble recovering from hibernation on some computers.
I liked your sig: "We have to go forth and crush every world view that doesn't believe in tolerance and free speech." - David Brin
Here are others:
"When Saudis attack, invade Iraq."
"War for peace."
"Invasion to promote democratic independence."
"Bombing for social stability."
"Iraqis should be happy to be killed by those well-meaning Americans."
"Neil Bush: Prostitution for family values."
Layoff the twinkee's man. If 72F cause you to sweat, you have more serious problems than server fans. Exercise. Visit the outdoors. Use the stairs.
Good points. There's nothing good about using more power, whether you're worried about the temperature in the room, or the environmental impact, or your wallet.
The guys over at http://www.silentpcreview.com are always interested in lowering power, because that means lower needs for noisy cooling. Some of them have great results with undervolting. There are desktop apps that can change the clockspeed and voltage on the fly, so some of them are running, IIRC, A64s at 1GHz, 0.9V, drawing very low power, then switching up to more normal speeds/voltages on the fly, when required.
There's even at least one app that will do this switching automatically based on load. Many Athlon 64 motherboards are supposed to have that built in ("cool-n-quiet"), but by all accounts it doesn't often work well.
Search the forums over at that site for more info.
Hmm... First time i read that I thought for sure that you had just invented a perpetual motion machine.
But maybe you are right. You don't seem to be violating physics.
The Internet is full. Go Away!!!
... they make set a new TECORD!!!
The trick is that the extra power (above the amount of electricity you use) comes out of the ambient air, causing it to be even more frickin' cold right next to the heat pump.
There's a limit to the ratio between the electricity you put in and the heat you pump out of the cold place and into the hot place. However, that limit isn't caused by conservation of energy, which is the principle that prevents perpetual motion; it's caused by some thermodynamics stuff that I really ought to go back over.
You über-admin! We all bow before your 1337 4dm1n 5K1LZ!!!!!1111
I want to delete my account but Slashdot doesn't allow it.
Just turn them off yourself... with extreme prejudice!
"[Regarding the 'cloud,'] ownership was what made America different than Russia." -- Woz
I prefer to take a more optimistic view. Living in the cool north, we gain the benefits of heat during the winter from the monster computers in my apartment. Obviously it isn't the most efficient means of heating, but it is a useful by-product
A CNet article had specific power details on the 130nm Athlon 64 and 90 nm Pentium 4:
"The 3800+ chip consumes 91 watts of power at idle, rising to 172 watts under a full load. That compares with 155 watts at idle and 258 watts under a full load for the Pentium 4 560."
The lower power consumption of the AMD parts arises from their lower clock frequency, as well as from AMD's use of silicon-on-insulator technology.
It's not clear if Cool n Quiet was used, but it shows the much better power utilization in existing AMD processors over Intel, even though Intel was giving a long talk about how important power usage was at IDF.
Paul
Has anyone else noticed that the difference in power consumption is almost directly proportional to the difference in clock speeds (2.2 for AMD and 3.4 for P4)? The P4 runs through 1.5 times as many cycles and used about 1.5 times as much power.
Out of curiosity, what machine is that?
AMD uses IBM's SSOI(strained silicon on insulator) process. This is the same process used to make the PowerPC 970.
IBM's strained silicon process is more advanced than Intel's, and offers better performance as a result. It's also more technically challenging to implement. Further, IBM's process incorporates SOI to reduce heat dissipation and increase energy efficiency. It is not surprising that the AMD chips perform better.
This alliance is good for both IBM and AMD since it allows them to share their development costs to better compete with Intel. In and ideal world all three companies would share development costs, and we would all benefit.
AMD > *
Dell Latitude D600. Pentium-M @ 1800MHz. And I lied; when it's plugged in it'll draw up to 45 or so. But if you're doing nothing strenuous (preferably at night, so the backlight is all the way down), then you can get it down to 12-13W, which is good as the battery is only 53Wh. A more realistic number, though, is about 16W, with the backlight low, low (but not zero) processor load, and using a wireless network.
the problem as gate geometries get smaller is that the leakage current of the transistors increases - even while they are not switching - hence lots of dissipated power whilst doing nothing. You can negate this to a certain degree using a process known as triple oxide to reduce this effect - the main drawback is this can slow down the switching speed. Also, it adds another level of complexity (and therefore cost and yield issues) to the manufacturing process.
I run SETI@Home, you insensitive clod!
"[Regarding the 'cloud,'] ownership was what made America different than Russia." -- Woz
My "110W" P4 3.0GHz PC uses total 90W at the wall at idle. That includes CPU, fans, graphics card, hard drives idling, PS inefficiency etc.
This AMD turning 112W at idle is nothing special and is noticeably more power than Intel still. It's very respectable though considering my Athlon XP 1700+ takes 170W or so at idle.
AMD is getting better. Intel is still king. And that's before you talk about Pentium M.
http://it.slashdot.org/article.pl?sid=04/10/04/172 6208
Fatass.
The commited IT guy stays thin so he can hand out in the server room longer;) Viva la pencil neck geek! Down with fatties!
just tell them that they can use your thing if they keep their computers in their own place and buy some wireless cards. they'd probably prefer the convenience of having a computer in their own place. unless they have LAN parties a lot of course...
It's 90+F ambient as I type this in a long sleeve shirt in a room with no air flow without sweating. Of course, I'm not super lard boy and I grew up in Texas. Wait till global warming hits, you northern boys are toast:)
Breakfast served all day!
The 90mm Athlon 64 3500+ uses 80 watts less than the P4 system under load and 40 watts less than the P4 when they are both idling. AMD chips are usually cheaper to buy but I would have never thought there would be so much electricity savings in running them after the purchase. This would add up to a lot of electricity savings for a large server farm of the 90mm AMD chips. Intel needs to get their fanny in gear and update their product line or something.
I run my computer 24/7 and I feel pretty bad about that and I've always thought that the A/C was rather inefficient. So I always doubled my wattage usage when I tried to figure out exactly how much energy I was using.
But it was actually a whole lot better than that.
Thank you very much for this clarification.
The Internet is full. Go Away!!!
We posted our 90nm Athlon 64 review last week that includes a comparison against the 130nm Athlon 64, and the 90 and 130nm P4. It also includes overclocking of the CPU.
ignorance is bliss. googlefiberatx.com
The average gamer rig has at least 4-6 leds and 2 cold cathode tubes!!!* how dare you fools in your power consumption calulations ignore the power consumption, and startup draw of the cold cathodes, and the miniscule power drain added by having 1-2 leds in each system fan... and the cpu fans and junk like that.
I do agree, that a 500 'true' 500 watt (or better) psu is genuinely only needed for a 'true' server platform, where 4-16 processors and 8-20+ hard drives are in array... however the 'normal' 500 watt psu is really only a 300 watt psu with the ability to run at 500 watts for 5 seconds at a time. any draw longer than that will cause them to explode in a fireball... which is why I buy antec True power series, because unlike cheaper quality power supplies they don't have exploding fireball mode.
* = like most slashdot posters numbers pulled out of my ass... but unlike most I admit it!
https://www.gnu.org/philosophy/free-sw.html
I am not an engineer, so please tell me if I'm just talking out of my ass. ;-)
TO START
PRESS ANY KEY
Where's the 'ANY' key? I see Esk, Kitarl, and Pig-Up...
Im usually warm at 74F with no air movement. As I type this my place is at 72F, the thermostat doesn't kick in until the mid 60s. But then again I live in 'The Frigid North'. I like the cold.
----- Question authority, but not ours. Hate the man, but we're not him.
that's gotta sting the intel fanboys
From what I've read, PCIe isn't going to noticably boost your performance over AGP 8x. So its not worth upgrading, if your system is already pretty current.
Of course, if your going dual video card or your current system is out-of-date then...
And BTUs? British Thermal Units? Why do you hate America?
fish and pipes
Before all of you jumped up and down on the new 90nm version of Athlon / Opteron 64, please be reminded that the new SSE3 support isn't yet implemented.
Perhaps on a later batch, circa 2005, will we see SSE3 and other goodies inside.
So, if you can wait just a little while, you may get something extra, without paying extra.
Muchas Gracias, Señor Edward Snowden !
It's funny that this has been one of the most overlooked features of the Athlon64 for thoes of us that don't max-out their CPU load all the time. The 754 & 939 socket CPUs have a neat technology called AMD Cool'n'Quiet which basically ramps the CPU voltage and frequency up and down depending on load when properly setup. I have an Athlon64 3200+ socket 754 which normally runs at 2Ghz but idles at 800mhz. The result? I've seen halariously my passive cooled motherboard chipset a degree hotter than my cpu (and yes this is stock heatsink that AMD provides with it's boxed CPUs). If you think that's funny I've actually disabled my CPU fan to see if the system could possibly idle without it. It passed that test with flying colours (under 40C) (thou I doubt that'd be a bright idea with load) This will be awesome for non-intensive load users because the reality is most web-surfing / e-mail and casual use rarely causes the CPU to break 800mhz for very long. The result is power savings and cooler systems. Socket 940's unfortunately don't support this feature. From everything I've read, it has something to do with the use of registered DDR ram. (It appearently can't take the frequency shifting abuse as well)
...while you guys are arguing about technicalities, I'll be out buying one because its cheaper than Intel, more durable, lasts longer, and makes me happy.
-- Game Developers: Stop porting badly-textured games from crappy console systems!