Slashdot Mirror
New Xeon CPU Hot and Underpowered
Kasracer writes "Web Sites The Register and GamePC received several of the new dual-core processors from Intel, dubbed 'Paxville', and ran a battery of tests on them. What did they find? From the article: 'There's no doubt about it, Intel's dual-core Xeons are their most power hungry Xeons to date ... Even when idling, two dual-core Xeons consume nearly 400W of power at any given time, which is amazingly high, even by Intel's standards ... their new dual-core chips (while powerful in their own right) simply are bested across the board by AMD's dual-core Opteron processors. Even worse, the Opterons typically perform much better while running at slower clock speeds and only having half the amount of on-die L2 cache to utilize.'"
Dell wants dualcore to sell, so they have it.
how long before they realize that it was a fatal move?
#
#\ @ ? Colonize Mars
#
Apple will most likely be using Pentium M's, as they are currently planning on phasing in the Intel chips from the ground up, whilst leaving the Power Macs to run on the G5's for the moment IIRC.
So there is a good chance they already know that Intel has something far better in store for them to use in 2007/2008
This new xeon Chip is sucking down more juice than the three macs I have In my house , It is 100W less than my server and PC
The only things certain in war are Propaganda and Death. You can never be sure which is which though
Rules of successful businesses. 1.) Listen to consumer 2.) Don't lie to consumer 3.) Make decisions based on companies largest comodity, not companies largest stock holders 4.) Don't ignore competition
So you're saing having a chip that uses 50% more power than its direct competitor and doesn't even beat it in a single benchmark isn't terrible? The Opterons beat the Paxvilles in every single test. Are you reading the same articles I am?
You're right thta they didn't measure the power of just the CPU, but they also didn't benchmark just the CPU, because you can't run the benchmarks with out memory, buses, IO etc. Duh. Besides, CPU power is not an apples to apples comparison - one CPU integrates memory controllers and high-speed CPU-CPU connections, the CPUs require different types of RAM...
The power the system draws is the more relevant to the system owner than the CPU power is. They used comparible systems.
I realize that 400 W while idling isn't typical of Intel processors, but still, didn't Apple choose Intel because of their supposedly low power consumption?
It's less a matter of design flaws as marketing flaws, I think. The P4 sucks in a lot of ways, but it's also very well-done in a lot of ways. The big problem is not so much netburst as it is Intel's inertia. Intel's working on a way to transition their product matrix from netburst on the desktop and in server space to something based on the pentium-M. The faster pentium-Ms beat the fastest P4s hands down in most benchmarks, but there are no good desktop chipsets for it yet, etc. Eventually Intel will release a dual-core P-M-based design, hopefully with an on-die memory controller, and then the Opteron will finally have some real competition.
Even if Intel eventually hits a process wall, they'll still be able to rest on their huge manufacturing capacity. For the past 5ish years, Intel has been building bigger chips than AMD, mostly in terms of L2 cache. It's not necessarily the best way to improve performance, but it's fairly easy, and leverages Intel's manufacturing strengths. Intel can afford to crank out dies 50-100% larger than an equivalent AMD die, and still make money at it, and still not run out of capacity. The reason Intel has been having shortages of late in the chipset arena is not lack of capacity but bad capacity management. They mis-read the market 3ish months ago and are paying for it now.
Anyway, here's hoping AMD's 65nm transition goes as smoothly as their 90nm one.
High-speed Road Trip (18.000KPH)
Even though it might be a little offtopic (But hey, this is slashdot ;-) :
Unfortunately that's not correct. Cars in Germany are quite expensive. If you compare the prices in Germany with those in the US for typical german brands like BMW, Mercedes, Audi you will notice that in fact those cars are usually cheaper in the US.
Concerning SUVs: I never understood why those cars with heavily overpowered engines are so popular in the US. I mean a typcial car with a 1.6 16V engine will have around 110 hp. That's enough to drive speeds up to ~200km/h (I think around 125mp/h?!) so it's sufficient to drive on the autobahns. And you can actually drive these speeds!
In the US, what's the usual speed limit? Like 90 mp/h? Why do you need such a strong engine, then? You can't use it anyway!
It's less a matter of design flaws as marketing flaws, I think. The P4 sucks in a lot of ways, but it's also very well-done in a lot of ways. The big problem is not so much netburst as it is Intel's inertia. Intel's working on a way to transition their product matrix from netburst on the desktop and in server space to something based on the pentium-M.
The P4 succeeded because of marketing. It's the "more MHz is better" myth, which was eventually debunked by AMD. My hunch is that the engineers knew better, but management wanted to create their own reality. A big chunck of the market bought into it.
Technically, AMD's design is much better than Intel's. The P4 itself was an aberration. Why else did Intel look to older P3/P-M architecture?
It's 65mp/h! Please try not to laugh your head off the next time you're driving an autobahn.
The real irony is they put it the low speed limit to save lives and gasoline, then they go and build SUVs that guzzle gasoline and are prone to rolling over at high speeds.
Height: 38U, Weight: 0 Newtons, Eyes: #0000FF, OS: Gray Matter 1.0 (Alpha)
As a small-time, low power switch-mode power-supply designer, I would like to object that it is very difficult to accurately measure the power draw of a modern desktop CPU, unless you design a whole motherboard specially dedicated to power measurements.
;-)
These beasts have peak current draws in the range of 100A @ 1.5V.
If you were to allow for a maximum of 1% voltage loss (15mV) across a measuring shunt resistor, this would mean 0,00015 Ohm Resistance - the equivalent of a piece of copper Wire with a cross-section of 1.0mm^2 and a length of 7mm. Good luck attaching a 1% accurate kelvin sense connection to this. You will also have to design a high performance multiplier circuit to make accurate RMS power measurements in the MHz Range.
But even then, and not considering mechanical difficulties like buried traces/planes, you cannot place this shunt betwwen the cpu and the Power supply (i.e. 1.5V switcher and bulk 1.5V capacitors), because the added inductance and skin effects would probably cause the CPU to malfunction.
So your best bet is to place shunts between the multiple switching coils and 1.5V Caps, which would probably work. But then you are only measuring the sum of the CPU current draw + the dissipation losses in the traces and the capacitors - which arent neglible, as a lot of people learned recently, as the overheated low-quality organic caps died on their motherboards.
But what is it worth ?
As a computer user, I care only for four things :
- The reliability
- The noise coming out of the box
- The cost of the power going into the box
- The cost for extra air-conditioning, or the savings on heating -
depending on the season and where you live
For all of these, the amount of power drawn from the wall plug is a very suitable indicator.
SUV's are high off the ground and comfortable.
That high off the ground also makes SUVs very unsafe - the death rate in SUVs is higher than in any other 4 wheel vehicle type because of the high center of gravity leads to a lot of rollovers. Even a simple tire failure or striking a guard rail can cause these things to flip.
Then there is of course the toll on the occupants of other vehicles these things hit. Car occupants are 50% more likely to be killed in a SUV-car accident than in a car-car accident.
The problem is so bad that the decline in highway deaths in the US has hit a plateau. Death rates in SUVs is actually rising.
Analysis of the statistics gives estimates that SUVs lead to an additional 6000 deaths on US highways every year.
future plans
Ahh - vaporware. We all know how stuff always gets delivered on time and lives up to all the marketing hype. And of course after issuance of the preannouncement the competitors are not allowed to improve their products.
Feh.
Which covers like over 80% of Americans. This is the #1 reason why SUVs, pickup trucks and minivans are so popular - they need large vehicles to haul their fat arses around...
Funny, there are videos of crash test of two Renault vehicles. One is Megane (you'd have hard time seeing such small thing in US probably...), the other is...truck comparable to your 18 wheelers. Both head on head, 60 kmph (contrary to what most people think, most of crashes happens at around that speed - drivers usually brake a substantiall bit).
Result: the truck barely notices the crash, the engine compartment of Megane dissapears...BUT the safety cage of Megane is basically untouched!
Only one detail: the truck was newest model, with very, very low bumper, designed so the small car won't drive under the truck, but...well, bump off.
It's not the issue of weight. It's the issue of bad, unsafe design.
And that issue is also present in SUVs. Look how heigh their bumper is (oh, but it must look cool and bad...)
One that hath name thou can not otter
You realize how arrogant and condescending you sound, don't you? I'm aware of the Laffer curve, and I'm also aware that it has two sides: the left side, where raising taxes increases revenue, and the right side, where raising taxes further decreases it. You seem pretty convinced that we stand on the right-hand side, but what makes you so sure of that? Increased revenues can just as easily be due to the normal economic cycle. Not to mention that it is an oversimplification: it's not just the total amount of taxation that affects GDP, but also who gets taxes and how. Some taxes will hurt the economy more than others, even if they cost their targets the same amount in dollar terms. In any case, I think it's just common sense that we shouldn't spend money we don't have -- so if the government thinks it is really important to spend more money on Iraq or whatnot, they need to raises taxes to cover that spending. If the public agrees, then the public will tolerate the extra taxes. If not, the public will elect different leaders. Hiding the costs by passing them on to future generations to pay back with interest is a lousy scam.
I don't care if it's 90,000 hectares. That lake was not my doing.
Anyone using Rioworks or Tyan boards should have their fingers broken in multiple places in order to stop them from making foolish purchaces again the future. Those boards could be replaced by a flavor of Gigabyte, Asus or ASRock 939Dual boards.
Om, nomnomnom...
The P4 succeeded because of marketing. It's the "more MHz is better" myth, which was eventually debunked by AMD. My hunch is that the engineers knew better, but management wanted to create their own reality.
As an engineer at Intel, I have to disagree with this. I don't know any engineers in the processors division, but I do know some in chipsets, and they fully bought into the MHz myth. "We're winning the Megahertz wars!" was a common line heard in business meetings back in the P4 heyday, and when I talked to chipset engineers about AMD vs. Intel architecture, they believed it all too. If I pointed out how AMD's CPUs outperformed ours at a much lower clockspeed, they'd just say how the P4 could potentially be clocked so much higher, so AMD would just hit a brick wall where they couldn't clock any higher, and Intel's chips could be clocked up to 10 GHz or so.
Of course, we all know now that was pretty stupid, since they didn't even hit 4 GHz before running into a thermal barrier.
Don't fool yourselves about Intel engineers. They're not that smart or special. Most of them just sit around every day writing HDL code, writing unit tests, and other boring stuff. The high-level architects are just these same dull engineers who have stuck around long enough to get promoted to that level; they're shooting from the hip too. Really smart engineers don't generally work at places like Intel. Considering how bad pay is for engineers in general, really smart people don't stick around at big companies for very long, and go start their own businesses, become consultants, or go into a different field altogether.