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.'"

Comments

AMD's new ad campaign

[Anonymous Coward]

Paris Hilton looking an Intel Inside sticker and saying "That's hot."

400W?

[danharan]

That's going to be the SUV of its category. Big, ugly, inefficient design catering to those who desperately need the ego boost.

It will hopefully die (yeah, bad pun) a very prompt death.

Re:400W?

[FlopEJoe]

I think it would be cheeper to buy a t-shirt that says, "I have a small penis."

Re:400W?

[grazzy]

I took the liberty to translate some of your sentences.

People spend a long time on the roads commuting. SUV's are high off the ground and comfortable. This is important, many people spend more time in their SUV's than they do with their families.

Some people should get a divorce.

SUV's are also particularly comfortable if you're overweight.

So fat people can fit their fat asses in the car.

The engines are good for acceleration, low and high end. It makes up in part for the automatic transmission.

Some people cant drive.

You need the automatic transmission so that you can eat your breakfast or speak on the cell phone while in traffic. It's also less frustrating in a traffic jam. You need the acceleration to be able to cut people off on the roads, and the height lets you see over sedans.

So the fat people can get fatter.

Finally, relatively speaking, gas is cheap in the U.S.

Our president has bombed enough arab states for the oil to be cheap, relatively speaking to the number of dead arabs.

Re:400W?

[Jeremi]

but there havw been times my honda accord couldn't cut the mustard and I wish I had one

You're in luck -- with an Honda, there's no need to buy a more powerful car. Instead, just add decals until it's fast enough.

Heat

[titla1k]

So they're a little bit hot, I see that as a good thing. Now you can cook breakfast on your case, without ever having to move!

This should change

[ottffssent]

The situation (Intel's, not necessarily the difference) should change RSN when Intel's 65nm process comes online. Looking at the huge lead AMD has right now, I don't see how Intel can beat them in both power and performance anytime soon unless they're willing to add a few hundred more pins to their sockets to accomodate on-die memory controller(s). I doubt Intel will do that. I also doubt they'll come back a bit from the 150W/CPU these Paxville chips crank out, so they'll be using the process headroom for higher clocks and/or larger caches.

Ultimately an on-die memory controller is the only way to bridge the increasingly large gap between the CPU and RAM. Intel's managed amazingly low latencies to RAM given that they've got an entire extra bus and chip to run through, but they're still ~50% higher than AMD's. The netburst architecture was supposed to be insensitive to RAM latencies but Intel is not keeping up in the bandwidth department either, and it's clear that these CPUs are suffering from a lack of RAM bandwidth (twice the processing power per chip, but no increase in bandwidth).

Re:This should change

[Anonymous Coward]

I'll give you a quick hint: the K8 (I.e. Opterons and Athlon 64 and X2 series) is a freaking marvel of technology. The dual-core variants even more so.

Intel's dual core chips are just two chips pasted on the same die. Take a look at a proper description of an X2 some time -- there's cache sharing, an inter-cache on-chip hypertransport bus and all that nice shit that Intel just doesn't have. It's not far-fetched to say that at the moment, speaking from a microarchitecture point of view, AMD is a generation ahead of Intel.

Re:This should change

[ottffssent]

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.

400w?!

[Anonymous Coward]

Sweet zombie Jesus, the heatsink must have fins like a '57 DeSoto! At 400w and using it 24/7 will make the cops think you're running a grow-op.

Re:And Apple wants to replace PPCs with *THAT* ...

[FidelCatsro]

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

Re:oh well

[Spacejock]

When all their 350w power supplies melt.

Re:Not terrible...

[strider44]

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?

Re:Not terrible...

[masklinn]

Yup, power consumption figures are for the whole system.

But using roughtly equivalent systems (same power supply, an Antec TruePower so you're looking at an "at or above" 75% efficiency power supply when drawing 200+W from it, a single Raptor 74Gb and a Plextor DVD-RW drive), AMD's Opteron system top at 235W idle (for the 2.8GHz Opteron box) without using PowerNow's power management system (GamePC reports that the total power consumption @idle fell to around 170W using PowerNow) while Intel's 2.8GHz Xeon system chews through 390W idle...

Bring on the winter!

[WidescreenFreak]

I don't understand what all of the fuss is about. With systems that generate this much heat, I want to buy one just because it will probably be cheaper to heat my house with a dual Xeon system than with heating oil, considering current fuel prices! I can simultaneously have the benefit of running one hell of a Battlefield 2, Half-Life 2, or SETI@Home system! Then when summer arrives I can switch back to my cooler AMD X2 system, thus saving money on cooling bills as well!

AND after playing BF2 for an hour or so the top of the case will be ready to cook up some chicken and steak tips! Introducting the new Intel, dual-Zeon, charcoal-less hibachi system!

Come on! You guys need to look at the positives of having such hot CPUs!

Re:Nonsense

[Anonymous Coward]

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.