SpeedStep On Your Desktop - Intel's Prescott-2M

Kez writes "Intel's Prescott core has undergone a few changes, and the latest version - Prescott-2M - includes new features, one of which is Enhanced SpeedStep technology. Given the jokes about the heat that the Prescott gives out, Intel had to act. It was inevitable that a power (and heat) saving technology such as SpeedStep would find its way into desktop PCs. HEXUS.net has an article looking at the new Prescott-2M based Pentium 4 660 and Extreme Edition 3.74Ghz CPUs, examining their new features and performance."

Comments

So, I can

[Gr8Apes]

only fry one egg at a time whilr doing anything other than staring at the login screen?

Dupe

[siliconeyes]

Slashdot

Dupes on your desktop

Natural Gas Prices are Rising

[bigtallmofo]

I look forward to heating my house with my new Intel processor!

Re:Natural Gas Prices are Rising

[The-Bus]

Screw that. Make sure the next Rovers are running these and we'll heat up Mars in no time.

It's not inevitable...

[Anonymous Coward]

...why should it be? AMD used to have heat issues, and they managed to find a way around them. To me, this almost seems like cheating on Intel's part. And what are they going to use as the excuse to "step down" a processor I paid to have run at a certain speed? With a laptop, they have the "save battery" excuse, which is a valid one (but still over-ridable by the user) - what's the desktop equivalent? The fact that they can't cool their processors is definitely not a good "excuse".

Re:It's not inevitable...

[olip]

uh ? perhaps saving energy?
Let me guess... your SUV always runs at full throttle ?

Re:It's not inevitable...

[hattig]

Athlon 64s all have PowerNow technology and have been able to do this from the start to cut power consumption drastically.

Considering that all the sites are now talking about Intel finally catching up by having a similar feature enabled by default, I'd say that it wasn't available before now.

Anyway, power consumption tests on these new Intel processors on other reviews (Tech Report) show that this technology is only useful when you aren't doing any work at all on the processor, when you do stuff, the Intel 6xx processor jumps to 50W-70W higher than an Athlon64 90nm under the same load. So if you are folding or SETIing or whatever, 24 hours a day, and your electricity is 10 cents a unit, you are talking up to $62 more a year in electricity bills.

If you keep a system for three years, a P4 will cost $180 more to run than an A64, and that is certainly something that should be factored into the purchase price for people who like their systems to keep on doing stuff. If you leave it idle overnight, then the cost difference will be a lot less of course, or if your overnight electricity is a lot cheaper then folding at night only is a good choice.

Re:It's not inevitable...

[Menchi]

I don't know about Intel CPUs but AMD's standard Windows Cool'n'Quiet driver ignores tasks with "idle" priority. As a result it does not raise the Vcore or clock speed just for SETI@Home unless you tweak the task priority.

I think this is a good choice. This way you can safe energy and donate CPU power at the same time.

Re:It's not inevitable...

[Bri3D]

HMM...let's think...maybe that you aren't using all of your CPU all of the time. If you do clock scaling right it doesn't affect performance at all. This is the same as saying you should run your car at whatever RPM it gets max horsepower at because "that's what you paid for." And the excuse...let's think...power? My P4 systems used to throw breakers in my house. I had to WIRE UP A WHOLE CIRCUIT for each 2 of 8 computers in my house to prevent breaker trips/fires/etc. So yeah I'd say this is a good idea. BTW AMD uses thermal management/throttling too.

My Yet-to-be-never-sent letter to Intel

[TheRealMindChild]

Dear Intel,

Thanks for taking such a GREAT APPROACH to your heat problems. I can't WAIT to use one of these new processors in my desktop, only to watch my whole computer DROP IN SPEED as I am an hour into Doom 3. I don't know that I can speak for everyone, but the whole design efficiency thing is overrated anyway. I simply can't live without the noise of a jet engine in my case. Keep cranking up those Mhz and I will continue to have my cpu throttled everytime I do something useful.

You're the best,
Sarcastic Consumer

Re:My Yet-to-be-never-sent letter to Intel

[jrand]

While I recognize the tone of your comment was meant to be funny, I don't understand the many comments that seem to suggest this type of power management will cause a drop in performance. From my understanding, Intel's Pentium M processor has been using this technology for some time and often performs better than a similarly clocked Pentium 4. Most people simply don't use the full capabilities of their processor most of the time. An architecture that takes advantage of this in order to comsume less energy and run more quietly just makes sense, and there is no reason to believe demanding consumers will take a performance hit.

Re:My Yet-to-be-never-sent letter to Intel

[MooseGuy529]

I have a Pentium-M laptop and I will explain how SpeedStep works in practice.

SpeedStep itself allows the CPU to change frequency (and voltage along with it) to save power. For example, my 1.7 GHz Pentium-M can run at 600, 800, 1000, 1200, 1400, 1500, or 1700 MHz. This is usually controlled by turning up the speed when the CPU usage is high and turning it down when the usage is low. Thus, if you are playing Doom, it will run as fast as it needs to to keep up. These "performance" states are described as "P-states" in the ACPI spec (they run from P0 [full speed] to P7 [slowest speed] on my computer)

There is a second, older type of throttling. that is just called throttling, and described as "T-states" in the ACPI spec. On older Pentium III's, there are two states, T0 (on all the time) and T1 (off half the time). On my Pentium-M, it goes from T0 (on all the time) to T7 (on 1/8 of the time) in 1/8 time increments. This throttling is much less efficient (it has to start and stop the CPU constantly, and still runs the clock at 1.7 GHz when it's on) but is used for a different purpose, as you will see.

ACPI "thermal zones" are objects that consist of a temperature, and "trip points" (temperatures) that trigger "active" and "passive" cooling. Active cooling is set at a lower temperature, and is linked to a fan object that the OS should turn on. Passive cooling is set at a higher temperature, and is linked to the processor object. When the temperature passes the "passive" threshold, the CPU is throttled using T-states.

I actually have a bunch of data about CPU speed (P-state) and throttling (T-state) versus temperature and power usage, and I can tell you that both types of throttling save battery power and run cooler. However, P-states are much more efficient. If you take a 1.7 GHz processor and run it at P0 and T7 (1.7 GHz on 1/8 of the time = about 215 MHz) it runs almost 20 degrees hotter and uses up about 5 Watts (the lowest usage I recorded was about 12.5 Watts, so that's a large fraction) more than running at P7 and T0 (600 MHz on all the time). It's also 1/3 the speed. So basically, P-states are much more efficient, but T-states are what is tied to cooling, probably because they existed first.

The unfortunate problem here is that P-states are much more efficient, but traditionally P-states are tied to usage and T-states are tied to temperature. It is often suggested to use T-states once you are in the bottom P-state (i.e. go 1700*8/8, 1500*8/8, ... 800*8/8, 600*8/8, 600*7/8 ... 600*2/8, 600*1/8) but frankly that doesn't save much power, and does hurt the responsiveness of the computer. (It needs a certain minimum speed to be able to speed itself back up in time to not look laggy...)

The best thing to do if your processor thermal-throttles itself is to 1. cool it better (perhaps attach an air conditioner to the side of the case?), 2. turn down the speed--voluntary throttling may sound like a waste, but it keeps the temp down better than letting the OS throttle it, and it gives better performance, or 3. get a Pentium-M.

I haven't actually been able to compare my Pentium-M to a Pentium 4, since I avoid those like the plague (1.5 hours battery life? how about 5?), but I can say that subjectively, it's quite snappy (thanks to 2 MB L2 cache and Linux's good disk caching) and doesn't show its slower clock except in raw processing work. (If anyone wants me to time a kernel build, email me and I'll do it, you pick the version and .config...)

Awesome!

[Tibor the Hun]

Now my CPU can slow down if I'm working it too hard.
This has got to be the best idea since hoola-hoops!

Re:Awesome!

[ginotech]

RTFA:

With a supporting BIOS, the processor will clock itself down and lower its voltage to decrease consumed power during idle periods, with the knock-on effect of reduced heat.

Perfect for cooking rice...

[dnaboy]

Run some serious number crunching to get a good rolling boil, then drop the cycle speed for that perfect simmering temperature.

No more mucking around trying to get that gas stove to just the right temperature!

Parallel

[Docrates]

Hey, if our brains do a nice enough job using lots of parallel instruction "dumb" processors, why are we so obssessed with ultra fast only-a-few-instructions-at-a-time single processors? I think the whole approach of the cell architechture is the right way to move forward.

Please spare me the "the brain can't multiply 100000*1234555 fast enough" argument. We can have the best of both worlds: complex single "cells" (unlike brain cells) repeated many many times for parallelism.

Re:Parallel

[Yartrebo]

Why does one company make a big press release (any maybe a few patent applications) and now it's called 'cell technology'. Call it node technology if you want that terminology. At least that isn't trademarked.

It's just parallel processing with a few minor twists. Consoles since the day of the NES and SNES have worked similarly, though without quite as many chips.

Call it by what it is: parallel processing.

Re:Parallel

[TerranFury]

Simple: Most algorithms are not easily split into independant parallel threads. If they could be, then previous (smaller) attempts to integrate vector processing (like MMX and SSE) would have had larger impacts than they did. Plus, many of the obvious vector operations have in fact been offloaded - to the GPU.

Re:Parallel

[RollingThunder]

Simply put, it's because effective parallel code isn't simple to produce.

another article

[bersl2]

Anandtech has another article up, but it emphasizes the increase in L2 cache and the effect this has on performance.

SUX-2000

[Anonymous Coward]

Intel was wise in renaming the throttleable version.
The original P4 is the SUV of CPU's.

Might I recommend SpeedswitchXP

[Stonent1]

This is a free program that lets you control speedstep in XP (something you could do with windows 2000). I have my laptop set for full performance when on AC and Max Battery when unplugged.

A Much Better Article Here...

[Hack Jandy]

Can I interest you in an article from someone who knows WTF they are talking about?

AnandTech

I don't know what the Hexus kid was on - but I feel safe trusting my reviews to people who have trouble writing big words!

From Page 2: Being LGA775 CPUs, the new processors all look the same. Being press samples that I get the privilege of testing, they're also unmarked with any meaningful information bar the slightly exciting Intel Confidential. So I draw on them. Not quite the Mona Lisa in miniature, mind you, rather an idea of what it is. Any retail example you purchase will be umblemished with my scriblings.

Tech progress through geek humor

[xtermin8]

"Given the jokes about the heat that the Prescott gives out, Intel had to act" Geek Jokes are such an important driving factor in improving technology- jokes and Slashdot posts, of course! ;-l

On balance, this is a good thing

[gmknobl]

It's just unfortunate that while the advantage of having a stepping processor on the desktop will cut down on the heat in my building's rooms, it will also cut down on the processing power at the same time.

Honestly, most people won't ever notice the difference since what they'll use it for is word processing and spreadsheets. They don't need the gawdoffal (tm) power these computers have now. In fact, the only thing driving the continual 3-4 year upgrade cycle is poorly written code and programs so huge that we'll never use all the features.

Which makes me think that maybe we should call some moritorium on "new" software, perfect what we do have, use lower power processors that are simply more efficient, and stop buying pcs altogether.

NAH!!! Just kidding! I mean, who really wants to stop this computer-centric commerce and put intel and microsoft out of business anyway... (looks around and sees slashdot's mac, linux and other os users...)

Uh, easy guys. It's only a joke... ;)

bugger them !

[Alberic]

Soon to be released by the Geek Buggers Consortium:
A deamon that automagically sends support@intel.com a standard mail when CPU is 100% at low speed.
This mail looks as follows:

"Dear support team,
If you received this mail, it's because of a malfuction in your Prescott CPU #22354432, which reached a idle state of 0% during 68 ms while still being in low frequency mode. It had a temperature of 56C

feel free to ignore this mail as you ignored the 122563 previously sent by this deamon, and just as you ignored the need of a solution for CPU heat problems.

Yours sincerely,
The Intel bugger deamon."

IBM water cooled 'mainframes' make a comeback

[gelfling]

Remember in the early 90's when many of you were still in grade school and the TCM based mainframes with their 400psi water chiller pumps were beginning to make way for the CMOS era? And we heard that a 10 CMOS CEC could easily replace a 2-3 TCM CEC because even though each one was rather slow and low powered they could gang them together and heat would not be a problem? We all chucked our TCM mainframes, got rid of all the chiller machinery with hacksaws and went on our merry ways.

Well it looks like the prognostication for a Brave New World was a little premature. It looks like we'll start to see the return of complex and expensive water chillers yet. Not the homemade black tee shirt and Krispy Kreme version but real, large, complicated chiller pipes that are built right into the CPU chip.

Very suspicious

[NatteringNabob]

Intel has apparently not posted SPEC numbers for these processors, and in fact seems to avoid publishing official SPEC numbers for non-Xeon processors. By contrast, AMD does post SPEC numbers for the FX-55, and the Opteron 252 results were available the day the chip was announced. The comparison between the latest Opterons and Xeons is none too flattering for Xeon although the 2MB cache should help the SPEC FP numbers quite a bit. The problem for Intel is that P4 still consumes gobs of power and produces a lot of heat even when it isn't doing anything. By contrast, the Athlon 64 3000+ (90NM) that I'm typing this on maxes out at about 65W, which is roughly the P4's idle power consumption. This machine torches the 2.6GHz P4 machine I have at work at compiling and running Java programs (of course, I'm running Fedora Core 3 here, and Win2K there so it isn't apples to apples). It is hard to see how Intel is going to cool 2 such cores on a single die whereas AMD shouldn't really have a problem. Note, that I'm not particularly an AMD fanboy. I have a couple of Dual Celeron boxes and a Dual PIII box, but Intel took a very wrong turn when they went the P4 route, and I don't see anything that indicates that they are getting back on track. The multimedia performance is nice, I gues, but realistically, how many users spend the bulk of their time encoding video?

600 more effecient even without SpeedStep

[edxwelch]

Actually what's more interesting than the SpeedStep thing, is the fact that the 600 series uses 25W less power than the 500 series on full load ( that's something when you consider that there is 1M more memory on the new chip).
Up til now Intel's 90nm process was a huge failure because of the heating problems and forced Intel to abandon their plans to hike speeds above 3.8GHz