Measuring the User For CPU Frequency Scaling

An anonymous reader writes "The Empathic Systems Project a Northwestern University demonstrate up to 50% power savings by controlling CPU frequency scaling based upon the end user. They measure the user with eye trackers, galvanic skin response, and force sensors to find a CPU frequency that the user is satisfied with. They are currently studying user activity and system performance on mobile architectures, specifically the Android G1 phone."

Comments

So does this mean

[MiKM]

Does this mean that clicking a button multiple times and yelling at my computer will finally make my it go faster? Sweet!

Re:So does this mean

[plut4rch]

It's like a Turbo button but with your mind!

Re:So does this mean

[Anonymous Coward]

No, it just means that not clicking a button multiple times and yelling will make it go slower.

Re:So does this mean

[mrsquid0]

What I really want is for a download to speed up when I drag the progress bar.

Re:So does this mean

[CarpetShark]

It's like a Turbo button but with your mind!

So... your mind becomes a 486?

Re:So does this mean

[AHuxley]

486 billion neurons should be enough for anybody.

Re:So does this mean

[martin-boundary]

Does this mean that clicking a button multiple times and yelling at my computer will finally make my it go faster?

Or maybe the opposite. Think "a watched pot never boils". They'll call it CPUPersonality(TM).

Re:So does this mean

[mattb112885]

Yes, just like hitting the top of my TV makes it stop buzzing or throwing my phone against the wall makes it stop ringing.

Re:So does this mean

[l00sr]

Yes. I hear the Microsoft version will take into account number and frequency of thrown chairs as well.

Re:So does this mean

[fel0niousmonk]

If only this were true.

However, I feel the next revolution to our worlds will be things that function just as you suspect. Perhaps this will come in the form of bionics, or simply more advanced materials, conductors, energy production, that function solely to provide additional resources via non-standard means. If we could translate the tapping of your foot while you're peeved at your computer for burning too much CPU (or your ADHD is going off the charts and YOU'RE trying to do too much at once) into more CPU cycles, the technological world would be a much more intuitive, ergonomic, and ... intelligent.

But sadly, a user-sensing-cpu, to me, means that that for hardcore users (or simply not habitual), you're going to always be wishing you could turn off that 'annoying POS feature that makes your computer slow to respond >:'.

Re:So does this mean

[perryizgr8]

which brings up the question why wasn't the speed faster by default? what is the logic behind slow download speeds and allowing the user to increase them at will?

Re:So does this mean

[complete loony]

So watching your process really will make it finish faster?

Re:So does this mean

[Anonymous Coward]

...and if you want it to go fast at all times, you'll have to keep on screaming. Reminds me of that episode of Simpsons where Homer was hipnotized and got trauma flashbacks so he was screaming intermitently while acting normal otherwise.

Re:So does this mean

[noidentity]

What I really want is for a download to speed up when I drag the progress bar.

After using some of the newer video game console emulators which have fast-forward buttons and sliders, I find myself reaching for it whenever the computer is taking too long.

Re:So does this mean

[jra]

Turbos, buddie!!

Re:first post

[Anonymous Coward]

Hey dumbass... I hope you realize that when this post gets modded down you will have negative karma.

It's almost impossible to recover from negative karma.

Time to register again...

And of course...

[Chabo]

Wide, crazy eyes and frantic button mashing mean that the CPU should be overclocked as much as possible, while closed eyes mean that the system should ignore changing the CPU frequency, and send a System Beep straight through the headphones.

Re:And of course...

[Anonymous Coward]

In related news, a system beep when eyes remain closed for longer than 30 seconds has been shown to cause a 50% savings in monetary spending.

The theory is that gamers can be woken up by their PC, so they need less energy drinks to function.

Careful Limitiations

[Anonymous Coward]

I have to say, I have to be worried if there aren't caps based upon the chip in use.

If we're really wanting things to go faster will this push it too hard and overclock the system?
If we're really lethargic about it will it underclock the system too much? I don't know if running a chip too slow can damage it but I think there may be consequences besides battery life.

Re:Careful Limitiations

[Ethanol-fueled]

I doubt that they'd allow the "fastest" settings to run overspec with regards to the system. Keep in mind that TFA was basically about research done for research's own sake. It'd be much easier to let the user define which threshold is more comfortable for them with a "faster/slower" slider or use existing speedstepping technology without the overhead of gesture-sensing.

"We saw there were instances where scaling back the central processing unit frequency didn't affect the user satisfaction, but it saved power," Shye says.

That ties in to the fact that much of our modern technology is so fast that it can do anything we want with power to spare, and why not conserve that power for longer battery life? Would the overhead make it more feasible than existing throttling technologies? Like I said, research for research's own sake.

Re:Careful Limitiations

[cskrat]

Nobody said anything about overclocking. And yes, underclocking does have limits imposed by the system's processor and BIOS. AMD and Intel already have features on all their product lines to allow for dynamic clock adjustments to reduce power consumption. AMD's cool and quiet feature will even lower the CPU voltage at lower clock frequencies to further reduce power consumption.

These guys aren't talking about new processor designs (though I'm sure some engineers at AMD and Intel read /. and will find this research), they're looking for ways to better implement the power saving features that are already present in modern CPUs.

Re:Careful Limitiations

[John Hasler]

> These guys aren't talking about new processor designs (though I'm sure some engineers at
> AMD and Intel read /. and will find this research), they're looking for ways to better
> implement the power saving features that are already present in modern CPUs.

They also seem to be assuming that the only function of the cpu is to provide snappy GUI response (which is probably true for most users).

Overhead?

[bcmm]

I cannot imagine that, in the near future, a mobile device will draw more power by just using full processor speed than it would by having to power all those sensors and interpret their data.

Re:Overhead?

[Red Flayer]

I cannot imagine that, in the near future, a mobile device will draw more power by just using full processor speed than it would by having to power all those sensors and interpret their data.

It's good that you cannot imagine that. Because if you could imagine that, then it might be something to be worried about.

As an aside, interpreting the data would likely be done by the processor, so if you're going to be running the processor at full speed, then the only thing to be concerned about is the draw of the sensors.

Re:Overhead?

[tkw954]

I recently did a test on a fanless VIA Eden system (CPU + mobo + RAM + notebook hd + 2 Delta 1010LT soundcards with a switch mode PSU). The power consumption was 29.1 W with the system idling and throttled down (600 MHz) and 31.9 W with a full 'ping -f localhost' load (1200 MHz). I know it's not an embedded ARM system, but this does give an idea of the nearly negligible power savings available by halving your clock speed.

Re:Overhead?

[Anonymous Coward]

But the point is to *avoid* running the processor at full speed.

What are you, retarded?

Re:Overhead?

[cerberusss]

I know it's not an embedded ARM system, but this does give an idea of the nearly negligible power savings available by halving your clock speed.

You got an 8.78% percent power savings. I don't think that's "nearly neglibible". Maybe you're correct in the absolute sense; what's a 2.8 W power savings? Then I'd say it still isn't too bad.

And yes, I'm the guy that pulls out the wall warts when not at home.

Re:Overhead?

[tkw954]

I should have said "negligible when compared to experimental uncertainty". In any case, you're right about the wall wart. I measured a draw of approximately 6 W with nothing plugged into it.

Re:Overhead?

[Anonymous Coward]

It all comes back to Ohm's Law. The only real way to save power is to lower your voltages. Just lowering clockspeeds won't do much.

Re:Overhead?

[borizz]

I'll bet the difference will be bigger if we take a quad-core desktop. :)

Re:Overhead?

[Phreakiture]

More to the point, though, I am not sure what is wrong with using the actual system load to determine clock speed. Rather than picking up on the user's state of being, let the computer pick up on its own.

If a computer has work to do, why not let it run at 100% until that work is done, then idle? This is the way it is done now, it is far less complex, it gets the most work done in the least time, and I wouldn't be surprised to see the energy savings be close to, if not equal to, this project.

Of course, I do applaud them for thinking outside the box. I will also gladly concede if my hypothesis is wrong.

Incidentally, the small differential on a Via system is waaaaaaay outside the norm. One of my machines is an AMD Athlon X2, and can scale between 1.0GHz and 2.6GHz. The whole system (minus monitor) uses about 53W at idle and 93W with both cores fully loaded. The Via it replaced (not fanless, with full-sized HDD and DVD) ran between 50W and 60W dependent on load. While it does use somewhat more energy per time than the Via it replaced, it uses substantially less energy per work produced -- the Athlon can do in 45 minutes what took the Via 6-8 hours.

so what this means is?

[FudRucker]

most people would be happy with something like win9x or win2k (linux for me thanks) on a 750Mhz CPU and 512 megs ram?

Re:so what this means is?

[Moryath]

Most of the drain users see today is OS bloat and Virus scan software bloat. Face it, A "fully updated" WinXP SP3 with a fully updated, modern antivirus package needs ~4 times the hardware a base WinXP (or even Win2K SP4) system would want.

Re:so what this means is?

[silas_moeckel]

This is simple all OS/App developers need to be given a 3 year old PC to test on. They need the big honking system to code/compile on.

Re:so what this means is?

[Anonymous Coward]

No, CPU isn't the bottleneck, never really has been. RAM and pathetic hard-drive IO is the problem for the vast majority of users. RAM is cheap now and no longer an issue. HDs have a long way to go for acceptable speed. Maybe when SSD drives have something resembling real world capacity, our machines will begin to feel less suggish.

Re:so what this means is?

[Darkness404]

3 year old? I'm sorry but I expect all programs that aren't games (and some CPU intensive programs) to run perfectly well on an early P4 with 512 MB of RAM. I currently use a 4-5 year old computer for most day-to-day work.

All programs/OSes should work perfectly on hardware made in ~2003, many people still have these (or older) computers, especially if they live outside of high speed internet access, or aren't very computer literate.

Re:so what this means is?

[Red Flayer]

Face it, A "fully updated" WinXP SP3 with a fully updated, modern antivirus package needs ~4 times the hardware a base WinXP (or even Win2K SP4) system would want.

That's nonsense. A base WinXP system (instead of a fully update XPSP3 + AV) would max out the processor and the internet bandwidth within days, if not hours, of being turned on.

See, what happens is that friendly hackers automagically scan the ports of a base XP install, then kindly install their own "service packs" to help make sure the XP system is using all its available resources. You woyludn't want to waste your resources, right?

Re:so what this means is?

[tagno25]

That's nonsense. A base WinXP system (instead of a fully update XPSP3 + AV) would max out the processor and the internet bandwidth within days, if not hours, of being turned on.

No, that is nonsense. If you are dumb enough to put any insecure OS directly onto the IPv4 (IPv6 is too large for hacking random IPs) internet then you deserve anything and every thing you get.

Re:so what this means is?

[DMalic]

I'm not sure it's "OS Bloat". With indexing turned off and no A/V I get 0% CPU use. I can't imagine Antivirus would up that all that much more. I think it's mostly little application bloat - quicktime and java and flash and the 182492814 other things you have to install sludge it up over time. A new installation IS so much faster than an old, heavily used one - even if both have msconfig startup lists cleaned out.

Re:so what this means is?

[DMalic]

What!? I'd agree with you if not for the little subject of Intel's worthless POS integrated chips - the ones 1/3 as powerful as everyone else's integrated graphics. I like seeing desktop compositing and media decoding passed off to my GPU, thankyou very much =)

Re:so what this means is?

[twidarkling]

Maybe when SSD drives have something resembling real world capacity, our machines will begin to feel less suggish.

First, I find this comment hilarious due to remembering the times when 1GB drives where hideously large, and games came on multiple CDs because there'd be no room to install the data, and SSDs are widely available at 64GB.

Second, I think I could probably get by with drives that small, if the price wasn't so stupid. I can get nearly a TB in HDD for $100 if I shop around. Or I can get 64GB SSD for 4x that price. So IMO, it's not the size, it's the price that's the limiter.

Re:so what this means is?

[Anonymous Coward]

I like seeing desktop compositing and media decoding passed off to my GPU, thankyou very much =)

It's nice that you have a good graphics card, but you're missing the parent's point. The lower the system requirements on your program, the larger potential user base you have available.

Unless your program is something that any fool would expect to need a powerful computer for (such as shiny-fancy AAA computer games, graphically advanced desktops, high def media playback, and so on), you should make it tight enough to run on computers like that example 2003 P4 setup. Of course, you can make more intensive features optional, like how Windows XP lets you enable or disable different visual effects.

Re:so what this means is?

[adolf]

Indeed. Most of the desktop computers at work are 3-5 year old Dell Dimensions with P4 Celerons running XP. And these aren't just idling along: The industry-specific quasi-web-based POS system they run is heavily intertwined with ActiveX, Java, and Acrobat, with bizarre hooks into strange hardware like signature pads, in an environment where time is money.

We fix them when they break (which isn't bloody often and usually consists of either a software or a power supply failure), and feed them more RAM periodically. New machines (we're growing) get 2 gigs of RAM because it's cheap these days. Most of the old ones are slugging along just fine, and have generally been upgraded to at least 768MB.

The next big performance boost would probably be to upgrade the hard drive for something faster, but that's generally labor-intensive, and getting close to the point where it'd be cheaper to replace the whole thing with something new.

The CPU? Geez. The machine spends its life thrashing the disk looking for DLLs or whatever, not number-crunching. A 2GHz-ish Celeron is brilliantly fast for this application.

Re:so what this means is?

[daveime]

You mean like if you lose at Russian Roulette, the solution is to have more chambers on the gun ?

Security through obscurity is not real security. More IP space just means they'll probably hack your toaster oven or yur fridge instead of your PC.

Re:so what this means is?

[silas_moeckel]

I do as well the point is most PC's have a horrid video chip set for for pretty much anything but high end games, video editing an other corner cases that is what developers should be doing there QA on. To often coders on short deadlines write junk and expect to pile on more hardware to compensate for bad code or design.

Re:so what this means is?

[Anonymous Coward]

Russian rulet with 6 chambers verses with 600000 chambers

Re:so what this means is?

[DMalic]

"Should"? Why don't companies? What are the downsides? I'm guessing much more effort would be required and you'd have fewer chances to optimize for faster equipment (unless you wanted to duplicate even more effort). In other words, significantly more expensive software.. Ahwell; everyone's buying laptops now, and those will break long before they go obsolete..

First Step

[ThistleForce]

Computers changing performance based on our moods? Hmm...i'm thinking android girlfriends are closer than we realize! It would be interesting to see just how much battery power this would save on my rig?

Re:First Step

[macraig]

Don't forget that these extra circuits and sensors will use power themselves, so the savings will be a bit less than you might hope. Also don't forget that this new bling will drive up the cost of NYM (Next Year's Model), so you'll be saving some money in one bookkeeping column by spending it in another....

Re:First Step

[Falconhell]

Wake me up when virtual wives are cheap and readily available!

Sounds way too complicated

[Anonymous Coward]

I suspect users do not care if things are fast enough. So you want the cpu to run just fast enough that you are not waiting on the CPU. And you should be able to tell that without all that galvanic, eye-tracking nonsense.

I suspect any waiting that might actually annoy the user to the point these complicated sensors might read is not going to be fixed by the CPU speed.

Re:Sounds way too complicated

[exploder]

Plus, what if I'm a fairly laid-back guy who doesn't bust a vein when my phone is sluggish? Will it just get slower, trying in vain to piss me off? That sounds _awesome_.

Re:first post

[Anonymous Coward]

Let's make it a good one, shall we?

Right out of Craig's List Adult Section . . .

[PolygamousRanchKid]

They measure the user with eye trackers, galvanic skin response, and force sensors to find a CPU frequency that the user is satisfied with.

Um, . . . yeah . . . okay . . .

"The Empathic Systems Project"

Oh, what a giveaway . . . "I'd like to buy some empathy . . ."

This just in, breaking news

[Hadlock]

Corporate customers found a 60% power consumption decrease after they found that most users are happy with scaling their computer back to 333mhz once microsoft office is fully loaded. Customers reported that most power consumption occurred during employee recreational time at work, when Youtube and Flash games take up the majority of the user's cycles.

Waste of Time

[sexconker]

So if I walk away from my machine to let it process a job, it'll go slower?

If this is to save power, then reducing speed when an intensive task is performed is retarded, since you'll waste energy (having to run the task proportionately longer).

If we're only taking into account saving power when idle/mostly idle, then basing this off of metrics from the user is a waste of effort. Just test your apps and see what a user feels is "fast" for certain tasks, then attach those target times to those tasks, and let the CPU try to hit that target.

You'll waste less energy monitoring a user's behavior and galvanic boner response, and you won't annoy the user when your system behaves inconsistently.

If you want, you can let users specify whether or not they want to emphasize battery life or performance, or turn the feature off entirely and let shit work as it should.

The trick would be getting this shit implemented at level low enough that each app would be able to specify target times and specific tasks. Of course, if you're the fuckers worried about battery life, you're the one designing the hardware/platform, so you've got control.

Re:Waste of Time

[tlhIngan]

So if I walk away from my machine to let it process a job, it'll go slower?

If this is to save power, then reducing speed when an intensive task is performed is retarded, since you'll waste energy (having to run the task proportionately longer).

If we're only taking into account saving power when idle/mostly idle, then basing this off of metrics from the user is a waste of effort. Just test your apps and see what a user feels is "fast" for certain tasks, then attach those target times to those tasks, and let the CPU try to hit that target.

You'll waste less energy monitoring a user's behavior and galvanic boner response, and you won't annoy the user when your system behaves inconsistently.

If you want, you can let users specify whether or not they want to emphasize battery life or performance, or turn the feature off entirely and let shit work as it should.

The trick would be getting this shit implemented at level low enough that each app would be able to specify target times and specific tasks. Of course, if you're the fuckers worried about battery life, you're the one designing the hardware/platform, so you've got control.

Except, this technology is NOT for computing applications, but for mobile applications - e.g., a phone.

For a phone, you do not want background processing tasks - they force the processor to stay "awake" and drain the battery very quickly. Even a simple task that wakes the CPU up every second will easily cause battery life to diminish from the 2+ weeks standby to a few days. (Take your battery capacity and divide it by the standby time - you'll find you have around 2-3mA to play with, which is just enough to maintain the radio connectivity).

Mobile processors have a technique known as DVFS - dynamic voltage and frequency scaling. The goal is to keep the voltage as low as possible (power consumed is proportional to voltage squared), which may mean you run the CPU at a lower frequency. There's a bit of overhead in switching frequencies, including having to ramp up core voltages and adjusting clocks, waiting for them to stabilize, etc.

The trick though, is to realize when the user really doesn't care for speed, and thus keep the CPU in a lower frequency (e.g., playing music), versus the user is actively doing stuff, and it would be desirable to have it finish as fast as possible (e.g., browsing the web) so while the user ponders, you can put the CPU into a low power state immediately, versus keep it at a slow clock and have the user wait. Also, you have to figure out when the user is doing something that really is requiring a lot of CPU power (playing movies), so you have to bump the speed up and hold it there, and not at the first instance of idleness, drop back down.

Basically, having this feedback ltes you find out what is going on - is the user not caring, and thus you should pick the slowest speed that'll get things done? Is the user actively engaged in the device, but the usage is bursty, so you should go into a low power state after the processing is done, or is the user doing something that requires processor, and dropping down wastes power due to overhead?

Re:Waste of Time

[sexconker]

For a phone, I do not want something trying to measure my eye movements, my skin, etc.

I want the shit to be as fast as possible so i can be done as soon as possible and the thing can be back in my pocket with the screen off, the speaker off, the bluetooth off, and the radio in it's lowest-power mode.

Throttling back speed means you have to run for longer to get anything done.
You can't throttle back power hogs like the screen or the radio, either.

This is a lot of noise about what will amount to something less effective than what we already have - throttling back when idle/near idle.

Re:Waste of Time

[Chris Burke]

The trick though, is to realize when the user really doesn't care for speed, and thus keep the CPU in a lower frequency (e.g., playing music), versus the user is actively doing stuff, and it would be desirable to have it finish as fast as possible (e.g., browsing the web) so while the user ponders, you can put the CPU into a low power state immediately, versus keep it at a slow clock and have the user wait. Also, you have to figure out when the user is doing something that really is requiring a lot of CPU power (playing movies), so you have to bump the speed up and hold it there, and not at the first instance of idleness, drop back down.

Basically, having this feedback ltes you find out what is going on - is the user not caring, and thus you should pick the slowest speed that'll get things done? Is the user actively engaged in the device, but the usage is bursty, so you should go into a low power state after the processing is done, or is the user doing something that requires processor, and dropping down wastes power due to overhead?

Everything you say is true, but it makes vastly more sense to determine the amount of processor speed needed by what the device is actually being asked to do rather than trying to glean the user's mood and how that relates to required processor speed. Decoding an mp3 is a low intensity activity, and you don't need to know the user's heart rate or any nonsense like that to know you can afford to turn down the cpu frequency if that's all its being asked to do. Similarly, no matter how emotional the user is getting over the text message they are typing, the processor is still going to be sitting in its idle loop 99% of the time waiting for the next keypress so it's perfectly safe to lower the frequency there too. If they're doing something that requires a lot more processor, well, again this is obvious from the processor's point of view. And while the switches themselves are slow from the processor's point of view, they are too fast to notice from the user's point of view so it's perfectly feasible to switch from one to the other as processor load indicates.

So given that we already know how* to tune a processor's frequency to match the work being asked of it in a way that minimizes power consumption but never appears "slow" to the user, what exactly does this add? Is it for when someone starts playing a CPU intensive game on their iPhone, but isn't actually playing it? Yeah I'm sure you could save a lot of power by realizing that the user isn't in the same room as the device, so their Quake framerate really dosen't matter. So would an auto-shutoff after two minutes of no user input, and my phone already has that too.

* It's not like there's some proven ideal algorithm for it, but nevertheless existing devices do a pretty good job and are getting better.

Re:Waste of Time

[perryizgr8]

For a phone, you do not want background processing tasks - they force the processor to stay "awake" and drain the battery very quickly. Even a simple task that wakes the CPU up every second will easily cause battery life to diminish from the 2+ weeks standby to a few days.

i WANT my chat app to run in the background and STAY connected to skype and gtalk. i also want my sms and call spam catcher to run at all times. i don't care about battery life as long as it gets me through the day comfortably. seriously what use is a 2 week plus battery standby when you have chargers everywhere? in homes, offices, cars, wherever you have a laptop, fast-food joints, everywhere has chargers.

Is this dymanic?

[davidwr]

When I'm reading the news, the computer can freeze and I won't notice unless some animated ad freezes, in which case I'll be grateful.

But as soon as I wiggle the mouse or the clock is due to change, screen better respond.

If I'm playing WoW or watching a DVD, my CPU and GPU and the rest of the system better be operating fast enough to keep up.

Hmm...

[fuzzyfuzzyfungus]

Any word on how this compares to the current recieved wisdom of "when you have a job, do it as fast as possible, then go to sleep"?

I don't want to be "that guy on the internet who says it can't possibly work from the comfort of his armchair"; and I'm all for new and interesting sensor integration schemes; but this strikes me as the sort of problem that is already mostly solved with far simpler techniques.

We can already rank processes by priority, via nice or similar, and we already know a decent amount about user psychology(people hate waiting and find unresponsive interfaces enormously frustrating), and determining "what combination of speed states across time will execute this sequence of instructions with the lowest energy cost, subject to the desireability of having the results sooner rather than later?" is a solvable problem.

Can we really learn individual quirks, not covered by general rules, or is this basically a system that underclocks your phone until just before the point where your head explodes?

Re:Hmm...

[Actually, I do RTFA]

determining "what combination of speed states across time will execute this sequence of instructions with the lowest energy cost, subject to the desireability of having the results sooner rather than later?" is a solvable problem.

That assumes we want the results sooner rather than later. For most phone apps, this isn't the case. So you can get extra power savings if you know when you want the results. Which they guess by how annoyed the user is.

Re:Hmm...

[Pulzar]

Any word on how this compares to the current recieved wisdom of "when you have a job, do it as fast as possible, then go to sleep"?

That's not really the best way to save power for many situations. We already know that the best way to save power is by figuring out the lowest possible speed you can run at and still satisfy the user -- for bursty jobs, or realtime ones, that's easy... you adjust the speed until you get to the point where you're just fast enough to never idle. This is great for graphics chips, video decoding, etc. These guys are trying to figure out the lowest speed you can run your CPU at during other everyday tasks -- that's tricky to do by just monitoring CPU usage.

If you wonder why low constant speed is better than high speed + idling... It's because once you lower the clock speed, you can lower the voltage as well... and dynamic power being fCV^2, voltage reductions give you the biggest pay-off.

Re:Hmm...

[perryizgr8]

These guys are trying to figure out the lowest speed you can run your CPU at during other everyday tasks -- that's tricky to do by just monitoring CPU usage.

why is it tricky? just scale down to half when cpu usage is 0-5%, .75 when usage 10-50% and and full power otherwise. changing clock speed would only take a few nanoseconds i suppose? it works very well on laptops.

Re:Hmm...

[jonaskoelker]

is this basically a system that underclocks your phone until just before the point where your head explodes?

No, that would be hald-addon-cpufreq, sometimes gratuitously underclocking my box to one third of its natural speed, making firefox unbearably unresponsive.

(and thanks a bundle, Ubuntu, for overriding what I asked cpufreqd to do for me, because you of course know better, and thanks again for the ample documentation of hald-addon-cpufreq)

Thank you for listening; we now return you to your scheduled programming.

How is this new?

[idontgno]

I thought all machines had sensory technology with reacted to the user's activity state. I just look forward to this being used for something besides making the machine malfunction when I need it the most.

Way I read it

[Moraelin]

Way I read it, it'll just make sure it goes just fast enough to want to make you scream for real anyway. I doubt that faking screaming alone will take care of the other variables they mention. But being genuinely stressed, probably will. And they'll underclock the computer until they start seeing what they consider an acceptable level of stress, regardless of whether you're actually screaming or not.

I seriously wonder who comes up with that kind of ideas. If the user seems to actually be enjoying his experience at the computer for a change, by all means, let's start degrading his/her experience until he starts showing some stress.

And it's good 'cause you can save a few watts! At the expense of probably reducing the user's life expectancy a little due to a constant baseline of stress, not just make him enjoy that life less. But it's teh green!

How much self-hate does someone need to actually want to punish themselves to save the planet? I guess we'll soon know.

Re:Way I read it

[Missing_dc]

Sounds like they are running "Windows"

Re:Way I read it

[popeye44]

Sounds to me like my porn avi's will start stuttering.. right to the magic moment.. then it'll clear up and play right.

Re:Way I read it

[john_roy]

How much self-hate does someone need to actually want to punish themselves to save the planet? I guess we'll soon know.

That's one of the most selfish comments I've seen in a while. It's because of people like you that we all live under shit, you selfish bastard.
What's a few watts, sure. Multiply that for the millions that use computers and you have your answer.

Re:Way I read it

[Runaway1956]

Orly? Want to see real selfishness? Stand down at Walmart, and watch the fat bitches driving in with their huge SUV's. Skinny bitches too, I guess - but they are all to lazy to walk to a corner market for a gallon of milk. Nooo - we've just GOT to fire up that 300 - 500 hp engine, crank up the AC, and waste 2 or 3 gallons of gasoline to make that run to Walmart. What about the commuter crowd? Driving that gas hog as much as 100 miles each way, 5 days a week, because they are to damned good to live in the neighborhoods in which they work.

I'm with Moraelin - I want my computer to RUN!! If it doesn't, I might as well just push the damned bamboo shoots under my own fingernails. I'll tolerate a three minute boot-up (especially since I reboot very seldom) I'll tolerate a one minute login (again, I don't do it very often) and I'll tolerate (barely) my laggy internet connection. But, don't DARE try to throttle my damned machine down!!!!

If/when I feel the need to throttle it, I WILL DO SO, to suit my own personal goal.

Re:Way I read it

[PitaBred]

Depends entirely on what the "acceptable level of stress" is set at. There are very few times where a person will need a machine running flat-out all the time. Hell, I barely even notice that I have frequency scaling turned on on my laptop (it's undervolted too... lasts much longer on battery). And that's not even taking into account my mood.

Give these researchers a little credit... they use the devices, too.

Re:Way I read it

[hazem]

How much self-hate does someone need to actually want to punish themselves to save the planet? I guess we'll soon know.

I don't think it's self-hate that drives this thinking. Rather it's a desire to be aware of how one's day to day decisions have a broader impact on the planet as a whole - and choosing to limit that impact where possible.

The 19th and 20th centuries and the growth of industrialism and consumerism was based on the idea that resources are infinite and pollution negligible. Under those "constraints", there is no reason to constrain yourself - do what you want because there are not consequences. Sadly for us, those assumptions are not accurate. The resources are indeed finite, and the cumulative effect of the pollutants we produce are now measurable.

It IS indeed painful to shift from a "I can have and do whatever I want" mindset to one where you think about the impact of everything you do. The real problem is that it's impossible to track the impact of the behaviors of one person on the global system. _I_ can pee in the well and we all still have pretty safe drinking water. But if we all individually make that same choice, we all pretty soon have bad water.

As for this system, it sounds horrible and would most likely be abused in the worst way. The idea in one perspective sounds good... identify where resources are needed and increase them. But what you describe is more likely, particularly from a capitalist mindset - continue degrading the experience until it is just barely acceptable.

What makes much more sense is to make a little widget that can show how much energy is being used in a given state and let the user decide how much they might want to slow down the processor. If they care about saving energy, they can dial it down themselves to the level they can tolerate. If they want a faster experience (vital in number crunching and gaming), let them do that - and the widget can show the incremental cost.

In a similar way of thinking, they just installed a new "smart" electric meter on my house. I really hope I'm able to access the data from it. If I can get variable pricing based on peak load in the system, then I have a lot of incentive to time my dish washer, clothes washer, etc to do their work in the non-peak times. It saves me money and makes a more efficient load on the system. Everyone wins. Hopefully they don't screw it up.

Re:Way I read it

[john_roy]

First of all, I can't stand down in to Wallmart and I don't have any intentions too because I'm not an American nor do I live in the US. You do know that SUV's is mostly an American thing. But that's not the point, and I'm not going to make this an country issue, since we have the same shit over here. I must point out that I only use my car on the weekend's and I do use public transportation, but I know that's not an option to everybody especially in the USA.
About your comment, It's the kind of thinking that don't make you any better. I don't do "this" because the others don't do "that"... I don't buy an hybrid car because I want to squeeze a few miles per hour of my car and my car as to be faster than my neighbor's car. I want my quad core 3 GHz always at full speed even that I don't use 5% of my 4 CPU's most of the time.
Good thinking both of you. You should be real proud...

Re:Way I read it

[Runaway1956]

Don't worry - there will be a Walmart near you soon, along with one of those trashy McDonald's "restaurants". If not this year, then maybe next year, after some Euro or Chinese company buys Walmart out, and goes global.

Meanwhile - my 2.5 ghz machines will run full speed, 24/7. When I'm not actually USING them, they crunch Rosetta and Seti@home numbers.

Re:Way I read it

[john_roy]

Meanwhile - my 2.5 ghz machines will run full speed, 24/7. When I'm not actually USING them, they crunch Rosetta and Seti@home numbers.

Good for you. I see that you have are contributing to a greater cause. But I'm sure that even if you did run frequency scaling it wouldn't be any performance issue because as you probably well know frequency scaling identify when your CPU needs more than 5%.

I have a dual core 2.66 Desktop and my only regret is that the only allowed CPU freq are 2.00(75%) and 2.66(100%). If there was a 50% option on my CPU I will use it since I can't see the difference most of the time. When I'm compiling or playing Quake4 the CPU goes 100%. The only difference I've noticed is in the electric bill at the end of the month.

Re:Way I read it

[Spyder0101]

Assuming accurate enough readings, your complaint is a non-issue. Even without any readings, a very fine-tuned control that allows you to throttle it yourself would be great. This is not for use on a desktop, this is for mobile devices. What is more stressful; waiting an extra second while an app boots and being mildly annoyed before the device throttles up to finish a bit quicker or your battery dying in the middle of an important phone call? I know I'll waste a second for up to 50% more battery life.

Re:Way I read it

[SanityInAnarchy]

Point is, we really shouldn't have to make this choice.

Electricity is just electricity. It can come from coal or oil, yes. It can also come from a waterfall, or a nuclear reaction, or the wind, or the sun, even geothermal...

Saving a few watts, multiplied by thousands of people, still isn't going to make a tiny fraction of the difference of, say, replacing a coal plant with a wind farm.

No, I'm guessing they're mainly focusing on battery life for mobile apps. And I applaud them for that, but I don't know that I like this particular method. I'd rather have it jump right up to full throttle when I need it, without me having to get stressed. And I'd much rather see effort put towards better batteries, and generating electricity from other sources -- like movement, considering how much I might be walking around with a mobile device...

Re:Way I read it

[john_roy]

Ellectricity is not just electricity. We are now facing global energetic problems, and the increase of energy motivated wars is a proof of that. We are facing production growth for decades, and it's subsequent energy needs. The problem is that we don't have infinite energy, and if we don't stop now to think about how to improve our energy consumption, it will maybe to late in 50 years. Not to mention the ambient problem that this implies.


About that just tiny difference that you mention, I have to say I disagree. I don't think it's tiny. I think if we can change the selfish habits even if in a small things, it will make a major diference. Everybody agrees in responsabilize the others and the bigger polluters, but most of the people are not willing to change any of their habit's and abdicate their confort for a better planet. I think this is an hypocrite way of thinking and viewing things. As long as everybody thinks like this nothing is going to change and everybody is responsible.

We had a campaign over here a few years back about separating the garbage for recycling. No one was recycling garbage at the time. The campaign was made for children. It was a uge success. The adults soon realize that their children ask them way they don't split the garbage, and since they have no excuse everybody started to recycle their garbage. This are the small changes that change the world. The children today are going to be the politicians, the C.E.O.'s of tomorrow. If everybody don't do nothing because is too little, then nothing will change.

Re:Way I read it

[home-electro.com]

I moderated the story -1, stupid. CPU scaling based on system load works quite well, WTF they need to make up something as stupid as this?

Re:Way I read it

[Anonymous Coward]

I'm pretty sure mine already do!

Re:Way I read it

[Anonymous Coward]

nothing says that its going to keep a baseline of stress, i would assume that its going to find that baseline of stress, and then stay above it so as NOT to stress the user, yet still conserve energy

Re:Way I read it

[perryizgr8]

Meanwhile - my 2.5 ghz machines will run full speed, 24/7. When I'm not actually USING them, they crunch Rosetta and Seti@home numbers.

actually if you get a core i7, it will scale UP by 133mhz by itself when need arises. yes! above the rated clock speed!

Re:Way I read it

[linzeal]

No one thought resources were infinite or pollution was negligible during the 19th and 20th centuries. Wars were fought over resources almost every decade of the past 200 years and pollution has been noted and challenged by the populace that are affected by it since day one.

Re:Way I read it

[mgblst]

I have visited a number of southern towns, popular with the crowd you mention. The fact is they make it very difficult to actually walk into the store, they have a little fence around the whole parking lot except for when cars in. And a lot of towns don't even have footpaths. No excuse for being fat or driving suvs, but Southern America is built for cars.

Re:Way I read it

[mrmeval]

They do it to get federal money for useless experiments that generate papers that then get filed with prestigious journals now run by other losers that can no longer get federal money for useless experiments.

This is funded by the "National Science Foundation" where the 'science' is in the mind of some bureaucrat.

Re:Way I read it

[adolf]

But to add stress in order to shave a few Watts?

I'm all for cleaning up the mess we've made of things, but not if it makes my personal environment less tolerable by design.

I'm not masochistic enough for this technology.

Re:Way I read it

[GigsVT]

I really hope I'm able to access the data from it. If I can get variable pricing based on peak load in the system, then I have a lot of incentive to time my dish washer, clothes washer, etc to do their work in the non-peak times. It saves me money and makes a more efficient load on the system. Everyone wins. Hopefully they don't screw it up.

http://www.theenergydetective.com/store/teds/ted1000.html

You can get this for not much money.

Re:Way I read it

[Runaway1956]

I have always been partial to AMD chips. Over time, I have acquired an aversion to intel. My biggest single grudge against intel was the chip that broadcast a unique identifier to the world, in effect defeating any anonymity if bad guys chose to track your internet usage.

But, the main reason I'm answering you? To say I love that sig!!! The Hurd likes to spin things to inflate their egos, but it's Linux that runs my machines. Nice educational rant there. :-)

Re:Way I read it

[daveime]

Yes well when the increase in cardiac arrests leads to increases in defibrillator usage, at least you'll have saved plenty of watts to power them won't you, you lemon.

While it might seem like a good idea to save a Watt here and there now, without considering the future consequences, you might end up using more later. It's called False Economy, just like goverments who always go with the lowest bidder to save pennies now, and then end up paying thousands of dollars extra in the long run through crappy workmanship, substandard materials etc.

That's the problem with most "green" solutions is that they are too much like carbon credits. You see the operative word is "credit" ... borrow now, and pay later.

In any case, saving a watt here and there on a personal level doesn't make the tinyest scratch in the big picture. 2005 average global energy consumption was about 1.5 Terrawatts i.e. 15 followed by 12 zeros.

Re:Way I read it

[perryizgr8]

yay! it irritates me to no end when someone keeps saying 'GNU slash Linux'. stupid people will blindingly accept any propaganda thrown at them. at least we refuse to accept any bearded disillusioned person's authority. that's what open source and linux are all about.

Re:Way I read it

[batman567]

i'd rather have my CPU running at 100%, than to have it running at 70%, and the other 30% being used to monitor my eyes, skin and nervous state of being!!! as for saving the planet - i doubt if the savings of 1 million of these "intelligent systems" would undo the unnecessary wastage that ONE solitary BMW X5 V8 (or Merc M class, or any other behemoth SUV)is causing.

Re:Way I read it

[john_roy]

Yes well when the increase in cardiac arrests leads to increases in defibrillator usage, at least you'll have saved plenty of watts to power them won't you, you lemon.

What a bad analogy, I must say.

Anyway, the Idea of this post seams idiotic. But that's not what I am discussing.

So what are you saying? People don't pollute at personal level? We can spend as much as we like because it's not going to make any difference?

You are being argumentative. You are pulling the classical minimization/exaggeration of the problem to minimize the personal use of energy. But I can even play by your rules if you like. First 1.5 Terrawats is not 15 followed by 12 zeros. It's 15 followed by 11 zeros. But you are right about 15 Terawatts. But even if everybody saves just 1 watt we are talking 6 Gigawatt's (6 fallowed by 9 zeros). But we are not talking just about 1 watt do we? If we just save 100W per persone we are talking about 600 Gigawatt's worldwide. If we can save 1000W per person... well you know the math. And I'm not talking about something not doable. 1000 Watt's per person is nothing

I find that most problems are complex by nature and this is no exception. Trying to simplify does not help from my point of view. The problem isn't a watt here or a watt there. The problem is about what you are willing to do to change the planet. And for what I'm seeing isn't much. If everybody thinks that can't do the difference then no change will happen. It's a problem of mentalities. It's a problem of global conscience that very few seem to have.

And we can do much at personal level.

Re:Way I read it

[daveime]

Okay I'll bite.

Yes, I dropped a decimal point somewhere, your are correct on the number of zeros.

But then you also try to play the numbers game with your "if every person on the planet did XYZ".

There are an awful lot of people on this planet who don't even HAVE electricity, never mind a mobile device to save those odd Watts.

A country like US has an average of 11kW per person usage, while Bangladesh has an average of 0.2kW per person usage.

If we can save 1000W per person

No, you can't simply scale up the math ad infinitum, multiply it by 6 billion people and still sound credible.

Realistic goals for energy efficiency require tangible quantities for it to work. Percentages are meaningless when you are talking about devices that require a miniscule fraction of the energy required to power say a 5 liter SUV, or a home temperature control system.

You want to make a difference ? Ban all car engines above 1.6 liter. Mandate all homes to be fitted / retrofitted with proven insulation technology. Develop realistic alternative energy sources like wind, wave and solar.

Don't just shut off my screensaver because it consumes 0.001 W more off than it does on. It's like avoiding pissing in the ocean in case it becomes too salty.

Re:Way I read it

[john_roy]

I agree most of what you said. Unfortunately it seems that someone will have to put some limits.
I'm talking Unfortunately because it could be avoided without those drastic measures.

I didn't make any scientific study of how much will save the planet if we reduce the CPU consumption nor do I want to make any point on that specifically. I've just reacted to what I tough was a selfish comment, that expresses the general idea(that's what is revolting to me and no one in specific). I'm not imposing my ideas here but I do get angry when all I see around me is people that talk about the others and are not willing to do anything themselves. It's especially revolting when we are talking about something that belongs to all of us, and few respect.

This is not about winning some debate on a flame war. This is mostly for us to get over our egos, look away from our computer, and meditate not on what we've been doing, but in what can we do to make the world just a little better. If people start to think like this instead the easy way maybe, and then maybe we can do a better tomorrow.

Re:Way I read it

[borizz]

Seriously? It's a chore to push the timer button on the dishwasher so that it starts in off-peak hours? That shouldn't stress you out.

Re:Way I read it

[castironpigeon]

I seriously wonder who comes up with that kind of ideas.

Catbert

Re:Way I read it

[adolf]

Seriously? Did you know it was a discussion about stress-based CPU throttling? WTF. Over!

Re:Way I read it

[SanityInAnarchy]

The problem is that we don't have infinite energy,

True, but I don't plan on living another 4-5 billion years to see the sun burn out. Within that timespan, we really do have about as much as we need.

I don't think it's tiny. I think if we can change the selfish habits even if in a small things, it will make a major diference.

If that major difference is still only a few fractions of a percent, that's really not going to reduce demand for alternative energies, or prevent a single energy-motivated war.

You mentioned this:

We had a campaign over here a few years back about separating the garbage for recycling. No one was recycling garbage at the time.

See, even per person, that is a huge difference, and has a pretty negligible effect on our daily lives -- it takes the same amount of time to toss a jar into the recycling bin as it does to toss it into the trash.

This, not so much -- a tiny effect on battery life, perhaps even counterproductive (slower response time means I have to spend more time with it powered up, versus letting it go to an extremely low-powered sleep mode when I'm done with it),

It's not hard to come up with the best of both worlds -- I'm typing this on an 800 mhz laptop. Actually, it's a 2.51 ghz laptop that is currently clocked down to 800 mhz because I'm not using it. The second I need it, the power is there. THIS is the kind of energy efficient technology I can appreciate.

What you're suggesting, if anything, is more like me forcing it to low-power mode, so it's always exactly 800 mhz. I'm sorry, but that's not worth it.

Repurpose the SysRq key

[Mal-2]

What good is the SysRq key? Repurpose it as a way for the user to say "please assign more system resources to whatever is in the foreground". If this can be done by clocking up, great. If the CPU is maxed out, then bump up the priority of the process. If there's nothing left to give, then the system beeps or throws a "tough shit, you bought the $100 computer" dialog box.

It does not seem like fundamentally new technology is necessary for us to be able to tell the computer it's lagging unacceptably. That doesn't necessarily mean it will be able to DO anything about it, but at least we can vent.

Mal-2

Re:Repurpose the SysRq key

[Anonymous Coward]

"tough shit, you bought the $100 computer" dialog box.

Even a half million dollar Cray would bow down to a Vista system running Crysis.

Re:Repurpose the SysRq key

[tagno25]

What good is the SysRq key?

It is very helpful when you have a kernel panic. It lets you safely unmount and reboot the system.
On another note the Windows kernel panic (not BSOD) in Vista looks and behaves just like it does in Linux.

Re:Repurpose the SysRq key

[cibyr]

I use that key still... how do you take screenshots?

And Alt+SysReq+{R,E,I,S,U,B} can safely reboot a locked-up linux system if the "Magic SysReq Key" kernel option is enabled.

Re:Repurpose the SysRq key

[Mal-2]

Ctrl-PrtSc or Alt-PrtSc depending on whether I want the entire desktop or just the single application. I don't use SysRq *alone*.

Mal-2

Re:Repurpose the SysRq key

[Sir_Lewk]

how do you take screenshots?

PtrSc, on the same physical button as my SysRq key.

Re:Repurpose the SysRq key

[perryizgr8]

is there really a kernel panic in vista? i did not know the kernel was distinct and well defined in windows.

Correct CPU frequency

[Capt.DrumkenBum]

What a useless study. I can tell you what system I need.
The correct CPU and frequency is currently a 100GHz 16 Core beast with 4TB of RAM. Of course I will NEED a machine that is twice as fast in 18 months.

Re:Correct CPU frequency

[Voyager529]

But can it run Vista?

Re:Correct CPU frequency

[perryizgr8]

yes of course! but not vista AND crysis SIMULTANEOUSLY.

Waste of effort for negative gain

[Anonymous Coward]

This is a huge waste. It's much more efficient to get the processing done as fast as possible and then put the CPU to sleep until there is more work to do. If you slow everything down, the CPU is working longer which takes more power.

Software based

[tagno25]

Why not just do like Linux can and does, have 4 settings that control how the processor functions.

I have the option between Conservative, Ondemand(Increases when processor usage is needed), Preformance(always at max), and Powersave(always at min). When my laptop is unplugged then it runs in powersave mode, but when plugged in then it is in ondemand mode.

Re:Software based

[retchdog]

1. Windows works almost exactly the same way, except with a moronic additional "degrade" option which is usually disabled nowadays.

2. If you have occasional spikes of demand (as opposed to continuously running job/game), "powersave" probably uses more power. It's more efficient to spike the proc to max for a few seconds; finish the job; and go back to mostly-idle.

Or in other words...

[macraig]

... using a mood ring to control the CPU? The hippies will love it!

I wonder...

[Anonymous Coward]

...what CPU frequency they'd give this kid

http://www.youtube.com/watch?v=kBVmfIUR1DA

scientology's tech stolen!

[TomR teh Pirate]

This is the same technology the guy working the Scientology booth at the local mall uses when he asks you some questions that are none of his business. Of course you're squeezing it harder; you can't wait to tell the guy he's an idiot.

Re:scientology's tech stolen!

[pxc]

Actually, those things measure electrical resistance and display it with the leftmost part of the gauge representing resistance greater than current, and the right side representing no resistance.

The last time I was downtown, I decided to test this as I walked by a Scientology booth. During my "free stress test", I touched the two cans together, and the needle jumped all the way to the right.

Spam...

[Anonymous Coward]

This paper was cute and pointless the first time I read it. Congrats on being the least technical paper in MICRO last year, now stop spamming your research to Slashdot.

Excellent

[kramulous]

Good that there is thought to this.

Kinda like tuning your codes to run really fast, then the poor monkeys in the basement send you a IR photo of some power couplings and ask what you're doing. I've always been going for flops but it has been getting a little more difficult now that I bring in power consumption into the optimisation cycle.

New measurement for the top500
flopspw ?

Re:Excellent

[kramulous]

Sorry, that new performance measurement should be
flopspa

Re:Excellent

[jpmorgan]

You might be surprised, but a lot of commercial HPC sales are already based on flops/watt.

Lots of companies make extensive use of computational models these days, but have offices in older buildings that don't have sufficient power infrastructure. When your power supply maxes out at 50kW, flops/watt becomes more important than straight flops.

Re:Excellent

[Jherek Carnelian]

New measurement for the top500

It's called the Green500 list.

Seems rather retarded

[Sycraft-fu]

I always want my computer to complete any task that I have to wait on as fast as possible. I don't like waiting if I don't have to. Thus, all necessary power should be thrown at a given task. The time to scale back, is when it is waiting on me. If I'm not giving it something to do, it can throttle back and idle.

However, we already have this technology. New processors and even videocards now do this. That is the technology that needs improvement. Have lots of power available, and only crank it up when there is a need. The idea being that the user never has to wait on anything, but the computer uses only the power necessary to complete the given task.

I don't want my computer sandbagging and only going half speed because it thinks that's "Good enough for me." No, go the speed the task you are doing demands (or full speed if said task needs more power than the system has).

Re:Seems rather retarded

[camperdave]

I don't like waiting if I don't have to.

Perhaps you'd like a tee shirt.

That's actually just the start

[Moraelin]

Actually, I'd say that's just the start of the problems. The next problem will be that half of anything you install nowadays, will want to preload itself or parts of itself in your tray, or install some services, or God knows what else.

And I'm not even talking proper spyware. E.g., even when I install OOo, the first thing I have to do is deactivate its preloading itself. 'Cause obviously they thought my RAM is there just so they can willy-wave about loading faster than MS Office, instead of fixing their brain-dead code to actually be fast. (Though apparently in the last release they actually did get around to optimizing a bit for a change.)

E.g., I install Sun's Java, 'course, it has to keep something in the tray just to make sure it can pester me to download the latest release I don't even want.

E.g., I install my old Audigy 4's software after moving it to another computer, and I promptly remember what I hated about its software in the first place. By default it installs a brain-dead bloated skinned second toolbar, so to speak, just in case I'm too stupid to launch its control pannels normally. And so it can get in my way when I accidentally move the mouse to its edge. It also installs stuff like its own CD/DVD detector (and launcher of the apropriate program for it), for no obvious reason, since Windows already does a perfectly good job there. It also blesses my computer with a bloated, slow loading splash screen, 'cause obviously doubling my computer's startup time is perfectly ok if it lets them shove in my face again that it runs an Audigy. Obviously my time and RAM are there just so they can advertise to me. Etc.

I'm not even singling out OOo or Java there, mind you. Lots of others do the same.

And then come the games, with their retarded DRM drivers and whatnot.

My point is that it used to be a time when you actually had to get virused or click on spyware to get half a gigabyte of your RAM full with crap. Increasingly in the last decade, you don't even need to do that. Just installing perfectly legit software can make your computer swap, if you're not savvy enough to find that crap in the registry and disable its auto-loading. Sometimes twice, because some are smart enough to re-enable themselves.

Re:That's actually just the start

[Anonymous Coward]

Don't worry, it's as bad in linux now. Install a modern distro and even after you swap over to a lightweight desktop you'll have hald, dbus, pulse audio, gnome-settings-daemon, gnome-keyring and a few other pieces of shit conspiring to turn what should be a perfectly usable desktop machine to the equivalent of running a in VM on the same hardware 18 months ago.

Re:That's actually just the start

[Anonymous Coward]

Start-Run-msconfig-chose "Selective startup"-go to the startup tab, uncheck all unnecessary.
Sheesh.

Re:That's actually just the start

[ShooterNeo]

That doesn't actually kill anything that runs as a system service... Also, some programs will re-add themselves to that menu.

Re:That's actually just the start

[Voyager529]

Rant Warning

The worse offender I've ever come across was when LG and Samsung included tray-resident apps...FOR FIRMWARE UPDATES! There is something seriously wrong with your drive if you need to have it constantly checking for new firmware, only eclipsed by the retarted thinking that people will be able to flash the firmware in the drive and NOT brick it.

Okay, I'm done with my rant. I wholeheartedly agree though, it seems that software devs have confused the system tray with the start menu. No need for 90% of the stuff that starts with computers to start with the computer by default.

Re:That's actually just the start

[TJamieson]

By default it installs a brain-dead bloated skinned second toolbar, so to speak, just in case I'm too stupid to launch its control pannels normally. And so it can get in my way when I accidentally move the mouse to its edge.

They still have that shit in their software? I remember being annoyed by that 10 years ago with my SBLive.

Re:That's actually just the start

[Anonymous Coward]

I switced to ubuntu 9.04, and everything runs great without any tweaking. Everything I need is preloaded, and I can download anything I may want simply by searching for it in "Add\Remove" or synaptic package manager.

Re:That's actually just the start

[iris-n]

Apparently you haven't noticed update-manager, that wastes 4 M of RAM to do a job that cron would take half a K to do.

Re:That's actually just the start

[Xyde]

Chatlog with friend:

<Me> why does windows software have splash screens
<Me> for things like, wireless driver software
<Me> hmm its been sitting here on the screen, frozen for over a minute now
<Him> or say, your printer
<Him> i'm so proud of my printer, and assorted accessories that I enjoy having my computer present a tv-sitcom style credits roll every time it starts up
<Him> oh here is the funny character who pretends to do work, but always is sleeping on the job
<Him> oh crazy Canon, you're such a character!
<Him> oh look here comes ATi and some random taiwanese sound chip that looks like a crab
<Him> what cute characters, they're why I watch this show
<Him> what would life be like if i didn't have a tray icon indicating to me when I was pushing on the trackpad
<Him> that's so handy, I always get confused you know
<Him> am I pushing on the track pad right now?
<Him> or is it my crotch?
<Him> i always mix them up, so handy that there is that little on screen icon there all day showing me
<Him> oh look, there are a bunch of quick to reach options, even though I'd never configure this more than once in my lifetime
<Him> good thing there are keyboard shortcuts to get here, woah, you know those scroll bars I assigned when I bought the laptop - I need to change those so frequently that I definitely need a keyboard short cut to get there
<Him> I didn't order crabs with my soundchip
<Him> and yet, here it is
<Him> just like crabs: they always come when you don't want them
<Me> don't forget the horrible interface
<Me> for 3D sound
<Me> with lots of bad gradients
<Him> this menu it needs more over compressed jpeg
<Him> and all the configuration options need to be laid out as giant long textual choices
<Him> with tabs
<Him> oh and can we put a help in there
<Him> it doesnt need to say thing other than "this option controls a sound option"
<Him> that's plenty of information for consumers

Re:That's actually just the start

[Anonymous Coward]

E.g., even when I install OOo, the first thing I have to do is deactivate its preloading itself. 'Cause obviously they thought my RAM is there just so they can willy-wave about loading faster than MS Office, instead of fixing their brain-dead code to actually be fast. (Though apparently in the last release they actually did get around to optimizing a bit for a change.)

MS office does the same, but without telling you. OOo has a system tray icon.

Re:That's actually just the start

[ion.simon.c]

What's update-manager's resident size?

I don't use Ubuntu, so I can't check for myself. :(

Re:That's actually just the start

[jonaskoelker]

'Cause obviously they thought my RAM is there just so they can willy-wave about loading faster than MS Office, instead of fixing their brain-dead code to actually be fast.

Right now I'm using 600 megs out of 2000 (not counting 225 megs of buffers and 872 megs of cache). Sure, the cache speeds things up; could that memory be better spent on caching something else?

In some cases, I think it makes great sense to cache ready-to-run applications.

Re:That's actually just the start

[Anonymous Coward]

CD writing firmware? Not upgrading the firmware to support new media formulations is probably the a cause of a significant number of tech support calls.

Re:That's actually just the start

[Anonymous Coward]

Sounds like you need a dose of Linux. OO etc. doesn't try to preload. Application updates are done by the package manager, as they should be, so apps don't load some update checker. And drivers are drivers, they don't load a big sack of crap with them. 512MB of RAM? No sweat, Ubuntu'll do it all in 256MB. (And it's not even considered a slim distro.)

Blackberry Storm

[Anonymous Coward]

Does it automatically overclock the Blackberry Storm so that it shows some semblance of responsiveness?

Another idea

[Anonymous Coward]

Or, instead of slowing down the system until the user is annoyed, you could just give them a slider bar somewhere to decide between "Fast" and "Low Power Usage." That way you're not stealing control from them and hacking them off.

Just No

[jvkjvk]

I want my computing experience to be pleasant, not have the power turned down until I am stressed at how slowly things are going and then have it ramped up again.

Sorry, but I have enough stress as it is without artificially adding more.

It's like we are becoming monkeys jumping through flaming hoops just to satisfy the computer! Bah.

For the system's icon...

[Anonymous Coward]

A Talosian's head appears: "Wrong thinking is punishable. Right thinking will be as quickly rewarded."

This will be fun...

[rickb928]

They measure the user with eye trackers, galvanic skin response, and force sensors to find a CPU frequency that the user is satisfied with. They are currently studying user activity and system performance on mobile architectures, specifically the Android G1 phone."

Yeah, so that's why my G1 keeps asking me to turn it over, so the camera can track my eyes. Perhaps they should try tracking the acclerometers so they see them max out when the battery goes dead and I heave it one more time into the trash, only to pick it out again and recharge. Yeah, that's sure scientific. Good work there.

Or maybe they are working with the other Android phone on the market that has a user-facing camera.

For a phone, you do not want background processing tasks - they force the processor to stay "awake" and drain the battery very quickly

Yup. Stop calling my G1 a phone. It's a handheld. Phones have reasonable battery life. There. Carry on.

Another great stride for AI

[Anonymous Coward]

They have invented a computer that goofs off whenever you are not looking.

Re:Another great stride for AI

[twidarkling]

Damn. First time I ever laughed at a comment on here.

Strange... some would say I do this at work...

[Solarbeat]

In the words of the immortal Homer Simpson: "You just go in there every day, and do it really half-assed... that's the American way!" My wife would probably say that I do this at home too (I just opened myself up for all sorts of insults there).

Rent costs

[tepples]

What about the commuter crowd? Driving that gas hog as much as 100 miles each way, 5 days a week, because they are to damned good to live in the neighborhoods in which they work.

In a lot of cases, the commuter crowd lives this way because the gas is cheaper than rent near work.

Re:Rent costs

[Runaway1956]

I'm sure that reason applies to some. In many cases, work is in an unattractive neighborhood, and the commuter has CHOSEN to buy/rent a home in a more "upscale" neighborhood. The last time I posted on the subject here at slashdot, some broad demonized me because she commutes like 35 or 40 miles. Her excuse? Her school age children deserve the best schools. Phhhht.

Re:Rent costs

[MrCrassic]

Actually, I choose job locations far from my home because it's more miles for me to bike, but we're the minority.

Re:Rent costs

[Anonymous Coward]

Well then hopefully scarcity of oil will take care of that sooner rather than later.

Re:Rent costs

[tepples]

Well then hopefully scarcity of oil will take care of that sooner rather than later.

It's not guaranteed. A decline in the supply of crude oil might not drive up the price of personal transport if natural gas vehicles, biodiesel vehicles, and plug-in vehicles powered by wind or solar thermal electricity become popular.

Re:Rent costs

[adolf]

I commute, but I didn't choose to.

I live in a nice, small city (about 40k) in Ohio. I've lived in the same town my entire life. I worked for a local branch of a slightly regional company. They closed the division I worked for, and moved my job to their home office, 30 miles away.

They paid hourly for my drive time, and for my gas. The arrangement has changed some now that I drive a company truck instead of my own car, but it's still similar to what it was.

Now, I like my job. And I like my town. And I'm a homeowner (and also was one when my job moved). I'm not moving to that other city (let's call it Ghettotropolis, complete with burned-out houses, street-walking hookers, and lots of crack), for any amount of money. Where I come from, folks lock their doors sometimes. Where my job moved to, crackheads will smash your car window to get the change out of the ashtray.

Not. Fucking. Happening.

So, what to do? Do you propose that I find another job nearer to home? Nevermind that there aren't even any local companies which are in even remotely the same trade.

I do work from home quite a bit, nowadays, which helps. But still: I haven't CHOSEN to commute. I've only chosen to keep my job. And it's a good job - in a time of cutbacks and layoffs and late bills, this company is having the best couple of years that it's ever seen.

It isn't always someone's personal decision to be a commuter.

Re:Rent costs

[Runaway1956]

I don't think that I implied that ALL commuters are selfish bastids. Just "many" of them.

Houston is a good example, which I am pretty familiar with. They built the suburbs miles away from ANY businesses or industry, intentionally far from the "undesirables", and attached ridiculously high price tags. And, every aspiring "anybody" snatched those high dollar housing projects up at ultra-inflated prices. There are probably a million heads of household in the Houston area who are "to good" to live in the old 'hood with the homies. And, they justify this elite lifestyle in a number of ways - all of which demonstrate that they are unwilling to work to make the city a better place to live.

Personally - I commute 25 miles. I live in rural Arkansas. It's 25 to 40 miles to town, depending on which direction I go. Unless I build a hog house or a chicken house, there is NO industry near my house. But, the wife's family owned this land before the Louisiana purchase, and we ain't goin' nowhere either.

But then, we aren't "elite", and we don't drive 12MPG gas guzzlers either. ;-)

Re:Rent costs

[kingofwaldos]

What are you talking about? Your post is full of decisions you made. You may not feel you have a choice, but in fact you just don't like the other choice. You job moved to the city, you chose to move with it rather than quit. You already have a house, you chose to stay in it rather than move to "ghettotropolis". I'm not saying that I would choose differently (I commute 30 miles myself), but to say you had no choice is wrong.

Re:Rent costs

[adolf]

It ain't "the city." It's another small town in Ohio, that happens to be a whole fuckton dirtier than I wish to tolerate, and about 30 miles from here. Ohio only really has about 5 cities, proper: Cincinnati, Columbus, Dayton, Cleveland, and maybe Toledo. This isn't any of them.

And, yeah: I guess you could say I chose not to try to sell my house in one of the most down realestate markets in recent history. But then you might also say that I've simply chosen not to be a fucking fool.

How about a shock sensor

[billcopc]

I'd like a computer that speeds up, every time I smash the keyboard or mouse in anger, you know, like a human would...

That should be easier to implement than my previous suggestion, which was a speech recognition algo that interprets swearing in various languages and can tell the difference in intensity between "Ah crap" and "STUPID F&@#IN' GODDAMNED TABARNAK MOTHERF&*@&#$ OUTLOOK!".

Re:How about a shock sensor

[jonaskoelker]

That should be easier to implement than my previous suggestion [...] F&@#IN' [...] MOTHERF&*@&#$

Actually, that's pretty simple. There's a sample implementation in /home/larryw/perl/trunk/parser/tokens.c.

Re:How about a shock sensor

[Anonymous Coward]

You meant tabernac. You get -1000 points for swearing incorrectly in Quebecois French.

You also get -10000 points for being either a poser or an illiterate. If you're a Quebec Francophone, you are illiterate for not knowing how to spell a common curse. If not a Quebec Francophone, you're a poser for trying to look like you know a foreign language when you obviously do not. Fucking loser.

Morons

[oldhack]

Time to burn some karma points.

Tell me one advantage this knucklehead idea possesses over having a simple slider/dial to adjust processor speed.

Re:Morons

[John Hasler]

> Tell me one advantage this knucklehead idea possesses over having a simple slider/dial
> to adjust processor speed.

It is suitable for knuckleheads who couldn't deal with such a slider.

Re:Morons

[oldhack]

Man, would you lay off Apple people?!

Re:Morons

[AK Marc]

Tell me one advantage this knucklehead idea possesses over having a simple slider/dial to adjust processor speed.

Because a user will always over-estimate the power he wants and the sliders will be stuck in the "most power" setting even when that isn't necessary. So this sets them as to how the user "feels" about the speed, rather than what they think it should be.

Re:Morons

[Veggiesama]

A slider? Everyone knows Mac people use a wheel.

Remember, this is on the Android G1 phone ...

[gun26]

... so, presumably, this isn't really about improving the speed but is instead a desperate attempt to get an actual full day's use out of the G1 before it has to be recharged. Reach for those stars, boys. :)

Re:Remember, this is on the Android G1 phone ...

[peragrin]

There is a reason why apple has stupid limits on background apps, and push notifications, and etc, etc.

Now if they could only allow user replaceable batteries. though still I get ~2 days between charges with moderate 3g and wifi browsing and turning off the wifi and bluetooth when not in use.

Re:Remember, this is on the Android G1 phone ...

[Mr2001]

There is a reason why apple has stupid limits on background apps, and push notifications, and etc, etc.

Except for their own apps, of course. Because Apple has never written a single line of buggy code, right?

Now if they could only allow user replaceable batteries.

There is a reason why the G1 has a replaceable battery. ;)

Not really needed

[Sycraft-fu]

A modern desktop (Windows desktop at any rate, presumably other OSes too) already does a lot of this. By default foreground threads get priority so you'll find that the foreground app gets to gobble up lots of CPU time if it wishes.

As for the clocking up, that is a hardware function that modern processors support well. My Core 2 Quad idles at about 2Ghz, which translates to a 6x multiplier. That's what it'll be running with system tasks going and a web browser and other such non-intense stuff. Now if I fire up something that hits the CPU, it clocks up to an 8.5 multiplier, which is 2.83GHz, it's rated speed. My graphics card does a similar thing, though with even larger clock deltas.

So we don't even need a key for users to press. All we need is further improvements to the existing technology. For example my processor could probably scale its speed even further. It also could potentially shut down ancillary cores. Though I have a couple hundred threads running on an idle system, most are doing little thus it could easily shut down two cores, clock the remaining two down, maybe one of them way down. So long as the time to restart the other cores and clock up was fast, it wouldn't be a performance or responsiveness problem.

We already have the technology we need, and it already works well. We just need to continue to improve it.

farts

[NicknamesAreStupid]

Why don't we just plug them into out butts and run 'em on methane. Mine would clock 10THz.

What does this solve?

[MrCrassic]

I peered through the paper, and I don't exactly see how throttling the processor to very low speeds (lower than Speedstep) when idle solves less than optimizing CPU clock speed based on user activity. When properly configured, the speed "bursts" are as short as the burst is needed (i.e. when loading a program, or when compiling), and multiple step levels ensure that the CPU isn't going from minimum to maximum instantaneously (though this behavior can be configured).

Maybe I just missed the point.

Holy crap!

[mmaniaci]

IMO, this is a terrible idea. Microsoft has tried to "interpret" what the user wants for decades and that didn't only fail, it made Windows one of the most annoying products on the planet. The last thing I want is my PC to constantly "interpret" me to figure out how slow it can run, more than likely keeping me at a constant level of aggravation in order to save a few mW. I'd rather my computer amaze at how fast it started up Firefox for once, not that it shaved $0.05 off my monthly power bill by throttling itself while I pull my hair out and smash my peripherals. This is not about going green, this is about a group of PhD's (or PhD students) trying to save their previously hip project (or thesis) by farming some hype off of /.

Re:first post

[Anonymous Coward]

If your troll account has positive karma, you fail as a troll.

cheque please.

Re:first post

[Anonymous Coward]

i > u

But less power means more energy!

[snowdon]

We did some work recently where we showed that in a lot of cases, running the CPU at a lower performance point actually resulted in more energy usage -- scaling down the CPU frequency means everything takes longer to run, which means that you get less time to spend in low-power idle modes. There are also a lot of other complexities with frequency scaling... Particularly on a platform like the Android where there would be multiple scalable frequencies, etc.

There's a whole lot of other problems with the slower-is-better approach... But check out the paper we've just published.

As a measure of QoS, I think this is quite cool work, but the way they translate this into frequency scaling seems broken.

Koala: A Platform for OS-Level Power Management

Just what I need..

[dexotaku]

Great. Just what I need - a computer with an attention span potentially shorter than mine.

Overclocking it, using Jim Carrey!

[G3ckoG33k]

Test it on Jim Carrey! Can't wait to see the overlocking results!!!

.

Re:first post

[Lord Bitman]

you've never actually had negative karma, have you?

desktop comparisons

[fuliginous]

Interesting potential for determining what people really think of Gnome v KDE, Linux/Gnome v Windows Vista v Xp etc

88 megajoule per year saved; not that much?

[jonaskoelker]

The power consumption was 29.1 W [lowest] and 31.9 W [highest]

That's a 2.8 watt difference. Over a year, that's 88.4 megajoules, or 24.5 kilowatt hours (*).

Not knowing what your power company charges you, you'll have to figure that out for yourself.

It's always nice to know whether it costs nickels or dollars :) ... Assuming of course you make the "meaningful" choice to have your system turned on but idle, instead of it being max-clocked and doing make-work. Shrink the dollar amount by your real savings percentage (50%? 10%? 1%?).

(Of course, trees don't grow on the money, but on healthy planets.)

(*) figures thanks to GNU units: (2.8 W * year) and (2.8 W * year) / (kW * hour); some decimals were chopped.

Isn't that hard to know if processing power...

[pwilli]

... is needed.

A small application, that monitors CPU usage:

If on average (far) below 100% for multiple seconds, scale down
If on average (very) close to 100% for multiple seconds, scale up Basic functionality of any modern chipset in desktop systems, works like a charm. If the user does some obscure thing that will lead to non-optimal scaling with the previous method, he may set the frequency manually (I use "SpeedSwitchXP" for that). Problem solved.

I really don't see how having a process to capture and evaluate data from sensors/camera that _always runs_ will help to save any energy, especially on embedded devices.

Alternatively just give the user some physical buttons or maybe a wheel (sthng. like on headsets for volume control) to choose the speed for his embedded device.

Only part of the equation

[nurb432]

They need to take into account what is being processed in the background too.

Don't want a compilation slowed down just because you get bored and nod off.

Alabama hick: Tell us about IRAM & if URA code

[Anonymous Coward]

Ion.simIAn.c, you alabama hick - Prove what you claimed about being a programmer (because all your errors from the past week now & more don't show any of us you are that is certain, lol!) & tell us more about the Gigabyte IRAM being a piece of trash (it works on Windows, but not Linux according to YOU @ least, so what is the "trash" here? Obviously the OS you use & its SATA access most likely).

"I'm a programmer." - by ion.simon.c (1183967) on Saturday May 02, @11:17PM (#27803057)

Really? Ok, same question you asked ME to prove & I did via the lists below you no longer question (along w/ other proofs I gave you but when YOU are asked for the same proofs? YOU RAN!)

SO, that "all said & aside"?

Prove to us you are a professional programmer, ion.simIAn.c, won't you?

After all, you CLAIMED that you are above, & demanded others do so as well, here:

"You claim that you're a professional. Prove it" - by ion.simon.c (1183967) on Sunday May 03, @08:52PM (#27811101)

OK - See the lists below (contact the magazines, publishing houses, or software companies involved @ your discretion, if you wish)... because it truly IS a pleasure watching you stick your foot in your mouth, each time you falsely accuse myself & others here.

So - professional technically means getting PAID to do a job, right? That's there below in the "My Name is Ozymandias, king of kings: Look upon my works, ye mighty, and despair" list, in fact, 1st entry...

AND

I've answered ALL of your questions (the ones that matter, & I did so, w/ out writing out a book to do so), here -> http://tech.slashdot.org/comments.pl?sid=1219095&cid=27806379 & here also -> http://slashdot.org/comments.pl?sid=1219095&cid=27853857

Funniest part is? When I and others (MEK_LoveBug) asked YOU to prove YOU ARE A PROFESSIONAL PROGRAMMER, as you claimed you were? You RAN, lmao!

----

"Google failed to find any offical mention of your work with Russinovich" - by ion.simon.c (1183967) on Monday May 04, @10:57PM (#27825779)

GOOGLE didn't fail, YOU DID (as usual, per this reply AND the list of your screwups here I enumerate below in this exchange)...

See this -> http://www.pcmech.com/article/defragging-the-windows-page-file/ (& the comment by "SuperFluid" there)

YOU can't even GOOGLE something right, lol...

You're only showing yourself as what you really are: Nothing more than a "I can't do anything w/out GOOGLE" type online...

SO, AGAIN - YOU say you're a programmer? PROVE IT!

(So, how do you like it? After all, that's the kind of crap you've been saying to me & I provide proof below... and, you do not, & YOU have NOTHING LIKE THE LISTS I PROVIDE BELOW, to your credit)

----

"I've emailed Mr. Russinovich to figure out what work that you've done with him" - by ion.simon.c (1183967) on Monday May 04, @10:57PM (#27825779)

For Sunbelt Software (I'll save you the time there) to whom we contracted out wares we had written, thru LC Tech!

(& also MANY years later, in 2003, when I fixed up his pagedefrag program, instructing him where it was hardcoded and how/why it could adversely affect the operations of his application if people moved their pagefile.sys location AND eventlogs (which is doable on both accounts, & he STILL has a hardcode to the latter) to another disk (he had them hardcoded to C: drive only, & it made his program fail). In the end? Well - he emailed me back thanking me in fact.

----

"You're thread's not stickied on xtr

You know, it's amazing...

[jra]

I read this article as "we're going to provide you with a means to make your computer throttle back as far as possible without getting in your way, and you can decide what to do with it".

Are slashdotters really this paranoid these days?

A better way

[Anonymous Coward]

Still, requiring the user to be annoyed (even a little) seems like a bad idea to me (but then, I'm a humanist who really wants the world to turn into a utopia where everyone is happy, so maybe I'm just biased). How about choosing the lowest clock speed that gets things done when they need to be done? For user interface things this might be the inverse of the refresh frequency of the display, for music decoding it might mean fast enough to keep the buffer full, and so on. A lot more sensible. In my view, every device that annoys users, even a little, is defective.

Where's the App?

[cortriga]

Did anyone go looking for the Android app "NU JamLogger" in the Android Marketplace? I couldn't find it and tried a variety of likely search terms.

How much of my G1's precious battery power was wasted on this fruitless search? We'll never know.

hahahahahaha at the alabama hick part

[MEK_LoveBug]

apk stop it already. You are making me laugh and ion.simon.c is making me cry at how silly a man can be due to pride or shame on his end of things. I have been following this since last week and it has been one of the most outrageously funny and sarcastic thread battles I have ever seen to date. You must realize that ion.simon.c wont tell us he is a programmer because it is obvious from his list of mistakes and false accusations above that he is not and certainly cannot prove he is since he avoids both your and my questions from last week in regard to that much. Seriously apk, even if he came up with some type of evidence his list of mistakes would invalidate myself ever thinking he was any good at it in any event. At this point it is a waste of time even trolling him back even though you have proven he started it up with you first and then tried it once more the past week. Some people never learn like ion.simon.c or they like taking punishment they bring on themselves.

Let me guess...

[Hurricane78]

In the experiment, they used big expensive external devices to measure the user reaction. But as soon as you add those devices to the calculation, it stops to make sense...