Undervolting a Laptop

Delph1 writes "Laptops often comes with two Achilles heels, heat and limited battery time. There are, if not cures, at least remedies to make them less obvious. By lowering the voltage to the processor you can not only drastically lower the heat dissipation, but also increase the battery time significantly. NordicHardware gives a nice walk through on the process and was able to boast 18% lower temperature and a 20% reduced power consumption."

Comments

Underclocking

[selfabuse]

ATI Tray Tools (or a similar program) will let you underclock your video card too. Good for when you have a hulking gaming laptop, but aren't playing games, and don't want to use it as a space heater for your living room.

Counter productive maybe?

[squoozer]

Surely if you drop the voltage your are going to have to under-clock the processor (reasoning that to over-clock you need to increase the voltage). Most processors for laptops already throttle the processor down when under light load now-a-days which must be a great energy saving. Would under volting it really then save more or would you just end up with a laptop that is dog slow? I'm sure if it was this easy one of the big laptop producers would already be doing it as a 20% increase for basically nothing would give them a fantastic advantage.

Re:Counter productive maybe?

[NitsujTPU]

You end up with a laptop that is dog slow. You're right, most modern laptops throttle themselves effectively in order to reduce power consumption.

What the guy is doing, however, is trying to lower the voltage consumption to the line where the processor starts to behave a little flaky, and then pumping it up just a bit over that. Processors are made in big batches, some of them just work better than others. If yours happens to be one of the good ones in the batch, you can reduce the voltage while maintaining performance (not needing to bump down the clock speed).

If you really obsess over it, you go into the research that my roommate does, where he spends endless hours, days, and weeks tweaking processor floor plans and running them through simulators. You might hope to build a more efficient processor through all of this.

I wouldn't recommend doing this if you're not partial to your laptop randomly hanging while you're working on it, but everyone needs a hobby.

Re:Counter productive maybe?

[evalf]

There are plenty of software that allow to stress-test the processor in order to ensure that the CPU is stable at the voltages that are set, such as prime95, that is mentioned in the article. It does not take "endless hours" to do that either: you just set the voltage you want to use, launch the stress-test utility, go to bed, and check if there are any errors in the morning... Then you can effectively determine the minimum voltage that is required to keep a stable system.

Re:Counter productive maybe?

[frdmfghtr]

Actually, after having read the article, you do get the savings without a hit in performance.

Here's how I understood what was written:

When the processor is running at a particular clock rate, it is supplied a certain voltage. Reduce this voltage, and the processor clock likewise slows down. This feature is not changed.

What IS changed are the voltage thresholds when this speed shift happens. For example, when the processor was running at the reduced clock speed, the voltage (VID) was 1.000 V. However, the author was able to reduced this voltage down to 0.925 V. Hence, when the processor was set to run at the lower clock rate, the VID was only 0.925 V instead of 1.000 V. He then adjusted the settings so that the clock runs at it's original reduced speed with the new lower voltage.

For the faster clock rate, the VID was 1.450 V. However, he was able to get the processor to run at full speed at 1.175V. Again, the clock speed is the same, but the VID itself is lower. Thus, for each speed state of the processor, he was able to run it at a lower voltage.

The best analogy I can think of is the final drive ratio on a car; you have two gears, low and high, and an engine that normally runs at two speeds, say 1000 and 2000 RPM. You only drive at two speeds, 25MPH (1000 RPM) and 50 MPH (2000 RPM.) You tweak the gear ratio in the transmission and engine speed such that, in the end, the car still drives down the road at 25 or 50 MPH but now the engine turns over at only 850 and 1900 RPM. Low and high road speeds are unchanged, but the engine speeds are lower.

Why don't laptop manufacturers do this? They would have to tune these voltages for each individual processor. I'm no expert in overclocking, but if I understand it right, same-model processors can be overclocked at different rates: If you and I have the exact same model processor, you may be able to overclock it more than I can overclock mine, due to manufacturing tolerances. The same principle seems to apply to undervolting; it has to be done in a controlled fashion on a machine-by-machine basis, over a period of several hours.

Computer Performance

[ranton]

How does reducing the Voltage in this way effect performance? If performance drops, then you could have just bought a computer with less processing power that also had lower power needs in the first place.

If there are no performance problems, then why dont all laptop manufacturers already do this?

--

Re:Computer Performance

[drinkypoo]

Generally speaking, limiting processor power limits maximum clock rate. If you undervolt you generally underclock. Most mobile processors already have a power-saving scheme that allows you to select the highest speed that will be used while the system is on battery. Even older systems (like my stinkpad A21p with Mobile P3) have multiple speeds and they will run at a slower one automatically when on battery. So there's not much of a difference unless you're reducing voltage to something lower than the system does automatically.

18% -- that's really funny

[Jason1729]

How do they come off saying a reduction from 78 to 64 degrees F is an 18% reduction in temperature? The Fehrenheit scale is arbitrary and does not have a meaningful zero point.

In celsius, their reduction is 26 to 18 degrees, a reduction of 31%

Why not define a new scale with the same degrees but 0 degrees (new scales) = 63 degrees F. Now on the new scale they've reduced the temperature from 15 to 1 degree, a reduction of 94%....wow that's way better than their lousy 18%.

Their number is totally meaningless.

Also, "undervolting" is not a word.

Re:18% -- that's really funny

[santiago]

The correct zero point to determine the reduction in heat output would be room temperature. Compare the difference between room temperature and the high-volt processor with the difference between room temperature and the low volt-processor. After all, if it were outputting no heat at all, it would be sitting at room temperature, a 100% reduction in heat output from its initial running state.

Re:18% -- that's really funny

[Odin's Raven]

Also, "undervolting" is not a word.

I'm sorry, but "undervolting" is a perfectly cromulent word. I'd agree that percentage was a poor choice for expressing temperature differences, but the primary point remains - undervolting can embiggen battery life.

I modded my Dual-Heel Processor

[digitaldc]

Laptops often comes with two Achilles heels, heat and limited battery time.

You know, I just found about this and I have modded my Laptop to the EXTREME!
I just went on a website and then tinkered with my new Dual-Heel Processor.
It's so EXTREME the battery catches fire 10 seconds after it finishes booting up.

Too much misinformation here.

[TheGuano]

Some facts:

Undervolting is NOT underclocking. You run the same clock speed, you just provide the CPU with less juice.

You do NOT need to underclock to undervolt, though if you're trying to hit a super-low voltage, a lower clockspeed will let you do it.

It can be perfectly safe. If you undervolt, and successfully run a Prime95 torture test for 24 hours, you're pretty much set. I'm currently running a 1.8Ghz Dothan Thinkpad at 1.134V (default at 1.8 is 1.340), and 0.700v at 600Mhz (default is 0.980 volts). That's on par or lower than those 1.0Ghz ULV Pentium-Ms!

I do this too.

[Anonymous Coward]

I find that if you disconnect the battery entirely, you end with 0 voltage draw on the battery. 0 amps are drawn, too. You can then go for many days without having to recharge the battery! This greatly increases overall battery life as well because of less wear and tear. With my Windows desktop environment being riddled with spyware and viruses, my productivity is only reduced slightly when I do this.

Nothing new for now...

[Razlor]

This procedure was described some months ago here, but without obnoxious "i spread my article over infinite pages in order to get more clicks" practice. I have been undervolting my Dothan a long time, using this little patch and some modifications to vidc. This keeps the fan off most of the time, saves some battery life and has no other impact whatsoever.

Undervolting is not underclocking.

[Destoo]

It seems a lot of people just assume that undervolting would be something akin to getting the inverse result of overclocking.

Here's the link to an interesting page about undervolting pentium M processors.

Experience shows that the processor may continue working correctly at lower-than-nominal voltages and frequencies, thereby reducing power consumption, heat and fan noise.

Even if your system seems stable, it may still suffer transient faults leading to arbitrary data corruption. In addition, errors in following these instructions (or changes between processor models) may operate the CPU above its nominal parameters, with effects up to and including laptop meltdown.

There's also a thourough discussion and user results from undervoltage on this thread.

Re:Bad Idea

[serbanp]

Instead of lowering the power consumption, you'll get higher amperage spikes as the equipment draws more power to compensate.

Sorry, this is wrong in the context of a CPU power supply.

When you lower the core voltage, several things happen at once:

1) the power dissipation due to the clock switching is lowered with the square of the voltage reduction. i.e. a reduction from 1.3V down to 1.1V will reduce this power component by 40%

2) the power dissipation due to the junction leakage and off-state punchthrough decreases by the ratio of the voltage.

3) but the switching speed of the MOSFET transistors decreases. Effects 1 and 2 are good as they mean an overall lower power dissipation. For 90nm processes and up, effect #1 dominates. For 65nm and below, the effect #2 becomes increasingly larger.

The downside is #3. Lowering the voltage means that some critical paths inside the CPU logic could become longer than the clock period, generating timing violations and system crashes. The only remedy against this is under-clocking.

In the end, the one thing you can gain by under-volting is the margin between your particular CPU and the lousiest one in the same class that will still perform OK at the same clock speed. As each CPU is tested and binned especially for power dissipation AND maximum clock speed, this margin is low and the gains minimal. And you spend a lot of time to find out what is the lowest safe voltage.

If you want less power dissipation and longer battery life, under-voltage and under-clock. This is done automatically already in the mobile CPUs, both from Intel and from AMD.

Re:CPU efficiency vs. heat rejection

[Pyrrus]

It's pretty much all lost to heat. The "work" done by the electricity it to provide a signal where high voltage indicates 1 and no voltage (ground) indicates zero. Every time a transistor switches either from 0 to 1 or from 1 to 0, current travels through it, using power which is released as heat. The higher the clock speed the more transistions, thus the more power consumption. Lower voltage reduces power consumption (power = volts x current(amps)), but as the "high" voltages becomes lower, the transistors much be more precise (it's easyer to tell the difference between 0V and 5V than it is to tell the difference between 0V and 2V). This is why overclockers usually increase the voltage, since at higher than spec frequencies there is more signal degradation which could (and does) make the system less stable.

Rovclock

[wiresquire]

For you Linux-ers who have ATI cards with no PowerPlay (it's disabled in my video BIOS - bastards!!), I'd recommend checking out rovclock.

While it doesn't actually reduce voltage, it can be used to underclock GPU and memory speed. My somewhat unscientific testing has shown no major differences between fglrx and radeon + rovclock with 2D, but I did note a 27% decrease in battery draw for 3D using the fglrx driver.

Of course, you're trading performance for battery life, and why you'd want to eg, play a 3D game on battery I wouldn't really understand

YMMV
ws