Is Your P4 Working At Half Speed?

ArneD writes: "While browsing xbitlabs.com discussion-board I found this message about the P4. The message suggests that the P4, when stressed and getting hot, starts to halt 50% of the time. When checking mail your precious P4 works at 1.5Ghz but when used for something meaningful (recompiling your kernel?!? ;-) the processor may in fact be a mere 750Mhz since it starts to issue PROCHOT signals that tells the processor to switch itself on/off 50% of the time until it's temperature is within Intels spec-range again." (Read more.)

"More information can be found in Intels Pentium 4 Thermal Design Guidelines (check out page 23)."

Several readers have submitted news of this clock-throttling, one aspect of the P4's built-in temperature sensor system Intel calls "Thermal Monitor." One thing to point out is that the same design guidelines document goes on to say that "the clock modulation feature of Thermal Monitor is disabled by default ... OEMs are expected to enable the thermal control circuit while using various controls and outputs to monitor the processor thermal status." Other things being equal (even if they never are) is there some reason to prefer a chip for not having this capability? If someone forced me to accept a free and loaded P4 system, I'd rather it be cool down at 750MHz temporarily than toast at 1.5GHz.

Comments

Re:Is Your P4 Working At Half Speed?

[Silver A]

Is Your P4 Working At Half Speed?

No, reading Slashdot isn't THAT taxing on my cpu.

Unless you're using Mozilla.

I work at half speed...

[MustardMan]

When things get too hot at work I switch into my brain-cooling mode. I spend 0.2 microseconds working then switch off to slashdot reading mode for 2 seconds. This modified duty cycle allows time for my brain to cool down. Once frustration levels are within acceptable tolerances, I switch back into 100% work mode.

Re:I work at half speed...

[DeeKayWon]

Reading Slashdot lowers your frustration level?

I'd hate to have your job.

is there some reason?

[Paradise_Pete]

s there some reason to prefer a chip for not having this capability?

Perhaps there's a reason to prefer a chip that doesn't get so hot in the first place. I heard Motorolla and IBM make one, and that some company has released a Unix variant that runs pretty well on it.

Re:well...

[The_Messenger]

Why can't processors dynamically adjust their clock speed based on temperature in the first place?

My Athlon Thunderbird does this. Around 90C, it dynamically adjusts its clock-speed to 0MHz.

--

Deja Vu...

[suss]

This story was posted and discussed at length 3 days ago...

This is not bad

[DivineOb]

Come on people... you even made me log in to reply to this one... This is not a bad thing, but a good thing. Power has been a problem for cpus for a while. This is, in fact, actually a quite cool feature. Generally how processors are designed is you get some guy to generate the maximum heat producing code that he can find. It doesn't do anything useful, and generally consists of lots and lots of floating point instructions. Then, you find out how much this heat this program generates when run on your processor. Now, you design your processor to be able to tolerate the heat generated by this program. However, first of all, no program that does anything useful will ever generate as much heat as this test program. SO really, you're forced to design your processor packaging for a way overkill case just to be sure that you don't have your processor die when someone is doing legitmate work with an unoverclocked processor. It has been shown that packaging costs increase by about $1 per watt generated by a processor for every watt over $30, so you can see that developing your packaging for the worst case scenario can be quite expensive. The alternative, then, is exhibited in the P4... Build your processor packaging for less than the worst case, then use some form of thermal throttling to prevent overheating. This has two advantages 1) It lowers your packaging costs 2) It prevents processor death in the case of catastrophing failure (such as a fan dying). I expected that people would get up in arms about this feature, but really, most of you just need to learn about the most recent research in this field to see this is actually a step in the right direction. However most people on slashdot are primed to jump on Intel at every opportunity, so they interpret this in the worst possible light. And BTW, I'm getting my PhD in computer architecture, so I know what I'm talking about :P. There have been papers at all the major conferences for the past few years dealing with power issues, and I might work on one myself soon.