How much does P4 slow down with thermal protection?

Status
Not open for further replies.

Mictlantecuhtli

Posts: 4,049   +11
Does anyone have information about this? Or should I just test?
I began thinking about this last night when my computer started to feel sluggish. I was using BeOS, Seti@Home running in background, listening to music, copying files when I realized that windows are resizing & moving slower than usual. Then I checked my CPU temperature - 82C! Looked into the case - CPU fan had shut down. Now if I had a realtime CPU speed monitor, I could make a chart about how much temperature affects speed. I'd say it was something like 200-300 MHz, it felt like that.
 

Didou

Posts: 4,190   +11
I think it depends on the settings in your BIOS.

There's a first option that says which action to take in case of overheat : ShutDown / Throttle

You should be able to find another option stating how much to throttle ( in case you choose to do so instead of ShutDown ).
 

svtcobra

Posts: 722   +0
Wow Mic...82C! My T-Bird would be in a grave right now and my credit card would be about 200 bucks heavier after the purchase of a new CPU. That thermal protection works very well on the Intel processor. Im sorry I dont have an answer to your question, I just wanted to comment on your situation.
 

Mictlantecuhtli

Posts: 4,049   +11
Originally posted by Didou
I think it depends on the settings in your BIOS.

There's a first option that says which action to take in case of overheat : ShutDown / Throttle

You should be able to find another option stating how much to throttle ( in case you choose to do so instead of ShutDown ).
Hmm, I haven't seen anything like that in this BIOS. My motherboard is Soltek 85SD-C. There is this SmartDoc Anti-Burning Shield but I've disabled it. It just nags if temperature is too high (well, I haven't seen it doing anything else).
 

Mictlantecuhtli

Posts: 4,049   +11
Ok, I found what I was looking for:
Intel Pentium 4 Processor in the 478-Pin Package at 1.40 GHz, 1.50 GHz, 1.60 GHz, 1.70 GHz, 1.80 GHz, 1.90 GHz and 2 GHz Datasheet
Thermal Monitor controls the processor temperature by modulating the internal processor
core clocks. The processor clocks are modulated when the TCC is activated. Thermal
Monitor uses two modes to activate the TCC: Automatic mode and On­Demand mode.
Automatic mode is required for the processor to operate within specifications and
must first be enabled via BIOS. Once automatic mode is enabled, the TCC will activate
only when the internal die temperature is very near the temperature limits of the
processor. When TCC is enabled, and a high temperature situation exists (i.e. TCC is
active), the clocks will be modulated by alternately turning the clocks off and on at a 50%
duty cycle. Clocks will not be off for more than 3 µs when TCC is active. Cycle times are
processor speed dependent and will decrease linearly as processor core frequencies
increase. A small amount of hysteresis has been included to prevent rapid active/inactive
transitions of the TCC when the processor temperature is near the trip point. Once the
temperature has returned to a non­critical level, and the hysteresis timer has expired,
modulation ceases and TCC goes inactive. Processor performance will be decrease by
~50% when the TCC is active (assuming a 50% duty cycle), however, with a properly
designed and characterised thermal solution the TCC most likely will only be activated
briefly when the system is near maximum temperature and during the most power
intensive applications.
For automatic mode, the 50% duty cycle is factory configured and cannot be modified.
Also, automatic mode does not require any additional hardware, software drivers or
interrupt handling routines.
The TCC may also be activated via On­Demand mode. If bit 4 of the ACPI Thermal
Monitor Control Register is written to a "1" the TCC will be activated immediately,
independent of the processor temperature. When using On­Demand mode to activate the
TCC, the duty cycle of the clock modulation is programmable via bits 3:1 of the same
ACPI Thermal Monitor Control Register. In automatic mode, the duty cycle is fixed at 50%
on, 50% off, however in On­Demand mode, the duty cycle can be programmed from
12.5% on/ 87.5% off, to 87.5% on/12.5% off in 12.5% increments. On­Demand mode may
be used at the same time automatic mode is enabled, however, if the system tries to
enable the TCC via On­Demand mode at the same time automatic mode is enabled AND
a high temperature condition exists, the 50% duty cycle of the automatic mode will
override the duty cycle selected by the On­Demand mode.
An external signal, PROCHOT# (processor hot) is asserted at any time the TCC is active
(either in automatic or On­Demand mode). Bus snooping and interrupt latching are also
active while the TCC is active. The temperature at which the thermal control circuit
activates is not user configurable and is not software visible.
Besides the thermal sensor and thermal control circuit, the Thermal Monitor feature also
includes one ACPI register, one performance counter register, three model specific
registers (MSR), and one I/O pin (PROCHOT#). All are available to monitor and control
the state of the Thermal Monitor feature. Thermal Monitor can be configured to generate
an interrupt upon the assertion or de­assertion of PROCHOT# (i.e. upon the activation/
deactivation of TCC).
If automatic mode is disabled the processor will be operating out of specification and
cannot be guaranteed to provide reliable results. Regardless of enabling of the automatic
or On­Demand modes, in the event of a catastrophic cooling failure, the processor will
automatically shut down when the silicon has reached a temperature of approximately
135 °C. At this point the system bus signal THERMTRIP# will go active and stay active
until RESET# has been initiated. THERMTRIP# activation is independent of processor
activity and does not generate any bus cycles. If THERMTRIP# is asserted, processor
core voltage (Vcc) must be removed within the timeframe defined in Table 16.
Note: TCC = Thermal Control Circuit, timeframe in Table 16 = 0.5 seconds
So, as ACPI is disabled, I assume automatic mode is enabled but yet I found it hard to believe my PC was running @ 50% speed.

Edit: sorry, wrong link, it's fixed now
 

T-Shirt

Posts: 289   +0
By design P4 thermal protectection will continue to slow down the processor, until thermal balance is met (temp rise stops) if this cannot be achived, if overheat continues it will turn off the processor before damage occurs. The settings in the bios do not control the degree of slowdown, thats based on tempature, they do allow you to set how soon before overheat slowdown begins.
 

T-Shirt

Posts: 289   +0
Originally posted by Mictlantecuhtli
Ok, I found what I was looking for:
Intel Pentium 4 Processor in the 478-Pin Package Thermal Design Guidelines

Note: TCC = Thermal Control Circuit, timeframe in Table 16 = 0.5 seconds
So, as ACPI is disabled, I assume automatic mode is enabled but yet I found it hard to believe my PC was running @ 50% speed.
But if it was a borderline overheat it may have been cycling back and forth between 50-100% many times a second. from your time scale several seconds at a time, the average speed may have been in the 75-90% range you perceived. I was work exactly as designed:grinthumb
It does mean you need to think about addtional cooling.
 

Mictlantecuhtli

Posts: 4,049   +11
Now that P4 speeds have passed 3 GHz, I decided to do a little research on this again.

First of all, I assume some, if not most, of you have heard of / seen Tom's Hardware Guide's video where they take the heatsink off of a P4 and it continues working, just slows down. Then they put the heatsink back and it speeds up quickly again.

As this test was done with Socket 423 CPU using i850 motherboard - Asus P4T - the question is:

Does this still apply for new P4s?

Some time ago when I had P4 1.6, I tried booting without heatsink at all. I got to BIOS, checked CPU temperature, which then went off scale quite quickly, and the system just froze. I put the heatsink back but it didn't help, I had to hit reset button.

With high clock speeds, could it be that the CPU can't slow down quickly enough? What I find weird is my CPU was 1.6 GHz and the CPU tested on Tom's video was 2.0.

Any thoughts? Anyone else willing to test? (I dare you :p)
 
Status
Not open for further replies.