Sign in with
Sign up | Sign in

IDF Taipei: Intel Releases DTS Specs For All Core 2 Processors (Updated)

By - Source: Tom's Hardware | B 16 comments

It has been a long time coming, but the pieces are slowly falling into place. Intel has now released the official Tjunction Max value for all 65nm and 45nm Core 2 processors at the Intel Developer Forum in Taipei.

In a previous report on the August IDF presentation in San Francisco, Tom’s Hardware discussed how the information provided by Intel had very little real-world value. The reason Tjunction Max (the temperature where thermal protection is engaged) is not the silver bullet for 45nm Core 2 processors is because the sensors suffer from extremely high amounts of "slope error," that is, they become less accurate as the real temperature moves further from Tjunction Max.

An Intel document (PDF) describes the error on Atom processors, which use the same or similar DTS as those on 45nm Core 2 processors:

"The digital thermal sensor (DTS) accuracy is in the order of -5°C +10°C around 90°C; it deteriorates to ±10°C at 50°C. The DTS temperature reading saturates at some temperature below 50°C. Any DTS reading below 50°C should be considered to indicate only a temperature below 50°C and not a specific temperature. External thermal sensor with “BJT” model is required to read thermal diode temperature."

According to Intel, if the actual temperature is below 50°C the temperature can’t be trusted at all. With calibration, the slope error can be offset to an extent, but the reported temperatures will never be as accurate as those which are reported by the DTS on 65nm processors. Furthermore, the sensors can sometimes "stick," particularly at lower temperatures, and the worst of these sensors can’t be calibrated properly.

Unlike their 45nm counterparts, the DTS for 65nm is much less affected by slope error, so that even a temperature readout that has not been calibrated can give a reasonably close representation of the actual temperature. The only major factor which will affect readings is Tjunction Max. Since the 65nm CPUs were released, enthusiasts and developers of temperature monitoring software have debated over the Tjunction Max. It was hoped that Intel would disclose these details at the August IDF; however, we were to be disappointed. A few months later and Intel has finally decided to disclose the Tjunction Max for every processor in the Core 2 line, both 45nm and 65nm, as well as Xeon server CPUs. The Tjunction Max values for all Core 2 processors are as follows:

65nm Desktop CPUs
ModelTarget Tj (B2/B3/L2)Target Tj (G0/M0)
E6000 and E4000 series70°C80°C
X680075°C85°C
Q6000 series80°C90°C
QX6000 series80°C90°C
QX68xx series80°C80°C
E1000 series75°C85°C

45nm Desktop CPUs
ModelTarget Tj (Stepping unspecified)
E8000 and E7000 series100°C
Q9000 and Q8000 series100°C
QX965095°C
QX977x85°C

65nm Xeon Dual-Core CPUs
ModelTarget Tj (Stepping unspecified)
E7220, E721080°C
7100 series100°C

65nm Xeon Dual-Core CPUs
ModelTarget Tj (B2)Target Tj (G0)
5080, 506080°C90°C
5063, 5050, 503080°C90°C
5160N/A80°C
5150, 5140, 5130, 5120, 5110N/A80°C
5148N/A80°C
L5138N/A100°C
3000 series80°C90°C

65nm Xeon Quad-Core CPUs
ModelTarget Tj (Stepping unspecified)
X735090°C
E7340, E7330, E7320, E731080°C
L734580°C
X5000 series90/95°C
E5000 series80°C
L5000 series70°C
L531895°C
X3230, X3220, X321090°C
XE90°C
XEE80°C

45nm Xeon Single-Core CPUs
ModelTarget Tj (Stepping unspecified)
L310495°C

45nm Xeon Dual-Core CPUs
ModelTarget Tj (Stepping unspecified)
X52xx series90°C
E524090°C
E5220, E520570/90°C
L524070°C
L5238, L521595°C
E3120, E3113, E311095°C
L311095°C

45nm Xeon Quad-Core CPUs
ModelTarget Tj (Stepping unspecified)
E7440, E7430, E742090°C
L744580°C
X54xx series85°C
E54xx series85°C
L540895°C
L5430, L5420, L541070°C
X33xx95°C
L336090°C
X33xx series95°C
L336090°C

45nm Xeon Six-Core CPUs
ModelTarget Tj (Stepping unspecified)
X746085°C
E745585°C
L745585°C

The above data will mean that for some users the temperatures currently being reported for their cores are actually quite a fair amount off; assuming we take Intel’s word for these maximum temperature values. For example, most temperature reporting programs would use 85°C as the Tjunction Max for a B2 E6600. According to Intel, the "official" Tjunction Max for this processor is only 70°C. That means that for a program which does not take into account any slope error, the temperature would be reported 15°C too high.

Of further interest is that many enthusiasts have done extensive testing to approximate Tjunction Max where it had not been specified. For the 45nm processors, Intel’s data generally aligns with the results of community testing. However, for 65nm the values provided by Intel are significantly different for some processors than what testing has shown. It may very well be that Intel has caused even more confusion than before.

You can expect most software developers to update their programs in the near future to reflect the information provided by Intel.

Update: Unfortunately, the data provided by Intel is not actually what was expected. The developer of Core Temp received an email last month from the presenter of the August IDF presentation on the DTS specifications which said that Tjunction Max would be disclosed for all processors in Taipei. In reality, Intel disclosed a value known as "Target Tjunction," which should not be used as Tjunction Max as it will result in unrealistic temperature readings. Taking the earlier example of the B2 E6600, if you had a low ambient temperature, changing Tjunction Max so that it aligned with the Target Tjunction may result in temperature readings close to or below 0°C when at idle. Temperatures below ambient aren’t possible on normal air cooling.

It seems that yet again Intel has avoided providing any valuable information at IDF. Intel hasn’t even stated exactly what Target Tjunction actually is. It is not recommended to change Tjunction Max to align with these values.

Discuss
Display all 16 comments.
This thread is closed for comments
  • 0 Hide
    cow_moo , October 21, 2008 8:44 PM
    Thanks for some of the cpu temp things
  • 0 Hide
    Anonymous , October 21, 2008 8:45 PM
    well, any temperature below 50 degrees C can't really harm the pc anyways, so what's the big deal around that?
    The way I see it, the thermometer inside the cpu gets more accurate the higher it gets in temperature, well,that's exactly where it's needed!

    I don't really care if my CPU inside runs on 36 degrees or 42 or 28!
    I do care if it's running at 60 or 70 degrees!
  • -2 Hide
    jkflipflop98 , October 21, 2008 9:19 PM
    Ummm. . . why the hell wouldn't you take Intel's word for those values? This place has become increasingly pro-AMD and anti-intel ever since you hired those clueless jackasses from that other rumor spreading site.
  • 0 Hide
    TheFace , October 21, 2008 9:22 PM
    My old Pentium D 830 always ran at a blazing 65 degrees or higher, and now my E8500 runs at a much cooler 35c. Does the Tj Max mean that, 100 degrees C is the highest temp that my processor can run without imminent permanent damage or what does it mean exactly? I guess I am confused as to why I should keep this number in mind when taking notice of my processor temp.
  • 0 Hide
    aggrressor , October 21, 2008 9:28 PM
    The whole Point is not 36C or 42C.. The point is that every temperature monitoring software is off by nearly 20C. As an example, I had my E6600 peaking at 90C when clocked to 3.6Ghz and didn't crap out. It freaked me out a bit, since i've never seen temps that high on any CPU. Including that Pentium4 'Presshot' LOL. These TjMax figures will make developers adjust their software for Core2 class CPU's to show a proper temperature. I personally don't care when temp. monitoring software shows 45C instead of 25C. However I do care when it shows 90C instead of 70C, cause that throw's me off.
  • 0 Hide
    gsteacy , October 22, 2008 12:14 AM
    aggrressorThe whole Point is not 36C or 42C.. The point is that every temperature monitoring software is off by nearly 20C. As an example, I had my E6600 peaking at 90C when clocked to 3.6Ghz and didn't crap out. It freaked me out a bit, since i've never seen temps that high on any CPU. Including that Pentium4 'Presshot' LOL. These TjMax figures will make developers adjust their software for Core2 class CPU's to show a proper temperature. I personally don't care when temp. monitoring software shows 45C instead of 25C. However I do care when it shows 90C instead of 70C, cause that throw's me off.

    Please read the update. You should stick with your previous readings as they are likely far more accurate. I apologise for any confusion caused.
  • 0 Hide
    aggrressor , October 22, 2008 5:37 AM
    Thanks for the update. Every little bit helps. I guess i'll hold off from extreme overclocking until intel releases something we all can work with.
  • 0 Hide
    jimmysmitty , October 22, 2008 8:39 AM
    gsteacy


    How could it be more accurate when the thermal spec for a E6600 is 60.1c? If it did hit 90c it would have started to throttle which he said it didn't.

    From what I read it could be off by more if they use a higher TjMax than what is specified and some were so that 90c might have been 70c.
  • 0 Hide
    aggrressor , October 22, 2008 4:26 PM
    I always turn off Thermal Throttling when I overclock. I only leave speedstep turned on for it not to fry at max clock constantly
  • 0 Hide
    gsteacy , October 22, 2008 11:44 PM
    jimmysmittyHow could it be more accurate when the thermal spec for a E6600 is 60.1c? If it did hit 90c it would have started to throttle which he said it didn't.

    Thermal spec (for desktop and server processors, not mobile) refers to Tcase Max, not Tjunction Max. Have a look here. Setting a 70C Tj Max resulted in temperatures reportedly well below ambient on air. If air could do that we wouldn't have much need for water now would we ;)  The problem with the August and October presentations is they don't seem to be consistent about this Target Tjunction. In the August IDF presentation, they had the following mentioned on the first slide about Core i7:

    • Approximate temperature in °C can be calculated by:
    –TJ = TJ_TARGET –DTS value
    –Ex: TJ_TARGET = 85, DTS = 24, Approximate TJ ≈ 85-24 ≈ 61 °C


    This indicates that Target Tj is Tj Max. In the October presentation, which was basically an extension of the August one, this was missing. The same basic logic above is used to in Core Temp to get the temperatures shown in the screenshot. If you are getting temps below ambient on air, then Tj Max must be higher than 70C on a B2 stepping CPU to make sure that you aren't breaking the laws of physics.

    So, jkflipflop, that is why we can't necessarily take Intel's word for Tj Target values; at least we can't assume they are Tj Max even though Intel provides indications that they are. I am not saying that Intel is lying about these figures, but they certainly aren't clear about their purpose, or even why they were included in the presentation.
  • 0 Hide
    neiroatopelcc , October 24, 2008 7:25 AM
    Guess we're stuck to hoping intel updates their tat application, so it can come with recent and upcomming cpu's - if anything, intels own developers must have access to the real data.
  • 0 Hide
    neiroatopelcc , October 24, 2008 7:26 AM
    "can come" should've been "can cope" - anyway, you know what it's meant to say now :) 
  • 0 Hide
    gsteacy , October 24, 2008 7:44 AM
    neiroatopelccGuess we're stuck to hoping intel updates their tat application, so it can come with recent and upcomming cpu's - if anything, intels own developers must have access to the real data.

    Of course they do :)  But we'll never get an updated TAT, because it probably isn't even meant to be publically available. I can't back that up with any highly credible sources though, just something I read on a forum last year. I doubt Intel would say either way.
  • 0 Hide
    neiroatopelcc , October 24, 2008 7:51 AM
    So it'd take an intel employee to get a copy of it? What about the likes of you ? don't you get that sort of stuff, and could put it on an ftp you forgot to secure for a few days or something? Not implying you would, but would it be possible? (to save humanity from inconsistent information)
  • 0 Hide
    gsteacy , October 24, 2008 8:05 AM
    Well from where I read about it (and I can't remember where that was) it was intended for reviewers only. I'm not a reviewer ;)  Take what I'm saying with a grain of salt, like I said, my source was a forum post. I don't actually know what TAT was intended for.
  • 0 Hide
    neiroatopelcc , October 24, 2008 8:57 AM
    Ask one of the reviewer guys at the rather large company you work for! perhaps they have more info on the matter. I'm sure I'm not the only person who'd want to know more about current and future versions of tat, or it's replacement.