Petz, I respect the amount of research you put into this thermal discussion, but you seem to have a few gross misrepresentations that I'd like to sort out. I hope you'll give the benefit of the doubt and address these points in your response.
Re: In Intel's case, for the quad core X5300 series 120w (145w max) Xeons, Intel states categorically that a heatsink designed to allow Tcase to reach 70C when dissipating 120w WILL result in "noticeable performance loss due to increased TCC activation [thermal throttling]." They state this is true even if the actual Tcase temp doesn't come close to 70C!
In this statement, you are only referring to the Thermal Profile B solution, which according to the spec is a reduced specification meant for 1U form factors. It's meant to give the designers a means of cooling the X-series Xeon in volumetrically constrained spaces, where otherwise, the choice would be to drop down to E-series parts. The spec also notes that servers will maintain the 63C degree Tcase of Thermal Profile A due to TCC activation, so you can extrapolate that the Thermal Profile B heat sink is really only dissipating 90W (note that this is not a problem for E5300 and L5300 Xeons, but just the highest bin X sku).
Re: The former (Intel) requires a HSF with 0.15degC/w, almost unattainable. The latter [Opteron] requires a HSF with 0.183 to 0.225 degC/w performance.
According to this spec, Intel's Thermal Profile B Psi(ca) guideline is 0.249 C/W. Only the standard X-series Thermal Profile A Psi(ca) is 0.190 C/W. This makes Xeon actually slightly easier to cool than Opteron.
download.intel.com (page 32)
Re: If you read nothing else, read this: You have stated several times that Pete "invented" TDPmax.
Actually, my claim is that Pete has invented a term that he calls TDPmax, but it doesn't relate to anything in the Intel specs.
Re: You stated that he invented it as the product of voltage times current. Table 6.3 of the above document clearly defines "Maximum Power" of 145 watts for the quad core Xeons. It is not power consumed, it is power dissipated as heat, which of course means that max power consumed is even larger.
X-Series Xeon, Petz. Let's make that clear. Second, Pete uses the figures in page 28 of the spec to make his calculations:
download.intel.com
He would take 1.5V and 125A to arrive at 187.5W "TDPmax". You've apparently found the spec, which says that 145W is the real TDPmax using the max possible VID, which means that I am justified for calling B.S. on pgerassi's thermal claims.
If you disagree, then show me where I am wrong. |
