Preventing ACPI from Damaging Your CPU
So just to re-iterate, even if you recompile the DSDT so that it compiles without any errors, there's no guarantee that ACPI won't kill/damage your processor unless the vendor has something special that can't be over-ridden by ACPI (such as is the case with HP's newer motherboards/processors). So how does Windows manage to get around this issue? From my limited understanding of ACPI, the problems seem to be due to the compilation of the DSDT with the Microsoft Compiler which Linux would have trouble dealing with because it's too lack on what gets through. Am I understanding this issue properly? Thanks for your help.
Quoted 31 lines · Rafael J. Wysocki
Quoted 3 lines · Mathew Brown
Thanks. But is 80C safe for a CPU? As I mentioned, 70C is considered dangerous for an Opteron chip. What type of temperatures can the Turions and the C2D support?
I think HP would force the fan at lower temperatures if 80C were considered as dangerous ....
Greetings,
RafaelQuoted 18 lines
Quoted 12 lines · Matthew Garrett
Quoted 5 lines · Mathew Brown
Thanks Matthew. Just out of curiosity, how did you find out about this feature (forcing the fan at 80C)? Also, is this specific to HP or do other vendors also support this? Finally, is 80C safe for the CPU (Intel or AMD?)? I read that Opteron chips could be damaged if their temperature reaches 70C. Thanks for your help.
A certain amount of reverse engineering of HP hardware while I was trying to diagnose some fan problems before. The fan control chip that HP use is pretty standard, so I think there are docs around somewhere.
Signature · 1 line
Matthew Garrett | [email protected]Signature · 2 lines
Mathew Brown [email protected]
Signature · 6 lines
Mathew Brown [email protected] -- http://www.fastmail.fm - Faster than the air-speed velocity of an unladen european swallow