On Sat, 17 May 2008, Chris Gilbert wrote:
+ case 0x01:
+ switch (model) {
+ case 0x02:
+ ret = "Phenom";
I think this would have to actually be "Family 10h", as Opteron's also
report the same cpuid. See page 5 of:
http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/41322.pdf
If you're ok with that I'll check in the change.
Hmmm, when all this was still in-kernel we were able to differentiate
(or at least, unambiguously identify my quad-core Phenom).
Here's the dmesg output from previous 4.99.60 kernel:
cpu0 at mainbus0 apid 0: (boot processor)
cpu0: AMD Phenom(tm) 9600 Quad-Core Processor, 2310.80 MHz
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
So it seems to me we lost something when moving this all to userland.
I guess we should also pick-up and fix errata 298 if necessary.
Although that is more complex as I believe the registers have to be
updated on every core.
Not sure what errata 298 is - guess I'll have to research that.
----------------------------------------------------------------------
| Paul Goyette | PGP DSS Key fingerprint: | E-mail addresses: |
| Customer Service | FA29 0E3B 35AF E8AE 6651 | paul@xxxxxxxxxxxx |
| Network Engineer | 0786 F758 55DE 53BA 7731 | pgoyette@xxxxxxxxxxx |
----------------------------------------------------------------------
|