Featured Articles

Nvidia GTX 770 spec is out

Nvidia GTX 770 spec is out

In addition to the GK110 based Nvidia Geforce GTX 780, we managed to get some details regarding the GK104-based GTX 770…

More...
Nvidia Geforce GTX 780 detailed

Nvidia Geforce GTX 780 detailed

We managed to confirm the full spec of the upcoming Nvidia Geforce GTX 780 graphics card as well as some performance…

More...
AMD shares take rollercoaster ride

AMD shares take rollercoaster ride

In the last 52 weeks AMD was on a rollercoaster ride, with prices ranging from $1.81 to $6.46. Yesterday it closed…

More...
HIS iCooler Turbo HD 7790 reviewed

HIS iCooler Turbo HD 7790 reviewed

Today we’ll take a closer look at a factory overclocked HD 7790, courtesy of HIS. The HIS HD 7790 iCooler Turbo…

More...
Kingston DataTraveler Ultimate 3.0 Generation 3 (32GB) reviewed

Kingston DataTraveler Ultimate 3.0 Generation 3 (32GB) reviewed

High capacity USB drives have become commonplace a while ago, but although some memory outfits are peddling huge drives, up…

More...
Frontpage Slideshow | Copyright © 2006-2010 orks, a business unit of Nuevvo Webware Ltd.
Tuesday, 16 November 2010 18:05

Hacker claims to have cracked AMD chips

Written by Nick Farell


Not sure about this one
A hacker claims to have discovered a debugging mechanism within AMD CPUs which enables people to learn more about how exactly AMD's chips work, and reverse engineer them. [I'm gonna build one in my shed over the weekend. sub.ed.]

The hacker “Czerno” posted his findings here. He claims that AMD processors have included firmware-based debugging features that expand greatly over standard, architecturally defined capabilities of x86. “Czerno” does not know why, but claims AMD has been secretive about these features which we would have thought would have given them some advantage over Intel. He said that hint of their existence was gained by glancing at the list of undocumented machine specific registers (MSRs). He said that there are four new machine specific registers (MSR) that are involved in the expanded debug facilities.

All those MSRs are "password" protected against casual access: read/write access (RDMSR/WRMSR) to the registers is granted only if EDI holds the correct password value (9C5A203A), otherwise, a GPF exception occurs. All these registers default/reset values are zero. The registers may do something with built-in self test of microprocessors. However they could also be something to run the processor's microcode during development. However since “Czerno” has been a bit vague about it all it is not clear if any of it is true.

We wonder if our readers have views on it.
Last modified on Tuesday, 16 November 2010 18:08
blog comments powered by Disqus

To be able to post comments please log-in with Disqus

 

Facebook activity

Latest Commented Articles

Recent Comments