Agner`s CPU blog

CPUID manipulation through virtualization

Author: Agner Fog

Date: 2010-08-16 12:24

Andrew Lofthouse wrote:

If VMWare is using hardware virtualization, all cpuid instructions are intercepted and hence can be spoofed.

Thanks a lot for the tip. Now everybody can test if their software has vendor-specific performance. You can get a 60 days evaluation from VMWare or get the server version for free.

By analogy to Andrew's code, I assume that you can make an AMD processor spoof to be "GenuineIntel" with these lines:

cpuid.0.ebx="0111:0101:0110:1110:0110:0101:0100:0111"
cpuid.0.edx="0100:1001:0110:0101:0110:1110:0110:1001"
cpuid.0.ecx="0110:1100:0110:0101:0111:0100:0110:1110"

The Intel software also checks the family number, which should be set to 6:

cpuid.1.eax="0000:0000:0000:0001:0000:0110:0111:0001"

You can verify this with CPUID.

Anybody who finds software with a strong performance effect of the vendor string are welcome to post the details here or mail them to me.

I am currently testing this effect in various math programs. I will post the findings here soon.

Reply To This Message

Previous Message

Next Message

Intel's "cripple AMD" function - Agner Fog - 2009-12-30

Intel's - Felid - 2010-01-01

Intel's "cripple AMD" function - inhahe - 2010-01-03

Intel's - Agner Fog - 2010-01-04

Intel's compiler is the best? - Weber - 2010-01-04

Intel's compiler is the best? - Agner Fog - 2010-01-09

Intel article - Agner Fog - 2010-01-22

Web Parallels - Jeff Craig - 2010-01-04

More Parallels - Agner Fog - 2010-01-23

Early Examples - Yuhong Bao - 2010-02-01

More Parallels - Yuhong Bao - 2010-02-20

New CPUID manipulation program - Agner Fog - 2010-01-22

CPUID manipulation through virtualization - Andrew Lofthouse - 2010-08-16

CPUID manipulation through virtualization - Agner Fog - 2010-08-16

CPUID manipulation program for AMD - Agner - 2010-10-01

CPUID manipulation program for AMD - Ralf - 2012-01-30

CPUID manipulation program for AMD - Agner - 2012-01-31

CPUID manipulation through virtualization - akshay - 2015-07-08

New CPUID manipulation program - AVK - 2011-02-09

New CPUID manipulation program - Agner - 2011-02-09

AMD Blog on compilers/benchmarch - margaret lewis - 2010-02-01

New version is still crippling Intel's competitors - Agner Fog - 2010-06-29

New version is still crippling Intel's competitors - granyte - 2014-09-16

Out of court settlement with FTC - Agner Fog - 2010-08-05

AMD library contains Intel's cripple-AMD function! - Agner Fog - 2010-08-11

Common math programs are affected - Agner Fog - 2010-08-20

Preliminary test results for Matlab - Agner Fog - 2010-09-16

Overview of CPU dispatching in Intel software - Agner Fog - 2010-08-23

New Intel compiler version - still the same! - Agner Fog - 2010-09-22

GCC now has support for function dispatch - Jean-Luc - 2010-09-27

Intel compiler question - James Russell - 2010-10-11

Intel compiler question - Agner - 2010-10-12

New Intel compiler version - still the same! - Don Kretsch - 2010-11-29

New Intel compiler version - still the same! - Daniel - 2011-12-23

New Intel compiler version - still the same! - Agner - 2011-12-25

New Intel compiler version - still the same! - Stanley Theamer - 2012-02-12

New Intel compiler version - still the same! - Stretcho - 2012-03-14

Still no library that is optimal on all processors - Agner - 2012-04-18

Still no library that is optimal on all processors - Guest - 2012-05-17

Still no library that is optimal on all processors - Agner - 2012-05-17

Still no library that is optimal on all processors - David - 2012-05-19

Still no library that is optimal on all processors - Agner - 2012-05-20

Still no library that is optimal on all processors - Bubba_Hotepp - 2012-06-16

Still no library that is optimal on all processors - Marat Dukhan - 2013-05-20

Still no library that is optimal on all processors - Agner - 2013-05-21