bug in crossproduct of optimized matrix library from Intel

[hanst]

hello,
i have recently downloaded the optimized matrix library
for the pentium 4 from the intel website at

http://www.intel.com/cd/ids/developer/asmo-na/eng/microprocessors/ia32/pentium4/optimization/20460.htm

however we found, that this library produces wrong
results for the double precision cross product. the
author of this library Ronan Zohar has not yet replied
to his email.

could anybody from the intel officials please forward
this information to him or give me an answer to the
question, why the cross product is wrong ?

i am compiling everything with the latest intel c++
compiler for windows 7.0.

regards,
torsten hans

Message Edited by intel.software.network.support on 12-09-2005 01:39 PM

[Ganesh_R_Intel]

Hanst,
Thanks for the post. Please also consider posting this message on premier.intel.com.

Regards,
Ganesh