[gmx-developers] Assembler loops on Itanium2 Montecito (again)

[Erik Lindahl]

Hi Rafael,


On Mar 3, 2008, at 9:53 AM, Rafael R. Pappalardo wrote:
>
> I agree with not devoting more efforts to ia64 assembly from you,  
> albeit I'll
> try to contact some people at SGI and see if they can find a  
> solution. What I
> would like to see implemented if a test so if the CPU is not Itanium  
> or
> Itanium 2 McKinley the use of assembly loops is disabled. The  
> advantage is
> that the same executable could be run in a cluster composed of a  
> mixture of
> McKinley  and Montecito CPUs. Do you believe it's possible to  
> include such
> test?


Yes, we could probably do that. In any case we'll fix this before we  
release 4.0.
The problem is that exactly the same loops (literally - byte by byte)  
appear to work fine in the 3.3 release series, so I fear it might be a  
linker or compiler issue.

The next week is pretty busy for me, but after that I might be  
interested in borrowing a guest account somewhere on a Montecino box  
to test things...

Cheers,

Erik
------------
Erik Lindahl   <lindahl at cbr.su.se>  Backup: <erik.lindahl at gmail.com>
Assistant Professor, Computational Structural Biology
Center for Biomembrane Research, Dept. Biochemistry & Biophysics
Stockholm University, SE-106 91 Stockholm, Sweden
Tel: +46(0)8164675  Mobile: +46(0)704218767  Fax: mail a PDF instead