Dan,
Of course, you are right .. I would love to use other version of intel,
but I just have this version ... I am on a position at an experimental
institute and I had to start from scratch and setup everything ...
>From my previous experience, I gained about 20 % performance intel
versus gnu ... So I decided to purchase the intel compiler (first time
at my institute)...
Tthey delivered me this new version . .... Not much choice ... :-(
I guess I'll stick to GCC for a while even if the code will be slower ....
Vlad
On 12/03/2010 03:48 PM, Daniel Roe wrote:
> Hi,
>
> It's not really certain what the causes for the errors are yet.
> However, other people have reported various issues when using the
> intel 12.0.0 compilers. In my opinion it's probably not worth the
> headache to use a bleeding edge compiler, particularly when other
> compilers have no issues. It's just my opinion, but I'd wait until
> intel comes out with a few more releases of the v12 compilers before I
> start relying on them.
>
> -Dan
>
> On Fri, Dec 3, 2010 at 9:27 AM, Vlad Cojocaru
> <vlad.cojocaru.mpi-muenster.mpg.de> wrote:
>
>> Dear Ambers,
>>
>> Attached you have 2 files: (i) the config.h file I used to compile the
>> serial version of Amber Tools 1.4 and (ii) the error messages upon 'make
>> test'
>>
>> Several tests fail with error mesages. These errors only occur when I
>> compile with intel 12.0.0 (with MKL 10.3). They are segmentation faults!
>>
>> The compilation worked properly. Also, when compiling with gcc44, there
>> are no error messages for the serial tests.
>>
>> Did anybody experienced these errors and could tell me the cause for them ?
>>
>> Details:
>> Linux x86_64 (2x 6 cores AMD Istanbul chips)
>> CentOS 5.5
>> compiler: intel-12.0.0
>> mkl libs: 10.3
>>
>>
>> Best
>> Vlad
>>
>> --
>> Dr. Vlad Cojocaru
>> Max Planck Institute for Molecular Biomedicine
>> Department of Cellular and Developmental Biology
>> Roentgenstrasse 20
>> 48149 Muenster, Germany
>> tel: +49-251-70365-324
>> fax: +49-251-70365-399
>> email: vlad.cojocaru[at]mpi-muenster.mpg.de
>>
>>
>>
>> _______________________________________________
>> AMBER mailing list
>> AMBER.ambermd.org
>> http://lists.ambermd.org/mailman/listinfo/amber
>>
>>
>>
> _______________________________________________
> AMBER mailing list
> AMBER.ambermd.org
> http://lists.ambermd.org/mailman/listinfo/amber
>
>
--
Dr. Vlad Cojocaru
Max Planck Institute for Molecular Biomedicine
Department of Cellular and Developmental Biology
Roentgenstrasse 20
48149 Muenster, Germany
tel: +49-251-70365-324
fax: +49-251-70365-399
email: vlad.cojocaru[at]mpi-muenster.mpg.de
_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
Received on Fri Dec 03 2010 - 07:30:03 PST
