[gmx-users] gromacs on itanium2

[Mark Abraham]

Marius Retegan wrote:
> Hi,
> First I've managed to compile 3.3.1 with Intel 9.1 and assembly loops
> for ia64. Then I've tried 3.3.3 and 4.0.4. For both I've got a similar
> error:
> ================================================================
> /bin/sh ../../../../libtool   --mode=compile icc -DHAVE_CONFIG_H -I.
> -I../../../../src -I/usr/X11R6/include -I../../../../include
> -DGMXLIBDIR=\"/fougeron/home/mretegan/software/gromacs-4.0.4/share/top\"
> -I/fougeron/home/mretegan/software/fftw3/include  -O2 -mtune=itanium2
> -MT nb_kernel010_ia64_single.lo -MD -MP -MF
> .deps/nb_kernel010_ia64_single.Tpo -c -o nb_kernel010_ia64_single.lo
> nb_kernel010_ia64_single.S
>  icc -DHAVE_CONFIG_H -I. -I../../../../src -I/usr/X11R6/include
> -I../../../../include
> -DGMXLIBDIR=\"/fougeron/home/mretegan/software/gromacs-4.0.4/share/top\"
> -I/fougeron/home/mretegan/software/fftw3/include -O2 -mtune=itanium2
> -MT nb_kernel010_ia64_single.lo -MD -MP -MF
> .deps/nb_kernel010_ia64_single.Tpo -c nb_kernel010_ia64_single.S -o
> nb_kernel010_ia64_single.o
> /tmp/iccDePOHl.s(1) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(2) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(3) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(4) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(5) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(6) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(7) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(8) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(10) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(15) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(193) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(195) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(269) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(423) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> /tmp/iccDePOHl.s(506) : error A2040: Unexpected token: Unary Diez
> Operator at: Start
> nb_kernel010_ia64_single.o - 15 error(s), 0 warning(s)
> ================================================================
> 
> After I started looking on the archive and I've found the this thread
> http://www.mail-archive.com/gmx-users@gromacs.org/msg16911.html. Then
> I've installed the latest Intel compilers (11.0) and I've managed to
> get it compiled. Unfortunately when I've tested the build, the complex
> test failed without producing any output (not even test FAILED). I
> tried to run them by hand, but strangely after I ran the mdrun command
> they just kept on running. No error whatsoever.
> 
> The fftw were compiled with the same compiler as Gromacs. I've use O2
> optimizations in CFLAGS.

There's been another thread this year (I think) and a bugzilla filed on 
this topic. In the meantime, it's quite reasonable to use configure 
--enable-fortran for IA64, as Berk(?) suggested in that thread.

Mark

> On Tue, Mar 3, 2009 at 8:14 PM, David van der Spoel
> <spoel at xray.bmc.uu.se> wrote:
>> Marius Retegan wrote:
>>> Hello
>>>
>>> Since I was unable to get a working version for Gromacs 4.0.4 on a
>>> Itanium 2 machine with the ia64 nonbonded kernel, I was wondering what
>>> would be the lost in speed if I would disable the assembly loops?
>>>
>> About a factor of two. What's the problem with compiling?
>>
>>> Thanks,
>>> Marius
>>> _______________________________________________
>>> gmx-users mailing list    gmx-users at gromacs.org
>>> http://www.gromacs.org/mailman/listinfo/gmx-users
>>> Please search the archive at http://www.gromacs.org/search before posting!
>>> Please don't post (un)subscribe requests to the list. Use the www
>>> interface or send it to gmx-users-request at gromacs.org.
>>> Can't post? Read http://www.gromacs.org/mailing_lists/users.php
>>
>> --
>> David van der Spoel, Ph.D., Professor of Biology
>> Molec. Biophys. group, Dept. of Cell & Molec. Biol., Uppsala University.
>> Box 596, 75124 Uppsala, Sweden. Phone:  +46184714205. Fax: +4618511755.
>> spoel at xray.bmc.uu.se    spoel at gromacs.org   http://folding.bmc.uu.se
>> _______________________________________________
>> gmx-users mailing list    gmx-users at gromacs.org
>> http://www.gromacs.org/mailman/listinfo/gmx-users
>> Please search the archive at http://www.gromacs.org/search before posting!
>> Please don't post (un)subscribe requests to the list. Use the www interface
>> or send it to gmx-users-request at gromacs.org.
>> Can't post? Read http://www.gromacs.org/mailing_lists/users.php
>>
> _______________________________________________
> gmx-users mailing list    gmx-users at gromacs.org
> http://www.gromacs.org/mailman/listinfo/gmx-users
> Please search the archive at http://www.gromacs.org/search before posting!
> Please don't post (un)subscribe requests to the list. Use the 
> www interface or send it to gmx-users-request at gromacs.org.
> Can't post? Read http://www.gromacs.org/mailing_lists/users.php
>