Jason Swails wrote:
> Ah, quite a reasonable thing to try. This eliminates the issues and it
> compiles just fine. I'll drop those from the configure script if you
> (anyone) would like.
>
>> ipo: warning #11020: unresolved gpu_get_nb_energy_
>> Referenced in /tmp/ipo_ifortLpW9vm.o
>> ipo: warning #11020: unresolved gpu_vdw_correction_
>> Referenced in /tmp/ipo_ifortLpW9vm.o
>> ipo: warning #11020: unresolved gpu_self_
>> Referenced in /tmp/ipo_ifortLpW9vm.o
>> ... etc.
>>
This specific error is not a problem with the CUDA code.
Bisecting this issue:
93555e6a7f298a042ac34bf96f932fa482522273 19th Jan OK
4376fb79e67efc1c177bd9285b9cdc7021191f30 19th Jan OK
1f0eb8586f4d526c438bc4cd8f31de0bef02db4b 19th Jan Broken
9ab1ab54ecdeb42ee956ec9d09878dc113fb869d 19th Jan Broken
Hence 1f0eb8586f4d526c438b seems to be the issue. As discussed, the -ipo
option seems to be causing the problem. I've modified the configure
script (f5437cacdb059f4d) to translate -ipo to -ip if CUDA is active;
hopefully this will fix this.
Regards,
Mark
_______________________________________________
AMBER-Developers mailing list
AMBER-Developers.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber-developers
Received on Fri Feb 11 2011 - 02:00:05 PST