you're right, my info on MSVC is 5yrs out of date http://stackoverflow.com/questions/6618027/long-long-in-c I've deleted the UINT64 typedef since it's no longer needed https://github.com/moses-smt/mosesdecoder/commit/1064aaacbe4e7dd0571f35ef0eba3a2efc212859
Marco - you should check in your changes. I'll test it on my machines and make sure it'll work On 24/03/2015 20:28, Kenneth Heafield wrote: > What's wrong with > > #include <stdint.h> > > and > > uint64_t > > Works on gcc, clang, and even MSVC. > > Kenneth > > On 03/24/15 12:28, Hieu Hoang wrote: >> it's probably a compiler-specific problem. I tried it on gcc 4.6.4 >> (ubuntu 12.04), gcc 4.8.2 (ubuntu 14.04), clang (osx), and they all work ok. >> >> you should use UINT64 instead, which is defined in Typedef.h. It's been >> debugged to work on all platforms/compilers i know >> >> On 24/03/2015 15:49, marco turchi wrote: >>> Hi All, >>> we have fixed the problem I reported yesterday. >>> >>> It is not clear to me the reason of that error, but I can compile >>> Moses with the --with-mm flag, if in all the files inside the >>> moses/TranslationModel/UG folder, I replace >>> >>> typename ::uint64 >>> >>> with >>> >>> ::uint64 >>> >>> The modified files are: mmsapt.h, sapt_pscore_unaligned.h, >>> mm/ug_bitext.h, mm/ug_mm_tsa.h, mm/ug_tsa_base.h, >>> mm/ug_tsa_bitset_cache.h and mm/ug_tsa_tree_iterator.h. >>> >>> I compile Moses on a x86_64-redhat-linux machine with gcc version >>> 4.4.7 20120313 (Red Hat 4.4.7-11) (GCC), boost 1_55_0 and xmlrpc-c >>> version 1_40_2. >>> >>> I hope this can be useful if someone has a similar problem. >>> >>> Thanks a lot! >>> Marco >>> >>> On Mon, Mar 23, 2015 at 5:40 PM, marco turchi <marco.tur...@gmail.com >>> <mailto:marco.tur...@gmail.com>> wrote: >>> >>> Hi All, >>> I'm compiling the last version of Moses (downloaded today from the >>> master). Everything works fine if I do not add the --with-mm >>> parameter, but when I include it, moses crashes. I have looked in >>> the mailing list but I have not found anything useful. >>> >>> Do you have any ideas about a possible reason? I attach the log-file >>> >>> Thanks a lot! >>> Marco >>> >>> >>> >>> >>> _______________________________________________ >>> Moses-support mailing list >>> Moses-support@mit.edu >>> http://mailman.mit.edu/mailman/listinfo/moses-support >> >> >> _______________________________________________ >> Moses-support mailing list >> Moses-support@mit.edu >> http://mailman.mit.edu/mailman/listinfo/moses-support >> > _______________________________________________ > Moses-support mailing list > Moses-support@mit.edu > http://mailman.mit.edu/mailman/listinfo/moses-support > _______________________________________________ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support