Hi Matthew,

Thank you for replying.

I'll try to clean up the "/tmp/ntabuild" directory and to build it again. 
However, I have voluntarily built it incrementally in order to account for the 
following errors I had with "libapr-1.a" static library:

"make: *** [all-recursive] Error 1
 /.../nupic/external/linux64/lib/libapr-1.a(filedup.o): In function `file_dup':
/tmp/apr-1.4.8/file_io/unix/filedup.c:40: undefined reference to `dup3' 
collect2: error: ld returned 1 exit status" (I replaced the libapr-1.a you 
provided with another one just downloaded)

"make: *** [all-recursive] Error 1
/.../Linux/rh5/x86_64/bin/ld: /.../external/linux64/lib/libapr-1.a(dir.o): 
relocation R_X86_64_32 against `apr_pool_cleanup_null' can not be used when 
making a shared object; recompile with -fPIC
/.../external/linux64/lib/libapr-1.a: could not read symbols: Bad value" (I 
replace the newest libapr-1.a, back with the one you provided)

The "ELF file OS ABI invalid" error is generated by "_engine_internal.so", 
which is the only one to have UNIX - GNU OS ABI among the other ".so" files in 
the same folder. In fact, they have the classical System V OS ABI. Maybe, the 
"_engine_internal.so" has been compiled in a newer system environment than the 
one I have. I bypassed it by merely changing its OS ABI field by "elfedit" as 
proposed here: 
"http://stackoverflow.com/questions/2020961/why-would-the-elf-header-of-a-shared-library-specify-linux-as-the-osabi";.
However, it would be better to have it in the System V version for a better 
backward compatibility.

No idea about the "undefined symbol: _ZZN4YAML3Exp9EndScalarEvE1e" error.

Thank you again.
Matteo


-----Original Message-----
From: nupic [mailto:[email protected]] On Behalf Of Matthew Taylor
Sent: Monday, February 17, 2014 6:00 PM
To: NuPIC general mailing list.
Subject: Re: [nupic-discuss] Build/install on a old Redhat platform

Matteo,

I noted this in the output you posted:

    Warning: directory "/tmp/ntabuild" already exists and may contain
(old) data. Consider removing it.

This is left over from a previous build attempt. Try removing this and 
rebuilding first.

> E   ImportError:
> /.../nta/eng/lib/python2.7/site-packages/nupic/bindings/_engine_internal.so:
> undefined symbol: _ZZN4YAML3Exp9EndScalarEvE1e

I have never seen this type of error before, it seems suspicious. Has anyone 
else seen this?

> "E   ImportError:
> /../nta/eng/lib/python2.7/site-packages/nupic/bindings/_engine_internal.so:
> ELF file OS ABI invalid"

I've also never seen this before either, but I found a related SO
article: 
http://stackoverflow.com/questions/7647818/glibc-elf-file-os-abi-invalid

---------
Matt Taylor
OS Community Flag-Bearer
Numenta


On Mon, Feb 17, 2014 at 4:03 AM, Matteo CAUSO <[email protected]> wrote:
> Hi All,
>
> I have tried to build and test NuPIC on a Red Hat Enterprise Linux 
> Server release 5.9 (Tikanga) platform.
>
> However, I have resulted with a successful built that is able to pass 
> none of the tests you have designed for it :
>
> C++ tests:
>
> $NTA/bin/htmtest
> $NTA/bin/testeverything
>
> Python unit tests:
>
> cd $NTA
> ./bin/run_tests.sh
>
> because of an "undefined symbol: _ZZN4YAML3Exp9EndScalarEvE1e" error. 
> In
> particular:
>
> bin/htmtest: symbol lookup error: bin/htmtest: undefined symbol:
> _ZZN4YAML3Exp9EndScalarEvE1e
> bin/testeverything: symbol lookup error: bin/testeverything: undefined
> symbol: _ZZN4YAML3Exp5BlankEvE1e
>
> E   ImportError:
> /.../nta/eng/lib/python2.7/site-packages/nupic/bindings/_engine_internal.so:
> undefined symbol: _ZZN4YAML3Exp9EndScalarEvE1e
>
> Furthermore, I have had also the following error for Python unit tests :
>
> "E   ImportError:
> /../nta/eng/lib/python2.7/site-packages/nupic/bindings/_engine_internal.so:
> ELF file OS ABI invalid"
>
> that I solved, by improperly forcing the System V value to the 
> "_engine_internal.so" SO ABI ELF field.
>
> So, I would kindly ask you if you have already encountered these 
> errors before and if you could propose me a solution to them.
>
> Please, find here enclosed the stdout file resulted as the build.sh outcome.
>
>
>
> Thanks in advance for your help.
>
>
>
> Matteo Causo
>
>
>
>
>
> P.S. here listed some errors I have faced during the building phase by 
> solving them brutally.
>
>
>
> "aclocal:configure.ac:104: warning: macro `AM_COND_IF' not found in library"
> (I commented this line into /.../build_system/unix/configure.ac)
>
>
>
> "make: *** [all-recursive] Error 1
>
> /.../nupic/external/linux64/lib/libapr-1.a(filedup.o): In function `file_dup':
>
> /tmp/apr-1.4.8/file_io/unix/filedup.c:40: undefined reference to `dup3'
>
> collect2: error: ld returned 1 exit status" (I replaced the libapr-1.a 
> you provided with another one just downloaded)
>
>
>
> "make: *** [all-recursive] Error 1
>
> /.../Linux/rh5/x86_64/bin/ld: /.../external/linux64/lib/libapr-1.a(dir.o):
> relocation R_X86_64_32 against `apr_pool_cleanup_null' can not be used 
> when making a shared object; recompile with -fPIC
>
> /.../external/linux64/lib/libapr-1.a: could not read symbols: Bad 
> value" (I replace the newest libapr-1.a, back with the one you 
> provided)
>
>
>
>
>
>
> _______________________________________________
> nupic mailing list
> [email protected]
> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
>

_______________________________________________
nupic mailing list
[email protected]
http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org

_______________________________________________
nupic mailing list
[email protected]
http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org

Reply via email to