<div dir="ltr">Openmpi is indeed compiled with shared libraries. I will disable that. Thanks!<div><br></div><div>I will try and recompile with non-shared libraries (however, the test is still non-mpi called, hence the recommendation shouldn't affect this output, no?)</div><div><br></div><div>Ok, I will, for now assume this is compiler/architecture specific. If I can reproduce the error on our other cluster I will let you know. </div><div>Expect it to be resolved unless I return ;)</div></div><div class="gmail_extra"><br><div class="gmail_quote">2015-06-02 17:18 GMT+02:00 Wei-keng Liao <span dir="ltr"><<a href="mailto:wkliao@eecs.northwestern.edu" target="_blank">wkliao@eecs.northwestern.edu</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi, Nick<br>
<br>
I found a Xeon machine that has icc and built 1.6.0 without errors.<br>
icc version 15.0.2 (gcc version 4.4.7 compatibility)<br>
<br>
I also notice from your config.log that CFLAGS was set even you did not set it at configure command line. If you search keyword for "ac_cv_env_CFLAGS_value", you can see it contains compile options<br>
"-m64 -fPIC -O2 -xHost -prec-div ... " See lines 72 and 3419. In my case, that variable is empty.<br>
Something strange in configure triggers the setting of use these explicit compile options.<br>
Maybe you should regenerate file configure by running command "autoreconf".<br>
<br>
The option -fPIC is for building share libraries, which I suspect is the cause of error you are seeing. I built my OpenMPI 1.8.5 with configure option "--enable-static --disable-shared".<br>
I was seeing problems when I used an OpenMPI with shared library option enabled to build netCDF or HDF5, so I disable it. (I remember shared option is discouraged by parallel HDF5.)<br>
Do you know how your OpenMPI was built?<br>
<span class="HOEnZb"><font color="#888888"><br>
<br>
Wei-keng<br>
</font></span><div class="HOEnZb"><div class="h5"><br>
On Jun 2, 2015, at 9:29 AM, Nick Papior Andersen wrote:<br>
<br>
><br>
><br>
> 2015-06-02 16:25 GMT+02:00 Rob Latham <<a href="mailto:robl@mcs.anl.gov">robl@mcs.anl.gov</a>>:<br>
><br>
><br>
> On 06/02/2015 02:58 AM, Nick Papior Andersen wrote:<br>
> ./nctst ./<a href="http://testfile.nc" target="_blank">testfile.nc</a> <<a href="http://testfile.nc" target="_blank">http://testfile.nc</a>><br>
> ncmpi_inq_typeids not implemented<br>
> [n-62-12-2:21767] *** Process received signal ***<br>
> [n-62-12-2:21767] Signal: Segmentation fault (11)<br>
> [n-62-12-2:21767] Signal code: Address not mapped (1)<br>
> [n-62-12-2:21767] Failing at address: 0xffffffffffffffe8<br>
> [n-62-12-2:21767] [ 0] /lib64/libpthread.so.0(+0xf710)[0x2b3e93945710]<br>
> [n-62-12-2:21767] [ 1]<br>
> /zdata/groups/common/nicpa/2015-test/generic/gcc/5.1.0/lib64/libstdc++.so.6(_ZNSo6sentryC2ERSo+0x19)[0x2b3e934ace79]<br>
> [n-62-12-2:21767] [ 2]<br>
> /zdata/groups/common/nicpa/2015-test/generic/gcc/5.1.0/lib64/libstdc++.so.6(_ZSt16__ostream_insertIcSt11char_traitsIcEERSt13basic_ostreamIT_T0_ES6_PKS3_l+0x29)[0x2b3e934ad589]<br>
> [n-62-12-2:21767] [ 3]<br>
> /zdata/groups/common/nicpa/2015-test/generic/gcc/5.1.0/lib64/libstdc++.so.6(_ZStlsISt11char_traitsIcEERSt13basic_ostreamIcT_ES5_PKc+0x27)[0x2b3e934ad9e7]<br>
> [n-62-12-2:21767] [ 4] ./nctst[0x40ad62]<br>
> [n-62-12-2:21767] [ 5] ./nctst[0x40b93c]<br>
> [n-62-12-2:21767] [ 6]<br>
> /lib64/libc.so.6(__libc_start_main+0xfd)[0x2b3e93d76d5d]<br>
> [n-62-12-2:21767] [ 7] ./nctst[0x405899]<br>
> [n-62-12-2:21767] *** End of error message ***<br>
><br>
> I understand the oddity here is that inq_typids is getting called somehow, and so the backtrace is in some ways irrelevant. I ran it through c++filt anyway:<br>
> I agree completely.<br>
><br>
><br>
> ./nctst ./<a href="http://testfile.nc" target="_blank">testfile.nc</a><br>
> ncmpi_inq_typeids not implemented<br>
> [n-62-12-2:21767] *** Process received signal ***<br>
> [n-62-12-2:21767] Signal: Segmentation fault (11)<br>
> [n-62-12-2:21767] Signal code: Address not mapped (1)<br>
> [n-62-12-2:21767] Failing at address: 0xffffffffffffffe8<br>
> [n-62-12-2:21767] [ 0] /lib64/libpthread.so.0(+0xf710)[0x2b3e93945710]<br>
> [n-62-12-2:21767] [ 1] /zdata/groups/common/nicpa/2015-test/generic/gcc/5.1.0/lib64/libstdc++.so.6(std::basic_ostream<char, std::char_traits<char> >::sentry::sentry(std::basic_ostream<char, std::char_traits<char> >&)+0x19)[0x2b3e934ace79]<br>
> [n-62-12-2:21767] [ 2] /zdata/groups/common/nicpa/2015-test/generic/gcc/5.1.0/lib64/libstdc++.so.6(std::basic_ostream<char, std::char_traits<char> >& std::__ostream_insert<char, std::char_traits<char> >(std::basic_ostream<char, std::char_traits<char> >&, char const*, long)+0x29)[0x2b3e934ad589]<br>
> [n-62-12-2:21767] [ 3] /zdata/groups/common/nicpa/2015-test/generic/gcc/5.1.0/lib64/libstdc++.so.6(std::basic_ostream<char, std::char_traits<char> >& std::operator<< <std::char_traits<char> >(std::basic_ostream<char, std::char_traits<char> >&, char const*)+0x27)[0x2b3e934ad9e7]<br>
> [n-62-12-2:21767] [ 4] ./nctst[0x40ad62]<br>
> [n-62-12-2:21767] [ 5] ./nctst[0x40b93c]<br>
> [n-62-12-2:21767] [ 6] /lib64/libc.so.6(__libc_start_main+0xfd)[0x2b3e93d76d5d]<br>
> [n-62-12-2:21767] [ 7] ./nctst[0x405899]<br>
> [n-62-12-2:21767] *** End of error message ***<br>
><br>
> --<br>
> Rob Latham<br>
> Mathematics and Computer Science Division<br>
> Argonne National Lab, IL USA<br>
><br>
><br>
><br>
> --<br>
> Kind regards Nick<br>
<br>
</div></div></blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature"><div dir="ltr"><div>Kind regards Nick</div></div></div>
</div>