- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello all,
Installed Intel C++ 10.1.018 compilers on Cent OS 4.5 based Rocks 4.3 linux cluster. Installation was smooth.
When I compile a parallel program with Open MPI, it gave following error:
# mpicc hellompi.c -o hellompi
/opt/intel/cce/10.1.018/lib/libimf.so: warning: warning: feupdateenv is not implemented and will always fail
It produced the executable. But while running the executable its failing with Segmentation fault:
# which mpirun
/opt/openmpi_intel/1.2.8/bin/mpirun
# mpirun -np 2 ./hellompi
./hellompi: Symbol `ompi_mpi_comm_world' has different size in shared object, consider re-linking
./hellompi: Symbol `ompi_mpi_comm_world' has different size in shared object, consider re-linking
[master:17781] *** Process received signal ***
[master:17781] Signal: Segmentation fault (11)
[master:17781] Signal code: Address not mapped (1)
[master:17781] Failing at address: 0x10
[master:17781] [ 0] /lib64/tls/libpthread.so.0 [0x34b150c4f0]
[master:17781] [ 1] /usr/lib64/openmpi/libmpi.so.0 [0x34b19544b8]
[master:17781] [ 2] /usr/lib64/openmpi/libmpi.so.0(ompi_proc_init+0x14d) [0x34b1954cfd]
[master:17781] [ 3] /usr/lib64/openmpi/libmpi.so.0(ompi_mpi_init+0xba) [0x34b19567da]
[master:17781] [ 4] /usr/lib64/openmpi/libmpi.so.0(MPI_Init+0x94) [0x34b1977ab4]
[master:17781] [ 5] ./hellompi(main+0x44) [0x401c0c]
[master:17781] [ 6] /lib64/tls/libc.so.6(__libc_start_main+0xdb) [0x34b0e1c3fb]
[master:17781] [ 7] ./hellompi [0x401b3a]
[master:17781] *** End of error message ***
[master:17778] [0,0,0]-[0,1,1] mca_oob_tcp_msg_recv: readv failed: Connection reset by peer (104)
mpirun noticed that job rank 0 with PID 17781 on node master exited on signal 11 (Segmentation fault).
1 additional process aborted (not shown)
But this is not the case, during non-mpi c code compilation or execution.
# icc sample.c -o sample
# ./sample
Compiler is working
#
What might be the reason for this & how it can be resolved?
Thanks,
Sangamesh
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
It's not clear to me if these are symptoms of just one problem. Some of this is more topical on the HPC forum. As icc doesn't support fenv, you may have to remove the dependence of your application on it, or build that part with gcc. If the problem comes from openmpi, and your openmpi is not built with icc, you may have to rebuild openmpi, or use Intel mpi. No doubt, the openmpi site would have relevant information. You could also file a feature report on premier.intel.com, if you care to explain the importance of fenv.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
> # mpicc hellompi.c -o hellompi
> /opt/intel/cce/10.1.018/lib/libimf.so: warning: warning: feupdateenv is not implemented and will always fail
---
This warning should be closedwith -limf in linking, static link would solve it than shared link?!
ex. %mpicc -limf hellompi.c -o hellompi
Next,
> ./hellompi: Symbol `ompi_mpi_comm_world' has different size in shared object, consider re-linking
---
Would not Compile & Installed mpirun verion mismatch hellompi module by mpicc ?
ex. mpirun module compiled by gcc, mpicc use Intel Compiler.
ex. mpirun 32bit module,hellompi 64bit.
ex. mpirun version 1.2.x vs. mpicc version 1.4.x.
Good luck & Best regards,
ken.com
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page