mpirun meets a segmentation fault

[Alpha-Librae]

error message:

mpirun -np 2 ./block.spin_adapted input.dat > output.dat * Process received signal * Signal: Segmentation fault (11) Signal code: Address not mapped (1) Failing at address: (nil) [ 0] /lib64/libpthread.so.0(+0xf890)[0x2b3e55ef5890] [ 1] ./block.spin_adapted[0x5528f6] [ 2] ./block.spin_adapted[0x7d68a4] [ 3] ./block.spin_adapted[0x7d0e88] [ 4] ./block.spin_adapted[0x7cf3ab] [ 5] ./block.spin_adapted[0x7ce3bd] [ 6] ./block.spin_adapted[0x46d2bb] [ 7] ./block.spin_adapted[0x46a453] [ 8] ./block.spin_adapted[0x54d02a] [ 9] /lib64/libc.so.6(__libc_start_main+0xf5)[0x2b3e57841b05] [10] ./block.spin_adapted[0x427db7] * End of error message *

it seems that the error occurs when a new thread is being created. source code downloaded on 06-10-2015. compiler: intel 2015 update 3 mpi version: openmpi-1.8.4 boost library version: 1.55.0

[gkc1000]

Please send the input file, also precise version that was used (e.g. where was it downloaded from?) If you are downloading from Github, please try again with the v1.0.0 tagged release. (We do not support development snapshots).

On Wed, Jun 24, 2015 at 3:54 AM, diradical notifications@github.com wrote:

error message:

mpirun -np 2 ./block.spin_adapted input.dat > output.dat * Process received signal * Signal: Segmentation fault (11) Signal code: Address not mapped (1) Failing at address: (nil) [ 0] /lib64/libpthread.so.0(+0xf890)[0x2b3e55ef5890] [ 1] ./block.spin_adapted[0x5528f6] [ 2] ./block.spin_adapted[0x7d68a4] [ 3] ./block.spin_adapted[0x7d0e88] [ 4] ./block.spin_adapted[0x7cf3ab] [ 5] ./block.spin_adapted[0x7ce3bd] [ 6] ./block.spin_adapted[0x46d2bb] [ 7] ./block.spin_adapted[0x46a453] [ 8] ./block.spin_adapted[0x54d02a] [ 9] /lib64/libc.so.6(__libc_start_main+0xf5)[0x2b3e57841b05] [10] ./block.spin_adapted[0x427db7] * End of error message *

it seems that the error occurs when a new thread is being created. source code downloaded on 06-10-2015. compiler: intel 2015 update 3 mpi version: openmpi-1.8.4 boost library version: 1.55.0

— Reply to this email directly or view it on GitHub https://github.com/sanshar/Block/issues/15.

[Alpha-Librae]

maybe something wrong with intel compiler 2015 leads to the segmentation fault. ：-（ the program works fine when compiled with GCC 4.8. ：-|

[gkc1000]

Please send the input file still that leads to the problem so we can reproduce it.

On Wed, Jun 24, 2015 at 5:57 AM, diradical notifications@github.com wrote:

maybe something wrong with intel compiler 2015 leads to the segmentation fault. ：-（ the program works fine when compiled with GCC 4.8. ：-|

— Reply to this email directly or view it on GitHub https://github.com/sanshar/Block/issues/15#issuecomment-114792972.

[Alpha-Librae]

The input file is a test example included in the source package. input.dat in README_EXAMPLE/1 and FCIDUMP in README_EXAMPLE.

在 2015年6月24日，18:44，gkc1000 notifications@github.com 写道：

Please send the input file still that leads to the problem so we can reproduce it.

On Wed, Jun 24, 2015 at 5:57 AM, diradical notifications@github.com wrote:

maybe something wrong with intel compiler 2015 leads to the segmentation fault. ：-（ the program works fine when compiled with GCC 4.8. ：-|

— Reply to this email directly or view it on GitHub https://github.com/sanshar/Block/issues/15#issuecomment-114792972.

— Reply to this email directly or view it on GitHub.

[junyang4711]

Hi, We couldn't reproduce your problem, as the same calculation was successful, using two CPUs in parallel, and Block 1.0.0 compiled with intel compiler 15.0.2. Please check how your libraries (boost, mpi, mkl...) are set up. They must be compatible with intel compiler. We recommend to use the same version of compiler for both Block and libraries.

[Alpha-Librae]

I'm sure that openmpi 1.8.4, boost 1.55.0 and Block 1.0.0 were all compiled with intel compiler 15.0.3. However if using GCC 4.8.3 instead of icpc, the binary works perfect. Anyway, thank you all for the code. :-)

[gkc1000]

We have not been able to reproduce the problem with icpc 15.0.2. If this problem persists, please reopen the issue.