problem with dss_reorder

problem with dss_reorder

Dear all,

The attached example tries to call dss_reorder for 29x29 symmetric matrix. The call to dss_reorder never ends. I have no idea what is wrong. The matrix is symmetric, having zeros in the right lower block as it comes from saddle problem. I wanted to attach a shell script compiling the attached example, but this chat does not like its extension, so here is the way how I compiled it:



LD_FLAGS="-Wl,--start-group $MKLPATHLIB/libmkl_intel_lp64.a $MKLPATHLIB/libmkl_intel_thread.a $MKLPATHLIB/libmkl_core.a -Wl,--end-group $COMPOSERLIB/libiomp5.a -lpthread -lstdc++ -lm"

c++ -g test_mkl_dss.cpp -o test_mkl_dss -I${MKLPATHINC} $LD_FLAGS

Info about my system:


major:     10
minor:     3
update:    4
status:    Product
build:     20110421
processor: Intel(R) Advanced Vector Extensions (Intel(R) AVX) Enabled Processor


Linux sul.localdomain 3.6.2-1.fc16.x86_64 #1 SMP Wed Oct 17 05:30:01 UTC 2012 x86_64 x86_64 x86_64 GNU/Linux

Compiler gcc:

Using built-in specs.
Target: x86_64-redhat-linux
Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl= --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-gnu-unique-object --enable-linker-build-id --enable-languages=c,c++,objc,obj-c++,java,fortran,ada,go,lto --enable-plugin --enable-java-awt=gtk --disable-dssi --with-java-home=/usr/lib/jvm/java-1.5.0-gcj- --enable-libgcj-multifile --enable-java-maintainer-mode --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --disable-libjava-multilib --with-ppl --with-cloog --with-tune=generic --with-arch_32=i686 --build=x86_64-redhat-linux
Thread model: posix
gcc version 4.6.3 20120306 (Red Hat 4.6.3-2) (GCC)

Many thanks for your help

Ondra Kamenik

Downloadtext/x-c++src test-mkl-dss.cpp1.67 KB
4 posts / 0 new
Last post
For more complete information about compiler optimizations, see our Optimization Notice.

the problem is reproduced. we will check the reason and let you know the update.

Dear all,

I put zeros to the diagonal and dss_reorder works including other steps of the solution (factorize and backsolve). See the attached example code which also checks a residual of the solution.

It would be very useful to either change pardisso so that it can swallow matrices like mine, or clearly document the matrix requirements.


Ondra K.


Downloadtext/x-c++src test-mkl-dss.cpp3.09 KB

Hello Ondra,

This issue has been fixed in MKL v.11.0 update 2 released yesterday.

You can download this update from intel registration center and check the problem on your side.



Leave a Comment

Please sign in to add a comment. Not a member? Join today