ScaLAPACK Archives

[Scalapack] Bug report of memory leakage for Scalapack subroutine PCGEMR

On Wed, 2006-06-21 at 08:37 -0700, Ming Li wrote:
Hello, Scalapack Developers,

Possible Bug of memory leakage for Scalapack
subroutine PCGEMR2D or my wrong usage.

At my program, I have to use a lot of PCGEMR2D to
distribute and re-distribute between global matrixes. 
It is OK to use a few of PCGEMR2D, but when I use too
much of PCGEMR2D, the program just crashed. Try to
point out the problem is really at PCGEMR2D, I wrote a
very simple test program with only PCGEMR2D called in
the test program (the source code is attached with
this email pcgemr2d-test.f90). 

In the test program, I set up several pause points by
reading in an integer, then I can read the memory
usage by the ?top? command of Linux. I can see the
memory usage will accumulated when more and more
PCGEMR2D is called.

If memory is accumulated large enough, the program
will crash with the following error message:

[2] Abort: VAPI_register_mr at line 65 in file
collutils.c
Timeout alarm signaled
Cleaning up all processes ...forrtl: error (78):
process killed (SIGTERM)
forrtl: error (78): process killed (SIGTERM)
forrtl: error (78): process killed (SIGTERM)
done.


In my test program, the program crashed after enter 3
integers which corresponding to total number of loop
between 1500 and 2000. 

My computer setup is as following:

   Intel Xeon EM64t process 
   2GB memory
   Intel fortran compiler V8.01
   MPICH
   Infinband communication network
   Intel Math Kernel Library Cluster version 8.0


May be it is due to my wrong usage, if that is the
reason, please help me with the correct usage of this
subroutine.

Thank you very much!!

Milton


Milton,
I have no problems at all running your test program. Following your
instruction I can't see any memory growth under the "top" command. I
also run the test program with a memory profiler (valgrind) I got no
memory-related message in the report. To run my tests I used
gfortran/gcc and reference BLAS. Do you have this kind of problem with
any number of processes? 

Thanks,
Alfredo

-- 
-----------------------------------------
Alfredo Buttari PhD,
Innovative Computing Laboratory,
UTK Computer Science Dept. 
1122 Volunteer Blvd. Knoxville, TN 37996 
Tel: 001-865-974-9985
URL: http://www.ce.uniroma2.it/~buttari


<Prev in Thread] Current Thread [Next in Thread>


For additional information you may use the LAPACK/ScaLAPACK Forum.
Or one of the mailing lists, or