[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Slow speed after changing from serial to parallel (with ex2f.F)



Hi,

I just tested the ex2f.F example, changing m and n to 600. Here's the result for 1, 2 and 4 processors. Interestingly, MatAssemblyBegin, MatGetOrdering and KSPSetup have ratios >>1. The time taken seems to be faster as the processor increases, although speedup is not 1:1. I thought that this example should scale well, shouldn't it? Is there something wrong with my installation then?

Thank you.

1 processor:

Norm of error 0.3371E+01 iterations  1153
************************************************************************************************************************
***             WIDEN YOUR WINDOW TO 120 CHARACTERS.  Use 'enscript -r -fCourier9' to print this document            ***
************************************************************************************************************************

---------------------------------------------- PETSc Performance Summary: ----------------------------------------------

./a.out on a atlas3-mp named atlas3-c58 with 1 processor, by g0306332 Wed Apr 16 10:03:12 2008
Using Petsc Release Version 2.3.3, Patch 8, Fri Nov 16 17:03:40 CST 2007 HG revision: 414581156e67e55c761739b0deb119f7590d0f4b

                         Max       Max/Min        Avg      Total
Time (sec):           1.222e+02      1.00000   1.222e+02
Objects:              4.400e+01      1.00000   4.400e+01
Flops:                3.547e+10      1.00000   3.547e+10  3.547e+10
Flops/sec:            2.903e+08      1.00000   2.903e+08  2.903e+08
MPI Messages:         0.000e+00      0.00000   0.000e+00  0.000e+00
MPI Message Lengths:  0.000e+00      0.00000   0.000e+00  0.000e+00
MPI Reductions:       2.349e+03      1.00000

Flop counting convention: 1 flop = 1 real number operation of type (multiply/divide/add/subtract)
                            e.g., VecAXPY() for real vectors of length N --> 2N flops
                            and VecAXPY() for complex vectors of length N --> 8N flops 

Summary of Stages:   ----- Time ------  ----- Flops -----  --- Messages ---  -- Message Lengths --  -- Reductions --
                        Avg     %Total     Avg     %Total   counts   %Total     Avg         %Total   counts   %Total
 0:      Main Stage: 1.2216e+02 100.0%  3.5466e+10 100.0%  0.000e+00   0.0%  0.000e+00        0.0%  2.349e+03 100.0%

------------------------------------------------------------------------------------------------------------------------
See the 'Profiling' chapter of the users' manual for details on interpreting output.
Phase summary info:
   Count: number of times phase was executed
   Time and Flops/sec: Max - maximum over all processors
                       Ratio - ratio of maximum to minimum over all processors
   Mess: number of messages sent
   Avg. len: average message length
   Reduct: number of global reductions
   Global: entire computation
   Stage: stages of a computation. Set stages with PetscLogStagePush() and PetscLogStagePop().
      %T - percent time in this phase         %F - percent flops in this phase
      %M - percent messages in this phase     %L - percent message lengths in this phase
      %R - percent reductions in this phase
   Total Mflop/s: 10e-6 * (sum of flops over all processors)/(max time over all processors)
------------------------------------------------------------------------------------------------------------------------


      ##########################################################
      #                                                        #
      #                          WARNING!!!                    #
      #                                                        #
      #   This code was run without the PreLoadBegin()         #
      #   macros. To get timing results we always recommend    #
      #   preloading. otherwise timing numbers may be          #
      #   meaningless.                                         #
      ##########################################################

Event                Count      Time (sec)     Flops/sec                         --- Global ---  --- Stage ---   Total
                   Max Ratio  Max     Ratio   Max  Ratio  Mess   Avg len Reduct  %T %F %M %L %R  %T %F %M %L %R Mflop/s
------------------------------------------------------------------------------------------------------------------------

--- Event Stage 0: Main Stage

MatMult             1192 1.0 1.6115e+01 1.0 2.39e+08 1.0 0.0e+00 0.0e+00 0.0e+00 13 11  0  0  0  13 11  0  0  0   239
MatSolve            1192 1.0 3.1017e+01 1.0 1.24e+08 1.0 0.0e+00 0.0e+00 0.0e+00 25 11  0  0  0  25 11  0  0  0   124
MatLUFactorNum         1 1.0 3.6166e-02 1.0 8.94e+07 1.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0    89
MatILUFactorSym        1 1.0 1.9690e-01 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 1.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatAssemblyBegin       1 1.0 1.9073e-06 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatAssemblyEnd         1 1.0 2.6258e-02 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatGetRowIJ            1 1.0 1.9073e-06 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatGetOrdering         1 1.0 5.4259e-03 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 2.0e+00  0  0  0  0  0   0  0  0  0  0     0
VecMDot             1153 1.0 3.2664e+01 1.0 3.92e+08 1.0 0.0e+00 0.0e+00 1.2e+03 27 36  0  0 49  27 36  0  0 49   392
VecNorm             1193 1.0 2.0344e+00 1.0 4.22e+08 1.0 0.0e+00 0.0e+00 1.2e+03  2  2  0  0 51   2  2  0  0 51   422
VecScale            1192 1.0 6.9107e-01 1.0 6.21e+08 1.0 0.0e+00 0.0e+00 0.0e+00  1  1  0  0  0   1  1  0  0  0   621
VecCopy               39 1.0 3.4571e-01 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
VecSet                41 1.0 1.1397e-01 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
VecAXPY               78 1.0 6.9354e-01 1.0 8.10e+07 1.0 0.0e+00 0.0e+00 0.0e+00  1  0  0  0  0   1  0  0  0  0    81
VecMAXPY            1192 1.0 3.7492e+01 1.0 3.63e+08 1.0 0.0e+00 0.0e+00 0.0e+00 31 38  0  0  0  31 38  0  0  0   363
VecNormalize        1192 1.0 2.7284e+00 1.0 4.72e+08 1.0 0.0e+00 0.0e+00 1.2e+03  2  4  0  0 51   2  4  0  0 51   472
KSPGMRESOrthog      1153 1.0 6.7939e+01 1.0 3.76e+08 1.0 0.0e+00 0.0e+00 1.2e+03 56 72  0  0 49  56 72  0  0 49   376
KSPSetup               1 1.0 1.1651e-02 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
KSPSolve               1 1.0 1.2159e+02 1.0 2.92e+08 1.0 0.0e+00 0.0e+00 2.3e+03100100  0  0100 100100  0  0100   292
PCSetUp                1 1.0 2.3852e-01 1.0 1.36e+07 1.0 0.0e+00 0.0e+00 3.0e+00  0  0  0  0  0   0  0  0  0  0    14
PCApply             1192 1.0 3.1021e+01 1.0 1.24e+08 1.0 0.0e+00 0.0e+00 0.0e+00 25 11  0  0  0  25 11  0  0  0   124
------------------------------------------------------------------------------------------------------------------------

Memory usage is given in bytes:

Object Type          Creations   Destructions   Memory  Descendants' Mem.

--- Event Stage 0: Main Stage

              Matrix     2              2   54691212     0
           Index Set     3              3    4321032     0
                 Vec    37             37  103708408     0
       Krylov Solver     1              1      17216     0
      Preconditioner     1              1        168     0
========================================================================================================================
Average time to get PetscTime(): 1.90735e-07
OptionTable: -log_summary
Compiled without FORTRAN kernels
Compiled with full precision matrices (default)
sizeof(short) 2 sizeof(int) 4 sizeof(long) 8 sizeof(void*) 8 sizeof(PetscScalar) 8
Configure run at: Tue Jan  8 22:22:08 2008
Configure options: --with-memcmp-ok --sizeof_char=1 --sizeof_void_p=8 --sizeof_short=2 --sizeof_int=4 --sizeof_long=8 --sizeof_long_long=8 --sizeof_float=4 --sizeof_double=8 --bits_per_byte=8 --sizeof_MPI_Comm=4 --sizeof_MPI_Fint=4 --with-vendor-compilers=intel --with-x=0 --with-hypre-dir=/home/enduser/g0306332/lib/hypre --with-debugging=0 --with-batch=1 --with-mpi-shared=0 --with-mpi-include=/usr/local/topspin/mpi/mpich/include --with-mpi-lib=/usr/local/topspin/mpi/mpich/lib/libmpich.a --with-mpirun=/usr/local/topspin/mpi/mpich/bin/mpirun --with-blas-lapack-dir=/opt/intel/cmkl/8.1.1/lib/em64t --with-shared=0
-----------------------------------------
Libraries compiled on Tue Jan  8 22:34:13 SGT 2008 on atlas3-c01
Machine characteristics: Linux atlas3-c01 2.6.9-42.ELsmp #1 SMP Wed Jul 12 23:32:02 EDT 2006 x86_64 x86_64 x86_64 GNU/Linux
Using PETSc directory: /nfs/home/enduser/g0306332/petsc-2.3.3-p8
Using PETSc arch: atlas3-mpi
-----------------------------------------
85.53user 1.22system 2:02.65elapsed 70%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (16major+46429minor)pagefaults 0swaps
Job  /usr/lsf62/bin/mvapich_wrapper time ./a.out -log_summary


2 processors:

Norm of error 0.3231E+01 iterations  1177
************************************************************************************************************************
***             WIDEN YOUR WINDOW TO 120 CHARACTERS.  Use 'enscript -r -fCourier9' to print this document            ***
************************************************************************************************************************

---------------------------------------------- PETSc Performance Summary: ----------------------------------------------

./a.out on a atlas3-mp named atlas3-c58 with 2 processors, by g0306332 Wed Apr 16 09:48:37 2008
Using Petsc Release Version 2.3.3, Patch 8, Fri Nov 16 17:03:40 CST 2007 HG revision: 414581156e67e55c761739b0deb119f7590d0f4b

                         Max       Max/Min        Avg      Total
Time (sec):           1.034e+02      1.00000   1.034e+02
Objects:              5.500e+01      1.00000   5.500e+01
Flops:                1.812e+10      1.00000   1.812e+10  3.625e+10
Flops/sec:            1.752e+08      1.00000   1.752e+08  3.504e+08
MPI Messages:         1.218e+03      1.00000   1.218e+03  2.436e+03
MPI Message Lengths:  5.844e+06      1.00000   4.798e+03  1.169e+07
MPI Reductions:       1.204e+03      1.00000

Flop counting convention: 1 flop = 1 real number operation of type (multiply/divide/add/subtract)
                            e.g., VecAXPY() for real vectors of length N --> 2N flops
                            and VecAXPY() for complex vectors of length N --> 8N flops

Summary of Stages:   ----- Time ------  ----- Flops -----  --- Messages ---  -- Message Lengths --  -- Reductions --
                        Avg     %Total     Avg     %Total   counts   %Total     Avg         %Total   counts   %Total
 0:      Main Stage: 1.0344e+02 100.0%  3.6250e+10 100.0%  2.436e+03 100.0%  4.798e+03      100.0%  2.407e+03 100.0%

------------------------------------------------------------------------------------------------------------------------
See the 'Profiling' chapter of the users' manual for details on interpreting output.
Phase summary info:
   Count: number of times phase was executed
   Time and Flops/sec: Max - maximum over all processors
                       Ratio - ratio of maximum to minimum over all processors
   Mess: number of messages sent
   Avg. len: average message length
   Reduct: number of global reductions
   Global: entire computation
   Stage: stages of a computation. Set stages with PetscLogStagePush() and PetscLogStagePop().
      %T - percent time in this phase         %F - percent flops in this phase
      %M - percent messages in this phase     %L - percent message lengths in this phase
      %R - percent reductions in this phase
   Total Mflop/s: 10e-6 * (sum of flops over all processors)/(max time over all processors)
------------------------------------------------------------------------------------------------------------------------


      ##########################################################
      #                                                        #
      #                          WARNING!!!                    #
      #                                                        #
      #   This code was run without the PreLoadBegin()         #
      #   macros. To get timing results we always recommend    #
      #   preloading. otherwise timing numbers may be          #
      #   meaningless.                                         #
      ##########################################################

Event                Count      Time (sec)     Flops/sec                         --- Global ---  --- Stage ---   Total
                   Max Ratio  Max     Ratio   Max  Ratio  Mess   Avg len Reduct  %T %F %M %L %R  %T %F %M %L %R Mflop/s
------------------------------------------------------------------------------------------------------------------------

--- Event Stage 0: Main Stage

MatMult             1217 1.0 1.2502e+01 1.2 1.88e+08 1.2 2.4e+03 4.8e+03 0.0e+00 11 11100100  0  11 11100100  0   315
MatSolve            1217 1.0 2.1088e+01 1.2 1.10e+08 1.2 0.0e+00 0.0e+00 0.0e+00 19 11  0  0  0  19 11  0  0  0   187
MatLUFactorNum         1 1.0 8.2862e-02 2.9 5.58e+07 2.9 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0    39
MatILUFactorSym        1 1.0 3.3310e-02 1.5 0.00e+00 0.0 0.0e+00 0.0e+00 1.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatAssemblyBegin       1 1.0 1.5567e-011854.8 0.00e+00 0.0 0.0e+00 0.0e+00 2.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatAssemblyEnd         1 1.0 1.0352e-01 1.0 0.00e+00 0.0 2.0e+00 2.4e+03 7.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatGetRowIJ            1 1.0 3.0994e-06 1.0 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatGetOrdering         1 1.0 5.0953e-0210.7 0.00e+00 0.0 0.0e+00 0.0e+00 2.0e+00  0  0  0  0  0   0  0  0  0  0     0
VecMDot             1177 1.0 4.0427e+01 1.1 1.85e+08 1.1 0.0e+00 0.0e+00 1.2e+03 37 36  0  0 49  37 36  0  0 49   323
VecNorm             1218 1.0 1.5475e+01 1.9 5.25e+07 1.9 0.0e+00 0.0e+00 1.2e+03 12  2  0  0 51  12  2  0  0 51    57
VecScale            1217 1.0 5.7866e-01 1.0 3.97e+08 1.0 0.0e+00 0.0e+00 0.0e+00  1  1  0  0  0   1  1  0  0  0   757
VecCopy               40 1.0 6.6697e-02 1.6 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
VecSet              1259 1.0 1.5276e+00 1.1 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  1  0  0  0  0   1  0  0  0  0     0
VecAXPY               80 1.0 2.1163e-01 2.4 3.21e+08 2.4 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0   272
VecMAXPY            1217 1.0 2.2980e+01 1.4 4.28e+08 1.4 0.0e+00 0.0e+00 0.0e+00 19 38  0  0  0  19 38  0  0  0   606
VecScatterBegin     1217 1.0 3.6620e-02 1.4 0.00e+00 0.0 2.4e+03 4.8e+03 0.0e+00  0  0100100  0   0  0100100  0     0
VecScatterEnd       1217 1.0 8.1980e-01 1.7 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  1  0  0  0  0   1  0  0  0  0     0
VecNormalize        1217 1.0 1.6030e+01 1.8 7.36e+07 1.8 0.0e+00 0.0e+00 1.2e+03 12  4  0  0 51  12  4  0  0 51    82
KSPGMRESOrthog      1177 1.0 5.7248e+01 1.0 2.35e+08 1.0 0.0e+00 0.0e+00 1.2e+03 55 72  0  0 49  55 72  0  0 49   457
KSPSetup               2 1.0 1.0363e-0110.5 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
KSPSolve               1 1.0 1.0289e+02 1.0 1.76e+08 1.0 2.4e+03 4.8e+03 2.4e+03 99100100100100  99100100100100   352
PCSetUp                2 1.0 1.5685e-01 2.3 2.40e+07 2.3 0.0e+00 0.0e+00 3.0e+00  0  0  0  0  0   0  0  0  0  0    21
PCSetUpOnBlocks        1 1.0 1.5668e-01 2.3 2.41e+07 2.3 0.0e+00 0.0e+00 3.0e+00  0  0  0  0  0   0  0  0  0  0    21
PCApply             1217 1.0 2.2625e+01 1.2 1.02e+08 1.2 0.0e+00 0.0e+00 0.0e+00 20 11  0  0  0  20 11  0  0  0   174
------------------------------------------------------------------------------------------------------------------------

Memory usage is given in bytes:

Object Type          Creations   Destructions   Memory  Descendants' Mem.

--- Event Stage 0: Main Stage

              Matrix     4              4   34540820     0
           Index Set     5              5    2164120     0
                 Vec    41             41   53315992     0
         Vec Scatter     1              1          0     0
       Krylov Solver     2              2      17216     0
      Preconditioner     2              2        256     0
========================================================================================================================
Average time to get PetscTime(): 1.90735e-07
Average time for MPI_Barrier(): 8.10623e-07
Average time for zero size MPI_Send(): 2.98023e-06
OptionTable: -log_summary
Compiled without FORTRAN kernels
Compiled with full precision matrices (default)
sizeof(short) 2 sizeof(int) 4 sizeof(long) 8 sizeof(void*) 8 sizeof(PetscScalar) 8
Configure run at: Tue Jan  8 22:22:08 2008

42.64user 0.28system 1:08.08elapsed 63%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (18major+28609minor)pagefaults 0swaps
1:08.08elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (18major+23666minor)pagefaults 0swaps


4 processors:

Norm of error 0.3090E+01 iterations   937
63.17user 0.05system 1:04.31elapsed 98%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (16major+13520minor)pagefaults 0swaps
53.13user 0.06system 1:04.31elapsed 82%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (15major+13414minor)pagefaults 0swaps
58.55user 0.23system 1:04.31elapsed 91%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (17major+18383minor)pagefaults 0swaps
20.36user 0.67system 1:04.33elapsed 32%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (14major+18392minor)pagefaults 0swaps
Job  /usr/lsf62/bin/mvapich_wrapper time ./a.out -log_summary



************************************************************************************************************************
***             WIDEN YOUR WINDOW TO 120 CHARACTERS.  Use 'enscript -r -fCourier9' to print this document            ***
************************************************************************************************************************

---------------------------------------------- PETSc Performance Summary: ----------------------------------------------

./a.out on a atlas3-mp named atlas3-c45 with 4 processors, by g0306332 Wed Apr 16 09:55:16 2008
Using Petsc Release Version 2.3.3, Patch 8, Fri Nov 16 17:03:40 CST 2007 HG revision: 414581156e67e55c761739b0deb119f7590d0f4b

                         Max       Max/Min        Avg      Total
Time (sec):           6.374e+01      1.00001   6.374e+01
Objects:              5.500e+01      1.00000   5.500e+01
Flops:                7.209e+09      1.00016   7.208e+09  2.883e+10
Flops/sec:            1.131e+08      1.00017   1.131e+08  4.524e+08
MPI Messages:         1.940e+03      2.00000   1.455e+03  5.820e+03
MPI Message Lengths:  9.307e+06      2.00000   4.798e+03  2.792e+07
MPI Reductions:       4.798e+02      1.00000

Flop counting convention: 1 flop = 1 real number operation of type (multiply/divide/add/subtract)
                            e.g., VecAXPY() for real vectors of length N --> 2N flops
                            and VecAXPY() for complex vectors of length N --> 8N flops

Summary of Stages:   ----- Time ------  ----- Flops -----  --- Messages ---  -- Message Lengths --  -- Reductions --
                        Avg     %Total     Avg     %Total   counts   %Total     Avg         %Total   counts   %Total
 0:      Main Stage: 6.3737e+01 100.0%  2.8832e+10 100.0%  5.820e+03 100.0%  4.798e+03      100.0%  1.919e+03 100.0%

------------------------------------------------------------------------------------------------------------------------
See the 'Profiling' chapter of the users' manual for details on interpreting output.
Phase summary info:
   Count: number of times phase was executed
   Time and Flops/sec: Max - maximum over all processors
                       Ratio - ratio of maximum to minimum over all processors
   Mess: number of messages sent
   Avg. len: average message length
   Reduct: number of global reductions
   Global: entire computation
   Stage: stages of a computation. Set stages with PetscLogStagePush() and PetscLogStagePop().
      %T - percent time in this phase         %F - percent flops in this phase
      %M - percent messages in this phase     %L - percent message lengths in this phase
      %R - percent reductions in this phase
   Total Mflop/s: 10e-6 * (sum of flops over all processors)/(max time over all processors)
------------------------------------------------------------------------------------------------------------------------


      ##########################################################
      #                                                        #
      #                          WARNING!!!                    #
      #                                                        #
      #   This code was run without the PreLoadBegin()         #
      #   macros. To get timing results we always recommend    #
      #   preloading. otherwise timing numbers may be          #
      #   meaningless.                                         #
      ##########################################################


Event                Count      Time (sec)     Flops/sec                         --- Global ---  --- Stage ---   Total
                   Max Ratio  Max     Ratio   Max  Ratio  Mess   Avg len Reduct  %T %F %M %L %R  %T %F %M %L %R Mflop/s
------------------------------------------------------------------------------------------------------------------------

--- Event Stage 0: Main Stage

MatMult              969 1.0 9.7564e+00 3.6 2.87e+08 3.6 5.8e+03 4.8e+03 0.0e+00  8 11100100  0   8 11100100  0   321
MatSolve             969 1.0 1.4244e+01 3.3 1.79e+08 3.3 0.0e+00 0.0e+00 0.0e+00 11 11  0  0  0  11 11  0  0  0   220
MatLUFactorNum         1 1.0 5.2070e-02 6.2 9.63e+07 6.2 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0    62
MatILUFactorSym        1 1.0 1.7911e-02 2.3 0.00e+00 0.0 0.0e+00 0.0e+00 1.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatAssemblyBegin       1 1.0 2.1741e-01164.3 0.00e+00 0.0 0.0e+00 0.0e+00 2.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatAssemblyEnd         1 1.0 3.5663e-02 1.0 0.00e+00 0.0 6.0e+00 2.4e+03 7.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatGetRowIJ            1 1.0 2.1458e-06 1.1 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
MatGetOrdering         1 1.0 1.2779e-03 1.2 0.00e+00 0.0 0.0e+00 0.0e+00 2.0e+00  0  0  0  0  0   0  0  0  0  0     0
VecMDot              937 1.0 3.5634e+01 2.1 1.52e+08 2.1 0.0e+00 0.0e+00 9.4e+02 48 36  0  0 49  48 36  0  0 49   292
VecNorm              970 1.0 1.4387e+01 2.9 3.55e+07 2.9 0.0e+00 0.0e+00 9.7e+02 18  2  0  0 51  18  2  0  0 51    49
VecScale             969 1.0 1.5714e-01 2.1 1.14e+09 2.1 0.0e+00 0.0e+00 0.0e+00  0  1  0  0  0   0  1  0  0  0  2220
VecCopy               32 1.0 1.8988e-02 1.2 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
VecSet              1003 1.0 1.1690e+00 3.8 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  1  0  0  0  0   1  0  0  0  0     0
VecAXPY               64 1.0 2.1091e-02 1.1 6.07e+08 1.1 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0  2185
VecMAXPY             969 1.0 1.4823e+01 3.4 6.26e+08 3.4 0.0e+00 0.0e+00 0.0e+00 11 38  0  0  0  11 38  0  0  0   747
VecScatterBegin      969 1.0 2.3238e-02 2.1 0.00e+00 0.0 5.8e+03 4.8e+03 0.0e+00  0  0100100  0   0  0100100  0     0
VecScatterEnd        969 1.0 1.4613e+0083.6 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  1  0  0  0  0   1  0  0  0  0     0
VecNormalize         969 1.0 1.4468e+01 2.8 5.15e+07 2.8 0.0e+00 0.0e+00 9.7e+02 18  4  0  0 50  18  4  0  0 50    72
KSPGMRESOrthog       937 1.0 3.9924e+01 1.3 1.68e+08 1.3 0.0e+00 0.0e+00 9.4e+02 59 72  0  0 49  59 72  0  0 49   521
KSPSetup               2 1.0 2.6190e-02 8.6 0.00e+00 0.0 0.0e+00 0.0e+00 0.0e+00  0  0  0  0  0   0  0  0  0  0     0
KSPSolve               1 1.0 6.2496e+01 1.0 1.15e+08 1.0 5.8e+03 4.8e+03 1.9e+03 98100100100 99  98100100100 99   461
PCSetUp                2 1.0 7.1320e-02 4.1 4.59e+07 4.1 0.0e+00 0.0e+00 3.0e+00  0  0  0  0  0   0  0  0  0  0    45
PCSetUpOnBlocks        1 1.0 7.1230e-02 4.1 4.62e+07 4.1 0.0e+00 0.0e+00 3.0e+00  0  0  0  0  0   0  0  0  0  0    45
PCApply              969 1.0 1.5379e+01 3.3 1.66e+08 3.3 0.0e+00 0.0e+00 0.0e+00 12 11  0  0  0  12 11  0  0  0   203
------------------------------------------------------------------------------------------------------------------------

Memory usage is given in bytes:

Object Type          Creations   Destructions   Memory  Descendants' Mem.

--- Event Stage 0: Main Stage

              Matrix     4              4   17264420     0
           Index Set     5              5    1084120     0
                 Vec    41             41   26675992     0
         Vec Scatter     1              1          0     0
       Krylov Solver     2              2      17216     0
      Preconditioner     2              2        256     0
========================================================================================================================
Average time to get PetscTime(): 1.90735e-07
Average time for MPI_Barrier(): 6.00815e-06
Average time for zero size MPI_Send(): 5.42402e-05
OptionTable: -log_summary
Compiled without FORTRAN kernels
Compiled with full precision matrices (default)
sizeof(short) 2 sizeof(int) 4 sizeof(long) 8 sizeof(void*) 8 sizeof(PetscScalar) 8
Configure run at: Tue Jan  8 22:22:08 2008



Matthew Knepley wrote:
The convergence here is jsut horrendous. Have you tried using LU to check
your implementation? All the time is in the solve right now. I would first
try a direct method (at least on a small problem) and then try to understand
the convergence behavior. MUMPS can actually scale very well for big problems.

  Matt