October 2022 - petsc-users - mailman3.cels.anl.gov

clarification on extreme eigenvalues from KSPComputeEigenvalues
by feng wang 06 Oct '22

06 Oct '22

Dear All, I am using the KSPComputeEigenvalues to understand the performance of my preconditioner, and I am using the right-preconditioned GMRES with ASM. In the user guide, it says this routine computes the extreme eigenvalues of the preconditioned operator. If I understand it correctly, these eigenvalues are the ones furthest away from (1,0)? If the preconditioning is perfect, all the eigenvalues should be (1,0). Thanks, Feng

2 4

How to use Intel OneApi mpi wrappers on Linux
by Paolo Lampitella 06 Oct '22

06 Oct '22

Dear PETSc users and developers, as per the title, I recently installed the base and HPC Intel OneApi toolkits on a machine running Ubuntu 20.04. As you probably know, OneApi comes with the classical compilers (icc, icpc, ifort) and relative mpi wrappers (mpiicc, mpiicpc, mpiifort) as well as with the new LLVM based compilers (icx, icpx, ifx). My experience so far with PETSc on Linux has been without troubles using both gcc compilers and either Mpich or OpenMPI and Intel classical compilers and MPI. However, I have now troubles using the MPI wrappers of the new LLVM compilers as, in fact, there aren’t dedicated mpi wrappers for them. Instead, they can be used with certain flags for the classical wrappers: mpiicc -cc=icx mpiicpc -cxx=icpx mpiifort -fc=ifx The problem I have is that I have no idea how to pass them correctly to the configure and whatever comes after that. Admittedly, I am just starting to use the new compilers, so I have no clue how I would use them in other projects as well. I started with an alias in my .bash_aliases (which works for simple compilation tests from command line) but doesn’t with configure. I also tried adding the flags to the COPTFLAGS, CXXOPTFLAGS and FOPTFLAGS but didn’t work as well. Do you have any experience with the new Intel compilers and, in case, could you share hot to properly use them with MPI? Thanks Paolo

5 10

Vector field ordering question
by Gong Yujie 06 Oct '22

06 Oct '22

Dear development team, I'm trying to write a code to deal with a multi-field problem. Currently I find that the vector ordering for the field is (a1,a2,a3,b1,b2,b3), here assume a1,a2,a3 belongs to one field and bs for another field. Can I get a point-block ordering for the unknowns as (a1,b1,a2,b2,a3,b3)? I'm using DMPlex for the mesh management and first use PetscFECreateDefault to create the PetscFE object, then use this object with DMAddField to add the field to the DMPlex object. DMCreateGlobalVector is used for generating vectors. I do the discretization myself instead of using PetscFE or PetscFV. My PETSc version is 3.16.0. Do you have a case using this point-block type data structure? Best Regards, Jerry

2 1

How to show the x window for cmd `make -f ./gmakefile test ...`?
by Zongze Yang 06 Oct '22

06 Oct '22

Hi, everyone, I am trying to run some test cases with x window, but the x window never showed up with command `make -f ./gmakefile test ...`. It seems a default option `-nox` is set. How to disable this option for `make test`? An example is shown below: ``` z2yang@ws6:~/repos/petsc$ PETSC_ARCH=arch-main-debug make -f ./gmakefile test search="dm_impls_plex_tests-ex20_2d" TIMEOUT=5000 EXTRA_OPTIONS="-post_adapt_dm_view draw:x -draw_pause -1 -options_view -petsc_ci false" Using MAKEFLAGS: -- EXTRA_OPTIONS=-post_adapt_dm_view draw:x -draw_pause -1 -options_view -petsc_ci false TIMEOUT=5000 search=dm_impls_plex_tests-ex20_2d TEST arch-main-debug/tests/counts/dm_impls_plex_tests-ex20_2d.counts ok dm_impls_plex_tests-ex20_2d not ok diff-dm_impls_plex_tests-ex20_2d # Error code: 1 # 12,22c12,26 # < DM Object: Post Adaptation Mesh 1 MPI process # < type: plex # < Post Adaptation Mesh in 2 dimensions: # < Number of 0-cells per rank: 49 # < Number of 1-cells per rank: 120 # < Number of 2-cells per rank: 72 # < Labels: # < celltype: 3 strata with value/size (1 (120), 3 (72), 0 (49)) # < depth: 3 strata with value/size (0 (49), 1 (120), 2 (72)) # < marker: 1 strata with value/size (1 (48)) # < Face Sets: 1 strata with value/size (1 (36)) # --- # > #PETSc Option Table entries: # > -check_pointer_intensity 0 # > -dm_coord_space 0 # > -dm_plex_box_faces 3,3 # > -draw_pause -1 # > -error_output_stdout # > -malloc_dump # > -nox # > -nox_warning # > -options_view # > -petsc_ci false # > -post_adapt_dm_view draw:x # > -pre_adapt_dm_view ascii::ascii_info # > -use_gpu_aware_mpi 0 # > #End of PETSc Option Table entries # FAILED diff-dm_impls_plex_tests-ex20_2d # # To rerun failed tests: # /usr/bin/gmake -f gmakefile test test-fail=1 ``` Thanks, Zongze

2 2

code with TS throws error at the end
by ashish bhole 05 Oct '22

05 Oct '22

Hi All, I am writing a code in Fortran to solve a linear advection equation using PETSc 3.18.0 (Vec and TS). It seems to work fine on my HP elitebook laptop with Fedora 30 OS and GCC 9.3.1. It gives acceptable numerical solutions, but throws the following error at the end, with as well as without parallel computing. The same error also appears with the slightly older version I tried: PETSc 3.14.0. The error message gives a hint for error locations, but I am unable to figure out what is wrong. I have attached a snippet for my TS usage lines. I spent some time searching for similar error reports but it was not so fruitful. So I am approaching the PETSc community for help understanding this error. Thank you. ------------------------------------ [0]PETSC ERROR: PetscTrFreeDefault() called from VecDestroy_Seq() at /home/abhole/lib/petsc-3.18.0/src/vec/vec/impls/seq/bvec2.c:753 [0]PETSC ERROR: Block [id=2154(800)] at address 0x2309ac0 is corrupted (probably write past end of array) [0]PETSC ERROR: Block allocated in VecCreate_Seq() at /home/abhole/lib/petsc-3.18.0/src/vec/vec/impls/seq/bvec3.c:34 [0]PETSC ERROR: --------------------- Error Message -------------------------------------------------------------- [0]PETSC ERROR: Memory corruption: https://petsc.org/release/faq/#valgrind [0]PETSC ERROR: Corrupted memory [0]PETSC ERROR: See https://petsc.org/release/faq/ for trouble shooting. [0]PETSC ERROR: Petsc Release Version 3.18.0, Sep 30, 2022 [0]PETSC ERROR: ./exe on a arch-linux-c-debug named ischia by abhole Wed Oct 5 13:06:27 2022 [0]PETSC ERROR: Configure options --with-cc=mpicc --with-cxx=mpicxx --with-fc=mpif90 --download-fblaslapack --download-scalapack --download-mumps --download-superlu --download-ptscotch --with-metis-include=/user/abhole/home/lib/metis-5.1.0/include --with-metis-lib=/user/abhole/home/lib/metis-5.1.0/lib/libmetis.a -lmetis --with-parmetis-include=/user/abhole/home/lib/parmetis-4.0.3/include --with-parmetis-lib=/user/abhole/home/lib/parmetis-4.0.3/lib/libparmetis.a -lparmetis -lmetis --with-hdf5-include=/user/abhole/home/lib/hdf5-1.8.18/include --with-hdf5-lib=/user/abhole/home/lib/hdf5-1.8.18/lib64/libhdf5.a --with-valgrind=1 --with-scalar-type=real --with-precision=double [0]PETSC ERROR: #1 PetscTrFreeDefault() at /home/abhole/lib/petsc-3.18.0/src/sys/memory/mtr.c:305 [0]PETSC ERROR: #2 VecDestroy_Seq() at /home/abhole/lib/petsc-3.18.0/src/vec/vec/impls/seq/bvec2.c:753 [0]PETSC ERROR: #3 VecDestroy() at /home/abhole/lib/petsc-3.18.0/src/vec/vec/interface/vector.c:521 [0]PETSC ERROR: #4 VecDestroyVecs_Default() at /home/abhole/lib/petsc-3.18.0/src/vec/vec/interface/vector.c:977 [0]PETSC ERROR: #5 VecDestroyVecs() at /home/abhole/lib/petsc-3.18.0/src/vec/vec/interface/vector.c:606 [0]PETSC ERROR: #6 TSRKTableauReset() at /home/abhole/lib/petsc-3.18.0/src/ts/impls/explicit/rk/rk.c:1102 [0]PETSC ERROR: #7 TSReset_RK() at /home/abhole/lib/petsc-3.18.0/src/ts/impls/explicit/rk/rk.c:1109 [0]PETSC ERROR: #8 TSReset() at /home/abhole/lib/petsc-3.18.0/src/ts/interface/ts.c:2644 [0]PETSC ERROR: #9 TSDestroy() at /home/abhole/lib/petsc-3.18.0/src/ts/interface/ts.c:2706 [0]PETSC ERROR: #10 main.F90:159 ------------------------------------------ -- With Regards Ashish Bhole

2 1

Is the results of `DMAdaptLabel` as expected in `src/dm/impls/plex/tests/ex20.c`
by Zongze Yang 05 Oct '22

05 Oct '22

Hi everyone, I am learning how to use the `DMAdaptLabel` for `DMPlex`, and found the example `src/dm/impls/plex/tests/ex20.c` which label one cell to refine. 1. This example is just a uniform refinement when using the following command. (see attached pdfs for the results). ``` [real-int32-gcc] z2yang@ws5:~/opt/firedrake/real-int32-gcc/petsc/src/dm/impls/plex/tests$ ./ex20 -dm_plex_box_faces 3,3 -dm_coord_space 0 -pre_adapt_dm_view ascii::ascii_info -post_adapt_dm_view draw:tikz:figure2.tex ``` Is this expected for this example? 2. I found there is a function named `DMAdaptLabel_Plex`, and `DMAdaptLabel` did not call that function when the type of the dm is `DMPlex`. Is the function `DMAdaptLabel_Plex` still in use? 3. `DMAdaptLabel` seems to lack some useful information when I use the wrong adaptor. For example, if I set `-dm_adaptor mmg`, then the process will give a segment fault because the `metric` passed to `DMAdaptMetric_Mmg_Plex` is NULL, see the output below: ``` [real-int32-gcc] z2yang@ws5:~/opt/firedrake/real-int32-gcc/petsc/src/dm/impls/plex/tests$ ./ex20 -dm_plex_box_faces 3,3 -dm_coord_space 0 -pre_adapt_dm_view draw:tikz:figure1.tex -post_adapt_dm_view draw:tikz:figure2.tex -dm_adaptor mmg [0]PETSC ERROR: ------------------------------------------------------------------------ [0]PETSC ERROR: Caught signal number 11 SEGV: Segmentation Violation, probably memory access out of range [0]PETSC ERROR: Try option -start_in_debugger or -on_error_attach_debugger [0]PETSC ERROR: or see https://petsc.org/release/faq/#valgrind and https://petsc.org/release/faq/ [0]PETSC ERROR: configure using --with-debugging=yes, recompile, link, and run [0]PETSC ERROR: to get more information on the crash. [0]PETSC ERROR: Run with -malloc_debug to check if memory corruption is causing the crash. Abort(59) on node 0 (rank 0 in comm 0): application called MPI_Abort(MPI_COMM_WORLD, 59) - process 0 ``` Thanks, Zongze Yang

2 3

Problem reading and HDF5 binary file
by fujisan 04 Oct '22

04 Oct '22

Hi everyone, I have written a matrix in an HDF5 binary file without problem using PetscViewerHDF5Open function like this: ! Write if (ishdf5) then PetscCall(PetscViewerHDF5Open(PETSC_COMM_WORLD,trim(filename ),FILE_MODE_WRITE,view,ierr)) else PetscCall(PetscViewerBinaryOpen(PETSC_COMM_WORLD,trim(filename ),FILE_MODE_WRITE,view,ierr)) endif PetscCall(MatView(A,view,ierr)) PetscCall(PetscViewerDestroy(view,ierr)) But when I want to read that HDF5 file like this: ! Read if (ishdf5) then PetscCall(PetscViewerHDF5Open(PETSC_COMM_WORLD,trim(filename ),FILE_MODE_READ,view,ierr)) else PetscCall(PetscViewerBinaryOpen(PETSC_COMM_WORLD,trim(filename ),FILE_MODE_READ,view,ierr)) endif PetscCall(MatCreate(PETSC_COMM_WORLD,A,ierr)) PetscCall(MatSetType(A,MATMPIAIJ,ierr)) PetscCall(MatLoad(A,view,ierr)) PetscCall(PetscViewerDestroy(view,ierr)) I get this kind of error message below. I don't have any problem writing / reading using PetscViewerBinaryOpen, and no problem writing / reading a vector using PetscViewerHDF5Open either. What am I missing ? Fuji [0]PETSC ERROR: --------------------- Error Message -------------------------------------------------------------- [0]PETSC ERROR: Unexpected data in file [0]PETSC ERROR: Attribute /Mat_0xc4000016_0/MATLAB_sparse does not exist and default value not provided [0]PETSC ERROR: See https://petsc.org/release/faq/ for trouble shooting. [0]PETSC ERROR: Petsc Release Version 3.18.0, unknown [0]PETSC ERROR: ./bin/solve on a x86_64 named master by beauduin Tue Oct 4 08:55:55 2022 [0]PETSC ERROR: Configure options --with-petsc-arch=x86_64 --COPTFLAGS="-g -O3" --FOPTFLAGS="-g -O3" --CXXOPTFLAGS="-g -O3" --with-debugging=0 --with-cc=mpiicc --with-cxx=mpiicpc --with-fc=mpiifort --with-single-library=1 --with-mpiexec=mpiexec --with-precision=double --with-fortran-interfaces=1 --with-make=1 --with-mpi=1 --with-mpi-compilers=1 --download-fblaslapack=0 --download-hypre=1 --download-cmake=0 --with-cmake=1 --download-metis=1 --download-parmetis=1 --download-ptscotch=0 --download-suitesparse=1 --download-triangle=1 --download-superlu=1 --download-superlu_dist=1 --download-scalapack=1 --download-mumps=1 --download-elemental=1 --download-spai=0 --download-parms=1 --download-moab=1 --download-chaco=0 --download-fftw=1 --with-petsc4py=1 --download-mpi4py=1 --download-saws --download-concurrencykit=1 --download-revolve=1 --download-cams=1 --download-p4est=0 --with-zlib=1 --with-hdf5=1 --download-hdf5=1 --download-mfem=1 --download-glvis=0 --with-opengl=0 --download-libpng=1 --download-libjpeg=1 --download-slepc=1 --download-hpddm=1 --download-bamg=1 --download-mmg=0 --download-parmmg=0 --download-htool=1 --download-egads=0 --download-opencascade=0 PETSC_ARCH=x86_64 [0]PETSC ERROR: #1 PetscViewerHDF5ReadAttribute() at /data/softs/petsc/src/sys/classes/viewer/impls/hdf5/hdf5v.c:1245 [0]PETSC ERROR: #2 MatLoad_AIJ_HDF5() at /data/softs/petsc/src/mat/impls/aij/seq/aijhdf5.c:63 [0]PETSC ERROR: #3 MatLoad_MPIAIJ() at /data/softs/petsc/src/mat/impls/aij/mpi/mpiaij.c:3034 [0]PETSC ERROR: #4 MatLoad() at /data/softs/petsc/src/mat/interface/matrix.c:1304 [0]PETSC ERROR: #5 bigmat.F90:62 [0]PETSC ERROR: #6 MatCreateVecs() at /data/softs/petsc/src/mat/interface/matrix.c:9336 [0]PETSC ERROR: #7 solve.F90:143 Abort(73) on node 0 (rank 0 in comm 16): application called MPI_Abort(MPI_COMM_SELF, 73) - process 0 forrtl: severe (174): SIGSEGV, segmentation fault occurred Image PC Routine Line Source solve 000000000043258A Unknown Unknown Unknown libpthread-2.28.s 00007FCAF0B78C20 Unknown Unknown Unknown libmpi.so.12.0.0 00007FCAF17A09D3 Unknown Unknown Unknown ....

1 2

Differences between main and release branches?
by fujisan 03 Oct '22

03 Oct '22

Hi everyone, What are the differences between the 'main' and 'release' branches? Where I git cloned version 3.17.4, I was by default in the 'main' branch. Where I git cloned version 3.18.0 (I haven't git pulled from 3.17.4 yet), I was by default in the 'release' branch. Fuji

3 4