[petsc-users] Debugger question

plication called MPI_Abort(MPI_COMM_WORLD, 0) - process 0 >> > _pmii_daemon(SIGCHLD): [NID 10649] [c23-3c0s6n1] [Mon Apr 2 13:06:48 >> 2012] PE 0 exit signal Aborted >> > Application 133198 exit codes: 134 >> > Application 133198 resources: utime ~1s, stime ~0s >> >> > > > -- > What most experimenters take for granted before they begin their > experiments is infinitely more interesting than any results to which their > experiments lead. > -- Norbert Wiener > > > -- What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead. -- Norbert Wiener -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/93e0a49c/attachment-0001.htm>

[petsc-users] Debugger question

plication called MPI_Abort(MPI_COMM_WORLD, 0) - process 0 >> > _pmii_daemon(SIGCHLD): [NID 10649] [c23-3c0s6n1] [Mon Apr 2 13:06:48 >> 2012] PE 0 exit signal Aborted >> > Application 133198 exit codes: 134 >> > Application 133198 resources: utime ~1s, stime ~0s >> >> > > > -- > What most experimenters take for granted before they begin their > experiments is infinitely more interesting than any results to which their > experiments lead. > -- Norbert Wiener > > > -- What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead. -- Norbert Wiener -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/dcbe3ead/attachment.htm>

[petsc-users] Debugger question

Satish Things work fine on my linux machine (and other linux clusters) and valgrind shows no error. Unfortunately Totalview (GUI starts fine on the node) gives me a licensing error on the Cray. I will continue to explore. Thanks Tabrez On 04/02/2012 09:05 PM, Satish Balay wrote: > Sounds like

[petsc-users] Debugger question

2 > 13:06:48 2012] PE 0 exit signal Aborted > > Application 133198 exit codes: 134 > > Application 133198 resources: utime ~1s, stime ~0s > > > > > -- > What most experimenters take for granted before they begin their > experiments is infinitely more interesting than any results to which > their experiments lead. > -- Norbert Wiener -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/2b63becd/attachment.htm>

[petsc-users] ex52_integrateElement.cu

t;> >>>>>>>>> SCRGP2$ ./ex52 -dim 2 -compute_function -show_residual -batch >>>>>>>>> Residual: >>>>>>>>> Vector Object: 1 MPI processes >>>>>>>>> type: seq >>>>>>>>> -0.25 >>>>>>>>> -0.5 >>>>>>>>> 0.25 >>>>>>>>> -0.5 >>>>>>>>> -1 >>>>>>>>> 0.5 >>>>>>>>> 0.25 >>>>>>>>> 0.5 >>>>>>>>> 0.75 >>>>>>>>> SCRGP2$ ./ex52 -dim 2 -compute_function -show_residual -batch -gpu >>>>>>>>> [0]PETSC ERROR: IntegrateElementBatchGPU() line 323 in >>>>>>>>> src/snes/examples/tutorials/ex52_integrateElement.cu >>>>>>>>> [0]PETSC ERROR: FormFunctionLocalBatch() line 679 in >>>>>>>>> src/snes/examples/tutorials/ex52.c >>>>>>>>> [0]PETSC ERROR: SNESDMComplexComputeFunction() line 431 in >>>>>>>>> src/snes/utils/damgsnes.c >>>>>>>>> [0]PETSC ERROR: main() line 1021 in >>>>>>>>> src/snes/examples/tutorials/ex52.c >>>>>>>>> application called MPI_Abort(MPI_COMM_WORLD, 35) - process 0 >>>>>>>>> >>>>>>>> >>>>>>>> This is failing on cudaMalloc(), which means your card is not >>>>>>>> available for running. Are you trying to run on your laptop? >>>>>>>> If so, applications like Preview can lock up the GPU. I know of no >>>>>>>> way to test this in CUDA while running. I just close >>>>>>>> apps until it runs. >>>>>>>> >>>>>>>> Thanks, >>>>>>>> >>>>>>>> Matt >>>>>>>> >>>>>>>> >>>>>>>>> >>>>>>>>> On Tue, Mar 27, 2012 at 8:37 PM, Matthew Knepley < >>>>>>>>> knepley at gmail.com> wrote: >>>>>>>>> >>>>>>>>>> On Tue, Mar 27, 2012 at 2:10 PM, Blaise Bourdin >>>>>>>>> lsu.edu>wrote: >>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> On Mar 27, 2012, at 1:23 PM, Matthew Knepley wrote: >>>>>>>>>>> >>>>>>>>>>> On Tue, Mar 27, 2012 at 12:58 PM, David Fuentes < >>>>>>>>>>> fuentesdt at gmail.com> wrote: >>>>>>>>>>> >>>>>>>>>>>> Hi, >>>>>>>>>>>> >>>>>>>>>>>> I had a question about the status of example 52. >>>>>>>>>>>> >>>>>>>>>>>> >>>>>>>>>>>> http://petsc.cs.iit.edu/petsc/petsc-dev/file/a8e2f2c19319/src/snes/examples/tutorials/ex52.c >>>>>>>>>>>> >>>>>>>>>>>> http://petsc.cs.iit.edu/petsc/petsc-dev/file/a8e2f2c19319/src/snes/examples/tutorials/ex52_integrateElement.cu >>>>>>>>>>>> >>>>>>>>>>>> >>>>>>>>>>>> Can this example be used with a DM object created from an >>>>>>>>>>>> unstructured exodusII mesh, DMMeshCreateExodus, And the FEM >>>>>>>>>>>> assembly done >>>>>>>>>>>> on GPU ? >>>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> 1) I have pushed many more tests for it now. They can be run >>>>>>>>>>> using the Python build system >>>>>>>>>>> >>>>>>>>>>> ./config/builder2.py check src/snes/examples/tutorials/ex52.c >>>>>>>>>>> >>>>>>>>>>> in fact, you can build any set of files this way. >>>>>>>>>>> >>>>>>>>>>> 2) The Exodus creation has to be converted to DMComplex from >>>>>>>>>>> DMMesh. That should not take me very long. Blaise maintains that >>>>>>>>>>> so maybe there will be help :) You will just replace >>>>>>>>>>> DMComplexCreateBoxMesh() with DMComplexCreateExodus(). If you >>>>>>>>>>> request >>>>>>>>>>> it, I will bump it up the list. >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> DMMeshCreateExodusNG is much more flexible >>>>>>>>>>> than DMMeshCreateExodus in that it can read meshes with multiple >>>>>>>>>>> element >>>>>>>>>>> types and should have a much lower memory footprint. The code >>>>>>>>>>> should be >>>>>>>>>>> fairly easy to read. you can email me directly if you have specific >>>>>>>>>>> questions. I had looked at creating a DMComplex and it did not look >>>>>>>>>>> too >>>>>>>>>>> difficult, as long as interpolation is not needed. I have plans to >>>>>>>>>>> write DMComplexCreateExodus, but haven't had time too so far. >>>>>>>>>>> Updating the >>>>>>>>>>> Vec viewers and readers may be a bit more involved. In perfect >>>>>>>>>>> world, one >>>>>>>>>>> would write an EXODUS viewer following the lines of the VTK and >>>>>>>>>>> HDF5 ones. >>>>>>>>>>> >>>>>>>>>> >>>>>>>>>> David and Blaise, I have converted this function, now >>>>>>>>>> DMComplexCreateExodus(). Its not tested, but I think >>>>>>>>>> Blaise has some stuff we can use to test it. >>>>>>>>>> >>>>>>>>>> Thanks, >>>>>>>>>> >>>>>>>>>> Matt >>>>>>>>>> >>>>>>>>>> >>>>>>>>>>> Blaise >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> Let me know if you can run the tests. >>>>>>>>>>> >>>>>>>>>>> Thanks >>>>>>>>>>> >>>>>>>>>>> Matt >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>>> Thanks, >>>>>>>>>>>> David >>>>>>>>>>>> >>>>>>>>>>> -- >>>>>>>>>>> What most experimenters take for granted before they begin their >>>>>>>>>>> experiments is infinitely more interesting than any results to >>>>>>>>>>> which their >>>>>>>>>>> experiments lead. >>>>>>>>>>> -- Norbert Wiener >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> -- >>>>>>>>>>> Department of Mathematics and Center for Computation & Technology >>>>>>>>>>> Louisiana State University, Baton Rouge, LA 70803, USA >>>>>>>>>>> Tel. +1 (225) 578 1612, Fax +1 (225) 578 4276 >>>>>>>>>>> http://www.math.lsu.edu/~bourdin >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>> >>>>>>>>>> >>>>>>>>>> -- >>>>>>>>>> What most experimenters take for granted before they begin their >>>>>>>>>> experiments is infinitely more interesting than any results to which >>>>>>>>>> their >>>>>>>>>> experiments lead. >>>>>>>>>> -- Norbert Wiener >>>>>>>>>> >>>>>>>>> >>>>>>>>> >>>>>>>> >>>>>>>> >>>>>>>> -- >>>>>>>> What most experimenters take for granted before they begin their >>>>>>>> experiments is infinitely more interesting than any results to which >>>>>>>> their >>>>>>>> experiments lead. >>>>>>>> -- Norbert Wiener >>>>>>>> >>>>>>> >>>>>>> >>>>>> >>>>>> >>>>>> -- >>>>>> What most experimenters take for granted before they begin their >>>>>> experiments is infinitely more interesting than any results to which >>>>>> their >>>>>> experiments lead. >>>>>> -- Norbert Wiener >>>>>> >>>>> >>>>> >>>> >>> >>> >>> -- >>> What most experimenters take for granted before they begin their >>> experiments is infinitely more interesting than any results to which their >>> experiments lead. >>> -- Norbert Wiener >>> >> >> > > > -- > What most experimenters take for granted before they begin their > experiments is infinitely more interesting than any results to which their > experiments lead. > -- Norbert Wiener > -- What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead. -- Norbert Wiener -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/bfdfce0e/attachment-0001.htm>

[petsc-users] Debugger question

Sounds like a Cray machine. start_in_debugger is useful for debugging on workstations [or clusters] etc where there is some control on X11 tunnels. Also 'xterm','gdb' or similar debugger should be available on the compute nodes [along with a x/ssh tunnel]. On a cray - you are better off looking f

[petsc-users] Debugger question

ng job: > > application called MPI_Abort(MPI_COMM_WORLD, 0) - process 0 > > _pmii_daemon(SIGCHLD): [NID 10649] [c23-3c0s6n1] [Mon Apr 2 13:06:48 > 2012] PE 0 exit signal Aborted > > Application 133198 exit codes: 134 > > Application 133198 resources: utime ~1s, stime ~

[petsc-users] Debugger question

On Apr 2, 2012, at 8:10 PM, Tabrez Ali wrote: > Hello > > I am trying to debug a program using the switch '-on_error_attach_debugger' > but the vendor/sysadmin built PETSc 3.2.00 is unable to start the debugger > in xterm (see text below). But xterm is installed. What am I doing wrong? > > B

[petsc-users] Debugger question

] PE 0 exit signal Aborted > Application 133198 exit codes: 134 > Application 133198 resources: utime ~1s, stime ~0s > -- What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead. -- Norbert Wiener -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/cef9d865/attachment.htm>

[petsc-users] Debugger question

Hello I am trying to debug a program using the switch '-on_error_attach_debugger' but the vendor/sysadmin built PETSc 3.2.00 is unable to start the debugger in xterm (see text below). But xterm is installed. What am I doing wrong? Btw the segfault happens during a call to MatMult but only wit

[petsc-users] ML and linear elasticity

Oh, OK, so you do not explicitly scale the matrix good. We had a user (John) recently that was using diagonal scaling and was getting failure with GAMG and then GAMG worked and he was no longer using diagonal scaling so I was thinking this was the problem. Mark On Apr 2, 2012, at 7:40 PM, Bar

[petsc-users] ML and linear elasticity

> scaling? If it is Mat then we might want MatSetNearNullSpace to do this, > otherwise we should think of a good way to deal with this. It is very error > prone to not do the right thing here, we should at least throw an error. > > -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/ca84edbd/attachment.htm>

[petsc-users] ML and linear elasticity

ht thing here, we should at least throw an error. -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/d671cf89/attachment.htm>

[petsc-users] ML and linear elasticity

Mark, Who would be doing the "diagonal scaling". Under normal conditions we never want to be passing to any preconditioner a diagonally scaled matrix (for exactly the issue you point out) so why are you worried about that case? Barry On Apr 2, 2012, at 6:40 PM, Mark F. Adams wrote: >

[petsc-users] ML and linear elasticity

is currently working with ML and reply to this message.) > > > -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/67a9a7ab/attachment.htm>

[petsc-users] transfer vector data diagonally on DA

cal (DMGlobalToLocalBegin/End) using a BOX stencil > with width at least 1, get the global array u_new[][][] from UGlobalNew and > the local arrays u[][][] from Ulocal, then assign u_new[k][j][i] = > u[k-1][j-1][i-1]. > > > > > > -- > What most experimenters take for granted before they begin their > experiments is infinitely more interesting than any results to which their > experiments lead. > -- Norbert Wiener > > > -- What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead. -- Norbert Wiener -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/1e98dcc6/attachment-0001.htm>

[petsc-users] ML and linear elasticity

modes have to be scaled appropriately). Who owns > the diagonal scaling? If it is Mat then we might want MatSetNearNullSpace > to do this, otherwise we should think of a good way to deal with this. It > is very error prone to not do the right thing here, we should at least > throw an error. > >> > >> > > > > > > -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/e30f220d/attachment-0001.htm>

[petsc-users] ML and linear elasticity

> > -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/d18642d0/attachment.htm>

[petsc-users] Scalability of PETSc

c KSP tutorials - KSP Laplacian, 2d (ex2.c) for mesh dim of n = 15 m = 100 Thanks Bibrak -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/6cbea21c/attachment.htm>

[petsc-users] ML and linear elasticity

HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/b6214df8/attachment.htm>

[petsc-users] ML and linear elasticity

use ML in an optimal manner for vector problems. Regards, Nicolas -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/9bee5c8a/attachment.htm>

[petsc-users] transfer vector data diagonally on DA

[k-1][j-1][i-1]. > > -- What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead. -- Norbert Wiener -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/198a0763/attachment.htm>

[petsc-users] dmmg_grid_sequence

gt; Like flowing water, the spirit stays free > http://www.loyno.edu/~li/home > New Orleans, Louisiana (504)865-2051(fax) > > -- What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead. -- Norbert Wiener -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/b6ef910c/attachment-0001.htm>

[petsc-users] ML and linear elasticity

> in order to use ML in an optimal manner for vector problems. >> >> The block size is used if you don't provide any other information. The >> preferred approach with petsc-dev is to use MatSetNearNullSpace(). (I'll >> make sure this is currently working with ML and reply to this message.) > > -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/d994becc/attachment.htm>

[petsc-users] dmmg_grid_sequence

On Mon, 2 Apr 2012, Matthew Knepley wrote: > On Mon, Apr 2, 2012 at 10:11 AM, Xuefeng Li wrote: > >> Hi, all. >> >> I am using multigrid with DMMG (5 levels) in my petsc program. >> Turning on the dmmg_grid_sequence option seems >> to slow down the program dramatically. For instance, >> the progr

[petsc-users] ML and linear elasticity

- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/ff42ce83/attachment.htm>

[petsc-users] dmmg_grid_sequence

nt was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/555a58f0/attachment.htm>

[petsc-users] dmmg_grid_sequence

Hi, all. I am using multigrid with DMMG (5 levels) in my petsc program. Turning on the dmmg_grid_sequence option seems to slow down the program dramatically. For instance, the program converges in 3 iterations in 6.270e+01 sec when dmmg_grid_sequence is OFF; it also converges in 3 iterations but i

[petsc-users] ML and linear elasticity

rently working with ML and reply to this message.) -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/bc15d0bf/attachment.htm>

[petsc-users] Scalability of PETSc

Bibrak, Start with http://www.mcs.anl.gov/petsc/documentation/faq.html#computers Then http://www.mcs.anl.gov/petsc/documentation/faq.html#log-summary and http://www.mcs.anl.gov/petsc/documentation/faq.html#slowerparallel Barry On Apr 2, 2012, at 7:37 AM, Bibrak Qamar wrote:

[petsc-users] transfer vector data diagonally on DA

[i] = > u[k-1][j-1][i-1]. > > > -- What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead. -- Norbert Wiener -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/485ddc8d/attachment.htm>

[petsc-users] transfer vector data diagonally on DA

east 1, get the global array u_new[][][] from UGlobalNew and the local arrays u[][][] from Ulocal, then assign u_new[k][j][i] = u[k-1][j-1][i-1]. -- next part -- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120402/b9318138/attachment-0001.htm>