[petsc-dev] asm / gasm
Mark Adams
mfadams at lbl.gov
Fri Jun 24 09:49:39 CDT 2016
Also, note that the problem, that I am running, has inactive processors
(ie, empty processors) on non-coarsest (ie, grids with smoothers). I don't
know if my old problems that (I recall) ASM worked had that.
On Fri, Jun 24, 2016 at 4:37 PM, Mark Adams <mfadams at lbl.gov> wrote:
>
>>> > Just to be clear: ASM used to work. Did the semantics of ASM change?
>>>
>>
>> Hi Mark,
>>
>> Assume that you said GASM used to work, and now is not working any more.
>>
>>
> I see everyone thinks that, but (intended to) said ASM, not GASM, used to
> work.
>
>
>> GASM was originally written by Dmitry. The basic idea is to allow
>> mulit-rank blocks, that is, a mulit-rank subdomain problem could be solved
>> using a small number of processor cores in parallel. This is different from
>> ASM.
>>
>> I was involved into the development of GASM last summer. There are some
>> changes:
>>
>> (1) Added a function to increase overlap of the multi-rank subdomains.
>> The function is called by GASM in default.
>>
>> (2) Added a hierarchical partitioning to optimize data exchange. Ensure
>> that small subdomains in a multi-rank subdomain are geometrically
>> connected. GASM does not use this functionality in default.
>>
>> Any way, if you have an example (like Barry asked) showing the broken
>> GASM, I will debug into it (of course, if Barry does not mind).
>>
>> Fande Kong,
>>
>>
>>>
>>> Show me a commit where ASM worked! Do you mean that the GASM worked?
>>> The code has GASM calls in it, not ASM so how could ASM have previously
>>> worked? It is possible that something changed in GASM that broke GAMG's
>>> usage of GASM. Once you tell me how to reproduce the problem with GASM I
>>> can try to track down the problem.
>>>
>>> >
>>> > But before that please please tell me the command line argument
>>> and example you use where the GASM crashes so I can get that fixed. Then I
>>> will look at using ASM instead after I have the current GASM code running
>>> again.
>>> >
>>> > In branch mark/gamg-agg-asm in ksp ex56, 'make runex56':
>>>
>>> I don't care about this! This is where you have tried to change from
>>> GASM to ASM which I told you is non-trivial. Give me the example and
>>> command line where the GASM version in master (or maint) doesn't work where
>>> the error message includes ** Max-trans not allowed because matrix is
>>> distributed
>>>
>>> We are not communicating very well, you jumped from stating GASM
>>> crashed to monkeying with ASM and now refuse to tell me how to reproduce
>>> the GASM crash. We have to start by fixing the current code to work with
>>> GASM (if it ever worked) and then move on to using ASM (which is just an
>>> optimization of the GASM usage.)
>>>
>>>
>>> Barry
>>>
>>>
>>> >
>>> > 14:12 nid00495 ~/petsc/src/ksp/ksp/examples/tutorials$ make runex56
>>> > [0]PETSC ERROR: --------------------- Error Message
>>> --------------------------------------------------------------
>>> > [0]PETSC ERROR: Petsc has generated inconsistent data
>>> > [0]PETSC ERROR: MPI_Allreduce() called in different locations (code
>>> lines) on different processors
>>> > [0]PETSC ERROR: See
>>> http://www.mcs.anl.gov/petsc/documentation/faq.html for trouble
>>> shooting.
>>> > [0]PETSC ERROR: Petsc Development GIT revision: v3.7.2-633-g4f88208
>>> GIT Date: 2016-06-23 18:53:31 +0200
>>> > [0]PETSC ERROR:
>>> /global/u2/m/madams/petsc/src/ksp/ksp/examples/tutorials/./ex56 on a
>>> arch-xc30-dbg64-intel named nid00495 by madams Thu Jun 23 14:12:57 2016
>>> > [0]PETSC ERROR: Configure options --COPTFLAGS="-no-ipo -g -O0"
>>> --CXXOPTFLAGS="-no-ipo -g -O0" --FOPTFLAGS="-fast -no-ipo -g -O0"
>>> --download-parmetis --download-metis --with-ssl=0 --with-cc=cc
>>> --with-clib-autodetect=0 --with-cxx=CC --with-cxxlib-autodetect=0
>>> --with-debugging=1 --with-fc=0 --with-shared-libraries=0 --with-x=0
>>> --with-mpiexec=srun LIBS=-lstdc++ --with-64-bit-indices
>>> PETSC_ARCH=arch-xc30-dbg64-intel
>>> > [0]PETSC ERROR: #1 MatGetSubMatrices_MPIAIJ() li
>>> >
>>> >
>>> >
>>> >
>>> >
>>> >
>>> >
>>> >
>>> >
>>> >
>>> > Barry
>>> >
>>> >
>>> > > On Jun 23, 2016, at 4:19 PM, Mark Adams <mfadams at lbl.gov> wrote:
>>> > >
>>> > > The question boils down to, for empty processors do we:
>>> > >
>>> > > ierr = ISCreateGeneral(PETSC_COMM_SELF, 0, NULL, PETSC_COPY_VALUES,
>>> &is);CHKERRQ(ierr);
>>> > > ierr = PCASMSetLocalSubdomains(subpc, 1, &is,
>>> NULL);CHKERRQ(ierr);
>>> > > ierr = ISDestroy(&is);CHKERRQ(ierr);
>>> > >
>>> > > or
>>> > >
>>> > > PCASMSetLocalSubdomains(subpc, 0, NULL, NULL);
>>> > >
>>> > > The later gives and error that one domain is need and the later
>>> gives an error (appended).
>>> > >
>>> > > I've checked in the code for this second error in ksp (make runex56)
>>> > >
>>> > > Thanks,
>>> > >
>>> > > [0]PETSC ERROR: --------------------- Error Message
>>> --------------------------------------------------------------
>>> > > [0]PETSC ERROR: Petsc has generated inconsistent data
>>> > > [0]PETSC ERROR: MPI_Allreduce() called in different locations (code
>>> lines) on different processors
>>> > > [0]PETSC ERROR: See
>>> http://www.mcs.anl.gov/petsc/documentation/faq.html for trouble
>>> shooting.
>>> > > [0]PETSC ERROR: Petsc Development GIT revision: v3.7.2-633-g4f88208
>>> GIT Date: 2016-06-23 18:53:31 +0200
>>> > > [0]PETSC ERROR:
>>> /global/u2/m/madams/petsc/src/ksp/ksp/examples/tutorials/./ex56 on a
>>> arch-xc30-dbg64-intel named nid00495 by madams Thu Jun 23 14:12:57 2016
>>> > > [0]PETSC ERROR: Configure options --COPTFLAGS="-no-ipo -g -O0"
>>> --CXXOPTFLAGS="-no-ipo -g -O0" --FOPTFLAGS="-fast -no-ipo -g -O0"
>>> --download-parmetis --download-metis --with-ssl=0 --with-cc=cc
>>> --with-clib-autodetect=0 --with-cxx=CC --with-cxxlib-autodetect=0
>>> --with-debugging=1 --with-fc=0 --with-shared-libraries=0 --with-x=0
>>> --with-mpiexec=srun LIBS=-lstdc++ --with-64-bit-indices
>>> PETSC_ARCH=arch-xc30-dbg64-intel
>>> > > [0]PETSC ERROR: #1 MatGetSubMatrices_MPIAIJ() line 1147 in
>>> /global/u2/m/madams/petsc/src/mat/impls/aij/mpi/mpiov.c
>>> > > [0]PETSC ERROR: #2 MatGetSubMatrices_MPIAIJ() line 1147 in
>>> /global/u2/m/madams/petsc/src/mat/impls/aij/mpi/mpiov.c
>>> > > [1]PETSC ERROR: --------------------- Error Message
>>> --------------------------------------------------------------
>>> > >
>>> > > On Thu, Jun 23, 2016 at 8:05 PM, Barry Smith <bsmith at mcs.anl.gov>
>>> wrote:
>>> > >
>>> > > Where is the command line that generates the error?
>>> > >
>>> > >
>>> > > > On Jun 23, 2016, at 12:08 AM, Mark Adams <mfadams at lbl.gov> wrote:
>>> > > >
>>> > > > [adding Garth]
>>> > > >
>>> > > > On Thu, Jun 23, 2016 at 12:52 AM, Barry Smith <bsmith at mcs.anl.gov>
>>> wrote:
>>> > > >
>>> > > > Mark,
>>> > > >
>>> > > > I think there is a misunderstanding here. With GASM an
>>> individual block problem is __solved__ (via a parallel KSP) in parallel by
>>> several processes, with ASM each block is "owned" by and solved on a single
>>> process.
>>> > > >
>>> > > > Ah, OK, so this is for multiple processors in a block. Yes, we are
>>> looking at small, smother, blocks.
>>> > > >
>>> > > >
>>> > > > With both the "block" can come from any unknowns on any
>>> processes. You can have, for example a block that comes from a region
>>> snaking across several processes if you like (or it makes sense due to
>>> coupling in the matrix).
>>> > > >
>>> > > > By default if you use ASM it will create one non-overlapping
>>> block defined by all unknowns owned by a single process and then extend it
>>> by "one level" (defined by the nonzero structure of the matrix) to get
>>> overlapping.
>>> > > >
>>> > > > The default in ASM is one level of overlap? That is new. (OK, I
>>> have not looked at ASM in like over 10 years)
>>> > > >
>>> > > > If you use multiple blocks per process it defines the
>>> non-overlapping blocks within a single process's unknowns
>>> > > >
>>> > > > I assume this still chops the matrix and does not call a
>>> partitioner.
>>> > > >
>>> > > > and extends each of them to have overlap (again by the non-zero
>>> structure of the matrix). The default is simple because the user only need
>>> indicate the number of blocks per process, the drawback is of course that
>>> it does depend on the process layout, number of processes etc and does not
>>> take into account particular "coupling information" that the user may know
>>> about with their problem.
>>> > > >
>>> > > > If the user wishes to defined the blocks themselves that is also
>>> possible with PCASMSetSubLocalSubdomains(). Each process provides 1 or more
>>> index sets for the subdomains it will solve on. Note that the index sets
>>> can contain any unknowns in the entire problem so the blocks do not have to
>>> "line up" with the parallel decomposition at all.
>>> > > >
>>> > > > Oh, OK, this is what I want. (I thought this worked).
>>> > > >
>>> > > > Of course determining and providing good such subdomains may not
>>> always be clear.
>>> > > >
>>> > > > In smoothed aggregation there is an argument that the aggregates
>>> are good, but the scale is fixed obviously. On a regular grid smoothed
>>> aggregation wants 3^D sized aggregates, which is obviously wonderful for
>>> AMS. And for anisotropy you want your ASM blocks to be on strongly
>>> connected components, which is what smoothed aggregation wants (not that I
>>> do this very well).
>>> > > >
>>> > > >
>>> > > > I see in GAMG you have PCGAMGSetUseASMAggs
>>> > > >
>>> > > > But the code calls PCGASMSetSubdomains and the command line is
>>> -pc_gamg_use_agg_gasm, so this is all messed up. (more below)
>>> > > >
>>> > > > which sadly does not have an explanation in the users manual and
>>> sadly does not have a matching options data base name
>>> -pc_gamg_use_agg_gasm following the rule of drop the word set, all lower
>>> case, and put _ between words the option should be -pc_gamg_use_asm_aggs.
>>> > > >
>>> > > > BUT, THIS IS THE WAY IT WAS! It looks like someone hijacked this
>>> code and made it gasm. I never did this.
>>> > > >
>>> > > > Barry: you did this apparently in 2013.
>>> > > >
>>> > > >
>>> > > > In addition to this one you could also have one that uses the
>>> aggs but use the PCASM to manage the solves instead of GASM, it would
>>> likely be less buggy and more efficient.
>>> > > >
>>> > > > yes
>>> > > >
>>> > > >
>>> > > > Please tell me exactly what example you tried to run with what
>>> options and I will debug it.
>>> > > >
>>> > > > We got an error message:
>>> > > >
>>> > > > ** Max-trans not allowed because matrix is distributed
>>> > > >
>>> > > > Garth: is this from your code perhaps? I don't see it in PETSc.
>>> > > >
>>> > > > Note that ALL functionality that is included in PETSc should have
>>> tests that test that functionality then we will find out immediately when
>>> it is broken instead of two years later when it is much harder to debug. If
>>> this -pc_gamg_use_agg_gasm had had a test we won't be in this mess now.
>>> (Jed's damn code reviews sure don't pick up this stuff).
>>> > > >
>>> > > > First we need to change gasm to asm.
>>> > > >
>>> > > > We could add this argument pc_gamg_use_agg_asm to ksp/ex56
>>> (runex56 or make a new test). The SNES version (also ex56) is my current
>>> test that I like to refer to as recommended parameters for elasticity. So
>>> I'd like to keep that clean, but we can add junk to ksp/ex56.
>>> > > >
>>> > > > I've done this in a branch mark/gamg-agg-asm. I get an error
>>> (appended). It looks like the second coarsest grid, which has 36 dof on one
>>> processor has an index 36 in the block on every processor. Strange. I can
>>> take a look at it later.
>>> > > >
>>> > > > Mark
>>> > > >
>>> > > > > [3]PETSC ERROR: [4]PETSC ERROR: --------------------- Error
>>> Message --------------------------------------------------------------
>>> > > > > [4]PETSC ERROR: Petsc has generated inconsistent data
>>> > > > > [4]PETSC ERROR: ith 0 block entry 36 not owned by any process,
>>> upper bound 36
>>> > > > > [4]PETSC ERROR: See
>>> http://www.mcs.anl.gov/petsc/documentation/faq.html for trouble
>>> shooting.
>>> > > > > [4]PETSC ERROR: Petsc Development GIT revision:
>>> v3.7.2-630-g96e0c40 GIT Date: 2016-06-22 10:03:02 -0500
>>> > > > > [4]PETSC ERROR: ./ex56 on a arch-macosx-gnu-g named
>>> MarksMac-3.local by markadams Thu Jun 23 06:53:27 2016
>>> > > > > [4]PETSC ERROR: Configure options COPTFLAGS="-g -O0"
>>> CXXOPTFLAGS="-g -O0" FOPTFLAGS="-g -O0" --download-hypre=1
>>> --download-parmetis=1 --download-metis=1 --download-ml=1 --download-p4est=1
>>> --download-exodus=1 --download-triangle=1
>>> --with-hdf5-dir=/Users/markadams/Codes/hdf5 --with-x=0 --with-debugging=1
>>> PETSC_ARCH=arch-macosx-gnu-g --download-chaco
>>> > > > > [4]PETSC ERROR: #1 VecScatterCreate_PtoS() line 2348 in
>>> /Users/markadams/Codes/petsc/src/vec/vec/utils/vpscat.c
>>> > > > > [4]PETSC ERROR: #2 VecScatterCreate() line 1552 in
>>> /Users/markadams/Codes/petsc/src/vec/vec/utils/vscat.c
>>> > > > > [4]PETSC ERROR: Petsc has generated inconsistent data
>>> > > > > [3]PETSC ERROR: ith 0 block entry 36 not owned by any process,
>>> upper bound 36
>>> > > > > [3]PETSC ERROR: See
>>> http://www.mcs.anl.gov/petsc/documentation/faq.html for trouble
>>> shooting.
>>> > > > > [3]PETSC ERROR: Petsc Development GIT revision:
>>> v3.7.2-630-g96e0c40 GIT Date: 2016-06-22 10:03:02 -0500
>>> > > > > [3]PETSC ERROR: ./ex56 on a arch-macosx-gnu-g named
>>> MarksMac-3.local by markadams Thu Jun 23 06:53:27 2016
>>> > > > > [3]PETSC ERROR: Configure options COPTFLAGS="-g -O0"
>>> CXXOPTFLAGS="-g -O0" FOPTFLAGS="-g -O0" --download-hypre=1
>>> --download-parmetis=1 --download-metis=1 --download-ml=1 --download-p4est=1
>>> --download-exodus=1 --download-triangle=1
>>> --with-hdf5-dir=/Users/markadams/Codes/hdf5 --with-x=0 --with-debugging=1
>>> PETSC_ARCH=arch-macosx-gnu-g --download-chaco
>>> > > > > [3]PETSC ERROR: #1 VecScatterCreate_PtoS() line 2348 in
>>> /Users/markadams/Codes/petsc/src/vec/vec/utils/vpscat.c
>>> > > > > [3]PETSC ERROR: #2 VecScatterCreate() line 1552 in
>>> /Users/markadams/Codes/petsc/src/vec/vec/utils/vscat.c
>>> > > > > [3]PETSC ERROR: #3 PCSetUp_ASM() line 279 in
>>> /Users/markadams/Codes/petsc/src/ksp/pc/impls/asm/asm.c
>>> > > >
>>> > > >
>>> > > >
>>> > > >
>>> > > >
>>> > > >
>>> > > >
>>> > > > Barry
>>> > > >
>>> > > >
>>> > > >
>>> > > >
>>> > > >
>>> > > >
>>> > > > > On Jun 22, 2016, at 5:20 PM, Mark Adams <mfadams at lbl.gov> wrote:
>>> > > > >
>>> > > > >
>>> > > > >
>>> > > > > On Wed, Jun 22, 2016 at 8:06 PM, Barry Smith <bsmith at mcs.anl.gov>
>>> wrote:
>>> > > > >
>>> > > > > I suggest focusing on asm.
>>> > > > >
>>> > > > > OK, I will switch gasm to asm, this does not work anyway.
>>> > > > >
>>> > > > > Having blocks that span multiple processes seems like over kill
>>> for a smoother ?
>>> > > > >
>>> > > > > No, because it is a pain to have the math convolved with the
>>> parallel decompositions strategy (ie, I can't tell an application how to
>>> partition their problem). If an aggregate spans processor boundaries, which
>>> is fine and needed, and let's say we have a pretty uniform problem, then if
>>> the block gets split up, H is small in part of the domain and convergence
>>> could suffer along processor boundaries. And having the math change as the
>>> parallel decomposition changes is annoying.
>>> > > > >
>>> > > > > (Major league overkill) in fact doesn't one want multiple blocks
>>> per process, ie. pretty small blocks.
>>> > > > >
>>> > > > > No, it is just doing what would be done in serial. If the cost
>>> of moving the data across the processor is a problem then that is a
>>> tradeoff to consider.
>>> > > > >
>>> > > > > And I think you are misunderstanding me. There are lots of
>>> blocks per process (the aggregates are say 3^D in size). And many of the
>>> aggregates/blocks along the processor boundary will be split between
>>> processors, resulting is mall blocks and weak ASM PC on processor
>>> boundaries.
>>> > > > >
>>> > > > > I can understand ASM not being general and not letting blocks
>>> span processor boundaries, but I don't think the extra matrix communication
>>> costs are a big deal (done just once) and the vector communication costs
>>> are not bad, it probably does not include (too many) new processors to
>>> communicate with.
>>> > > > >
>>> > > > >
>>> > > > > Barry
>>> > > > >
>>> > > > > > On Jun 22, 2016, at 7:51 AM, Mark Adams <mfadams at lbl.gov>
>>> wrote:
>>> > > > > >
>>> > > > > > I'm trying to get block smoothers to work for gamg. We
>>> (Garth) tried this and got this error:
>>> > > > > >
>>> > > > > >
>>> > > > > > - Another option is use '-pc_gamg_use_agg_gasm true' and use
>>> '-mg_levels_pc_type gasm'.
>>> > > > > >
>>> > > > > >
>>> > > > > > Running in parallel, I get
>>> > > > > >
>>> > > > > > ** Max-trans not allowed because matrix is distributed
>>> > > > > > ----
>>> > > > > >
>>> > > > > > First, what is the difference between asm and gasm?
>>> > > > > >
>>> > > > > > Second, I need to fix this to get block smoothers. This used
>>> to work. Did we lose the capability to have blocks that span processor
>>> subdomains?
>>> > > > > >
>>> > > > > > gamg only aggregates across processor subdomains within one
>>> layer, so maybe I could use one layer of overlap in some way?
>>> > > > > >
>>> > > > > > Thanks,
>>> > > > > > Mark
>>> > > > > >
>>> > > > >
>>> > > > >
>>> > > >
>>> > > >
>>> > >
>>> > >
>>> >
>>> >
>>>
>>>
>>>
>>> ------------------------------
>>>
>>> _______________________________________________
>>> petsc-dev mailing list
>>> petsc-dev at mcs.anl.gov
>>> https://lists.mcs.anl.gov/mailman/listinfo/petsc-dev
>>>
>>>
>>> End of petsc-dev Digest, Vol 90, Issue 30
>>> *****************************************
>>>
>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20160624/ff18ecc2/attachment.html>
More information about the petsc-dev
mailing list