Re: [petsc-dev] Faulty logic in MatHYPRESetPreallocation?

Stefeno, Doe this look right to you? Thanks Barry > On Dec 17, 2018, at 3:18 AM, Pierre Jolivet via petsc-dev > wrote: > > Hello, > I am not sure the hypre routines are called in the right order in > MatHYPRESetPreallocation. > Indeed, attached, you’ll find two Massif logs,

Re: [petsc-dev] Fwd: PETSc blame digest (next-tmp) 2018-12-24

--with-log=0 and you don't have code to manage this case. Take a look at the petsclog.h for #else after the defined(PETSC_USE_LOG) you need macros that return 0 for those two things. > On Dec 25, 2018, at 11:49 AM, Matthew Knepley via petsc-dev > wrote: > > This makes no sense, > > pets

Re: [petsc-dev] Faulty logic in MatHYPRESetPreallocation?

Pierre, Could you make a pull request on this? Thanks Barry > On Dec 17, 2018, at 3:18 AM, Pierre Jolivet via petsc-dev > wrote: > > Hello, > I am not sure the hypre routines are called in the right order in > MatHYPRESetPreallocation. > Indeed, attached, you’ll find two Ma

[petsc-dev] testing code which use partitioners

It really irks me that we can't use the various partitioners in our nightly tests because they use rand() and produce different results on different machines. Here is what I propose 1) add ./configure flag --with-petsc-rand 2) if the flag is set then provide our own rand() and srand()

[petsc-dev] git script for finding "outdated" branches in next

Jed gave me this git script to find branches in next that have not yet been merged to master alias gitmasternotupdated="comm -12 <(git branch -r --merged origin/next | grep origin/ | sort) <(git branch -r --no-merged origin/master ) | xargs -n1 git log -1 --format='%Cgreen%ci %C(yellow)%d%

Re: [petsc-dev] Segmentation faults in MatMatMult & MatTransposeMatMult

I concur that there should be a VecCreateWithArray() to automatically uses Seq vector for one process and MPI for multiple. Barry > On Jan 15, 2019, at 3:01 AM, Dave May via petsc-dev > wrote: > > > > On Tue, 15 Jan 2019 at 08:50, Pierre Jolivet > wrote: > OK, I was wrong about MA

Re: [petsc-dev] setting viewer format from options

> On Jan 16, 2019, at 6:47 AM, Hapla Vaclav via petsc-dev > wrote: > > I need to distinguish a PetscViewerFormat in DMLoad() and MatLoad(). Presumably this information would be stored in the *.info file associated with the datafile you are opening for reading. It makes no sense for it to

Re: [petsc-dev] setting viewer format from options

Barry > On Jan 17, 2019, at 4:49 AM, Hapla Vaclav wrote: > > > >> On 17 Jan 2019, at 00:47, Smith, Barry F. wrote: >> >> >> >>> On Jan 16, 2019, at 6:47 AM, Hapla Vaclav via petsc-dev >>> wrote: >>> >>> I n

Re: [petsc-dev] cray warning - reduction in alignment ignored

I cannot remember why it is sizeof(PetscScalar) specifically. I do remember that having an alignment is crucial to DMNetwork and it can fail and crash if there is no alignment. So it is possible that the code will not work with the Cray compilers. The attribute is checked in config/PET

Re: [petsc-dev] cray warning - reduction in alignment ignored

gt;-2. > Vertex 1: >-1. > Vertex 2: >3. > Vertex 3: >0. > > > /scratch/snx3000/haplav/petsc/src/snes/examples/tutorials/network/power>srun > ./power -snes_rtol 1.e-3 > nb = 9, ngen = 3, nload = 3, nbranch = 9 > Nonlinear solve converged due to

Re: [petsc-dev] Man pages usage of "Collective on XXX"

> On Feb 6, 2019, at 2:01 PM, Dave May via petsc-dev > wrote: > > * I notice that most man pages will say > Collective on > e.g. > https://www.mcs.anl.gov/petsc/petsc-current/docs/manualpages/DMDA/DMDACreate.html > > * Some others say > Collective on > > e.g. > https://www.mcs.anl.gov

Re: [petsc-dev] DMCreateMatrix_Shell

Hmm, why is this check wrong (though it may be incomplete)? Is there an example where it triggers an error when it shouldn't? It is my understanding that the check is there to make sure if the user requested a particular matrix type then it won't return a different type that is unexpected

Re: [petsc-dev] DMCreateMatrix_Shell

> On Feb 9, 2019, at 11:48 AM, Stefano Zampini > wrote: > > > >> On Feb 9, 2019, at 11:17 AM, Smith, Barry F. wrote: >> >> >> Hmm, why is this check wrong (though it may be incomplete)? Is there an >> example where it triggers an error when

Re: [petsc-dev] DMCreateMatrix_Shell

> On Feb 9, 2019, at 1:27 PM, Stefano Zampini wrote: > > > >> On Feb 9, 2019, at 10:19 PM, Smith, Barry F. wrote: >> >> >> >>> On Feb 9, 2019, at 11:48 AM, Stefano Zampini >>> wrote: >>> >>> >>> >&

Re: [petsc-dev] Errors in MatSetValuesBlockedLocal() when using AIJ, but not BAIJ!

> On Feb 20, 2019, at 12:50 PM, Mills, Richard Tran via petsc-dev > wrote: > > Folks, > > I'm working with some PFLOTRAN examples, and I've been scratching my head for > a while at errors that are being generated in MatSetValuesBlockedLocal(), > related to new nonzeros requiring a malloc.

Re: [petsc-dev] Errors in MatSetValuesBlockedLocal() when using AIJ, but not BAIJ!

> On Feb 21, 2019, at 8:28 PM, Mills, Richard Tran wrote: > > On 2/21/19 1:48 PM, Smith, Barry F. wrote: >> >>> On Feb 20, 2019, at 12:50 PM, Mills, Richard Tran via petsc-dev >>> >>> wrote: >>> >>> Folks, >>> >>

Re: [petsc-dev] KSPMonitor and petsc4py

Pierre, I can confirm the problem. Lisandro, Could you please take a look at this? I have no explanation for why this would happen. Barry > On Feb 25, 2019, at 1:21 PM, Pierre Jolivet via petsc-dev > wrote: > > I’m not sure this is the expected behavior. Is it? > $ gi

Re: [petsc-dev] Why do we use void* instead of PetscObject in PETSc?

There is a lot of merit for this alternative approach. This suggestion is also closely related to the (I think it's Toby's) proposal to replace the (function), ctx pairs that manage call backs in PETSc with objects. There will be a bit of an issue with dealing with the Fortran co

[petsc-dev] PETSc release by March 29, 2019

Due to ECP deliverables there will be a PETSc release by March 29, 2019. Please prepare materials you wish to get into the release soon and check on the progress of your current pull requests to make sure they do not block beyond the release deadline. Thanks Barry If someon

Re: [petsc-dev] KSPMonitor and petsc4py

umber(0) > A, P = get_op_pc(ksp, transpose=False) > pcg(ksp, A, P, b, x, *self.work) > > def solveTranspose(self, ksp, b, x): > LOG('ConjGrad.solveTranspose()') > +ksp.setIterationNumber(0) > A, P = get_op_pc(ksp, tran

Re: [petsc-dev] KSPMonitor and petsc4py

ed Brown wrote: > > I think Lisandro's point is that KSPSolve does not set ksp->its = 0. > That happens in each KSPSolve_XXX. The Python implementation of a KSP > forgot to do that, but perhaps it should happen in KSPSolve. > > "Smith, Barry F. via petsc-dev" w

Re: [petsc-dev] Why do we use void* instead of PetscObject in PETSc?

> On Mar 4, 2019, at 5:54 AM, Dave May wrote: > > Hi Barry, > > > On Mon, 4 Mar 2019 at 03:26, Smith, Barry F. wrote: > >There is a lot of merit for this alternative approach. > >This suggestion is also closely related to the (I think it's

Re: [petsc-dev] KSPMonitor and petsc4py

pcg(ksp, A, P, b, x, *self.work) > > def solveTranspose(self, ksp, b, x): > LOG('ConjGrad.solveTranspose()') > +ksp.setIterationNumber(0) > A, P = get_op_pc(ksp, transpose=True) > pcg(ksp, A, P, b, x, *self.work

Re: [petsc-dev] KSPMonitor and petsc4py

> On Mar 4, 2019, at 12:57 PM, Lisandro Dalcin wrote: > > > > On Mon, 4 Mar 2019 at 09:20, Smith, Barry F. wrote: > >By golly you are right, > >I don't know how we got to the model where each implementation > independently sets it to 0. Ins

Re: [petsc-dev] PETSc release by March 29, 2019

I may not have the time > to deal with anyway. > > Satish, does the above schedule work for you? Since you're creating the > tarballs, you've got the final word on this :-) > > Best regards, > Karli > > > > > On 3/4/19 4:31 AM, Smith, Barry F.

Re: [petsc-dev] Arm DDT feature questions

I don't know of such things. For TotalView there are routines such as #if defined(PETSC_USE_DEBUG) #include <../src/sys/totalview/tv_data_display.h> PETSC_UNUSED static int TV_display_type(const struct _p_Vec *v) { const PetscScalar *values; char type[32]; PetscErrorCode

Re: [petsc-dev] DMKSP and pcfieldsplit

Lawrence, Is this issue resolved or still stuck. I totally agree with you that Matt's change seems inane, how can one possibly just take the function/pointer that operates on the whole DM and assume it will work for a subDM? Anyways, unfortunately after Jed introduced the DMKSP p

Re: [petsc-dev] MATCOMPOSITE as fallback for matrix-matrix multiplication

Sounds like overkill on the complexity meter. Barry > On Mar 11, 2019, at 6:15 AM, Isaac, Tobin G via petsc-dev > wrote: > > One thought: we could extend MatReuse with MAT_INITIAL_MATRIX_GET_VALUES to > indicate that a matrix that implements MatGetValues() is desired, to allow > som

Re: [petsc-dev] MATCOMPOSITE as fallback for matrix-matrix multiplication

composite matrix unless you have a specific use case that would require MAT_INITIAL_MATRIX_GET_VALUES Barry > > On Mon, Mar 11, 2019 at 06:09:55PM +, Smith, Barry F. wrote: >> >> Sounds like overkill on the complexity meter. >> >> Barry >> >&g

Re: [petsc-dev] Getting Richardson output

Richardson has this "special case where it calls PCApplyRichardson() under certain circumstances (for efficiency) but KSPSolve_Richardson() has the check if (exists && maxit > 0 && richardsonP->scale == 1.0 && !ksp->numbermonitors && !ksp->transpose_solve && !nullsp) { so if monitoring i

[petsc-dev] Fwd: You're Invited: Aurora Announcement Ceremony and Reception

For those interested in the A21 ("first exascale machine") announcement time. Barry Begin forwarded message: From: Argonne Newsroom mailto:argonnenewsr...@anl.gov>> Subject: You're Invited: Aurora Announcement Ceremony and Reception Date: March 11, 2019 at 2:59:32 PM CDT To: mailto:bsm..

Re: [petsc-dev] Getting Richardson output

t 9:59 PM Smith, Barry F. wrote: > >Richardson has this "special case where it calls PCApplyRichardson() under > certain circumstances (for efficiency) but KSPSolve_Richardson() has the check > > if (exists && maxit > 0 && richardsonP->scale == 1.0

[petsc-dev] How long?

PETSc source code is becoming an unmaintainable, unextendable monstrosity. How long until Julia is mature enough that we can (re)implement PETSc in it? Barry

Re: [petsc-dev] How long?

scale machines support > Julia > when they are delivered? > > Todd. > >> On Mar 11, 2019, at 9:28 PM, Smith, Barry F. via petsc-dev >> wrote: >> >> >> PETSc source code is becoming an unmaintainable, unextendable monstrosity. >> Ho

Re: [petsc-dev] How long?

11, 2019, at 9:37 PM, Smith, Barry F. via petsc-dev > wrote: > > > There is no particular reason they shouldn't. > >In fact, we should ask for an uplift to prepare Julia for exascale if > someone hasn't already ;) > > Barry > >

Re: [petsc-dev] How long?

11, 2019, at 11:14 PM, Zhang, Hong wrote: > > Is linux kernel maintainable and extendable? Does anyone want to reimplement > linux in Julia? > > Hong (Mr.) > >> On Mar 11, 2019, at 9:28 PM, Smith, Barry F. via petsc-dev >> wrote: >> >> &

Re: [petsc-dev] How long?

aintainable and extendable? Does anyone want to reimplement >> linux in Julia? >> >> Hong (Mr.) >> >>> On Mar 11, 2019, at 9:28 PM, Smith, Barry F. via petsc-dev >>> wrote: >>> >>> >>> PETSc source code is becoming an unmaintainable, unextendable monstrosity. >>> How long until Julia is mature enough that we can (re)implement PETSc in it? >>> >>> Barry >>>

Re: [petsc-dev] Unwanted Fortran stub

It is because you have manual page documentation for it. The comment above it starts with /*@ if you don't want a manual page then remove the @ if you want a manual page but no stub then use /*@C Barry > On Mar 12, 2019, at 1:46 PM, Zhang, Junchao via petsc-dev > wrote: > > I declar

Re: [petsc-dev] Is there a good reason that BuildSystem's cuda.py requires GNU compilers?

Richard, You need to remove the isGNU() test and then experiment with getting the Nvidia tools to use the compiler you want it to use. No one has made a serious effort to use any other compilers but Gnu (at least not publicly). Barry > On Mar 12, 2019, at 10:40 PM, Mills, Ri

[petsc-dev] https://www.dursi.ca/post/hpc-is-dying-and-mpi-is-killing-it.html

I stubbled on this today; I should have seen it years ago. Barry

[petsc-dev] OpenMP for GPU course

I got this off an ECP mailing list. OpenMP Brookathon 2019 April 29 – May 2, 2019 URL: https://www.bnl.gov/ompbrookathon2019/ The Computational Science Initiative at Brookhaven National Laboratory (BNL) is organizing in conjunction with Oak Ridge National Laboratory (ORNL) and IBM, the "Op

Re: [petsc-dev] OpenMP for GPU course

oorly it would be good to have concrete evidence that it performs poorly. > > Matt > > "Smith, Barry F. via petsc-dev" writes: > > >I got this off an ECP mailing list. > > > > > > OpenMP Brookathon 2019 > > April 29 – May 2, 2019

Re: [petsc-dev] OpenMP for GPU course

> On Mar 19, 2019, at 12:17 PM, Jed Brown wrote: > > Matthew Knepley writes: > >> Are you saying that using OpenMP 4.5 "offload" is something you would do? > > For applications that make sense for GPUs, yes. Oh, so you mean for AI ;)

Re: [petsc-dev] OpenMP for GPU course

> On Mar 19, 2019, at 12:22 PM, Matthew Knepley wrote: > > On Tue, Mar 19, 2019 at 1:17 PM Jed Brown wrote: > Matthew Knepley writes: > > > Are you saying that using OpenMP 4.5 "offload" is something you would do? > > For applications that make sense for GPUs, yes. > > Would you say t

Re: [petsc-dev] https://www.dursi.ca/post/hpc-is-dying-and-mpi-is-killing-it.html

big machine-learning shops actually been moving > towards more use of MPI? Citation > > Yeah, MPI has plenty of warts. So does Fortran -- yet that hasn't killed > scientific computing. > > --Richard > > On 3/17/19 1:12 PM, Smith, Barry F. via petsc-dev wrote: >> I stubbled on this today; I should have seen it years ago. >> >> Barry >> >> >

[petsc-dev] PETSc 3.11 Release

We are pleased to announce the release of PETSc version 3.11 at http://www.mcs.anl.gov/petsc The major changes and updates can be found at http://www.mcs.anl.gov/petsc/documentation/changes/311.html We recommend upgrading to PETSc 3.11 soon. As always, please report problems to petsc-ma...@m

[petsc-dev] change in behavior of VecPointwiseDivide() ?

Please take a look at issue https://bitbucket.org/petsc/petsc/issues/270/vecpointwisedivide-problematic-for Thanks Barry

Re: [petsc-dev] git repo branches housekeeping

> On Apr 1, 2019, at 10:37 AM, Balay, Satish via petsc-dev > wrote: > > On Mon, 1 Apr 2019, Lisandro Dalcin wrote: > >> On Fri, 29 Mar 2019 at 19:22, Balay, Satish via petsc-dev < >> petsc-dev@mcs.anl.gov> wrote: >> >>> ref: https://lists.mcs.anl.gov/pipermail/petsc-dev/2018-April/022748.ht

Re: [petsc-dev] On remaining libMesh-PETsc fieldsplit interface cleanup

> On Apr 1, 2019, at 8:19 PM, Matthew Knepley via petsc-dev > wrote: > > On Mon, Apr 1, 2019 at 9:12 PM Boris Boutkov via petsc-dev > wrote: > Hello all, > > I've been working on the libMesh - PETSc interface for utilizing > gmg/fieldsplit on the command line by creating DMShells; things

Re: [petsc-dev] SNESSolve and changing dimensions

Pierre, You may be able to use SNESReset() instead of calling SNESDestroy() and creating a new SNES for each change in problem dimension; but you will still need to write an "outer loop" that calls SNESSolve() repeatedly and decides whether you should change the problem size. Note that yo

[petsc-dev] NVIDIA cuTENSOR library for accelerating tensor operations

Is this relevant for anything upcoming in PETSc? Barry From: Timothy Costa tco...@nvidia.com Date: April 02, 2019 Subject: Pre-Release: NVIDIA cuTENSOR library for accelerating tensor operations cuTENSOR is a new library containing highly optimized tensor primitives for NVIDIA GPUs. It

Re: [petsc-dev] Transpose and AXPY

Pierre, Go ahead and make a pull request. Please add a PetscInfo() line when it does the transposes that says something like "Explicitly transposing MATTRANSPOSEMAT matrix to perform MatAXPY()" Barry I don't like aesthetically the trick of calling PetscObjectQueryFunct

Re: [petsc-dev] Deprecation strategy for Enums

Junchao, Do you want to give this a go? Maybe it is a script in lib/petsc/bin/maint or a makefile rule that takes two git branch names and reports any changes between them (presumably by running ./configure && make twice to generate the libraries and making a copy of one branches incl

Re: [petsc-dev] New implementation of PtAP based on all-at-once algorithm

Excellent! Thanks Barry > On Apr 11, 2019, at 6:08 PM, Fande Kong via petsc-dev > wrote: > > Hi Developers, > > I just want to share a good news. It is known PETSc-ptap-scalable is taking > too much memory for some applications because it needs to build intermediate > data structur

Re: [petsc-dev] New implementation of PtAP based on all-at-once algorithm

> On Apr 11, 2019, at 9:07 PM, Mark Adams via petsc-dev > wrote: > > Interesting, nice work. > > It would be interesting to get the flop counters working. > > This looks like GMG, I assume 3D. > > The degree of parallelism is not very realistic. You should probably run a > 10x smaller pro

Re: [petsc-dev] Tons of errors with an unusual PETSc configuration

gt; On Apr 17, 2019, at 7:27 AM, Lisandro Dalcin wrote: > > > > On Wed, 17 Apr 2019 at 10:45, Smith, Barry F. wrote: > > I admit I don't understand why it is implemented this. That is why it isn't > turned on automatically in this situation; perhaps it breaks on

Re: [petsc-dev] MatComputeExplicitOperator

I think MPIAIJ was selected because it provided the most parallel functionality compared to MPIDENSE for which more operations were not written. This may not be relevant any more. Definitely the code needs to be fixed. Fixing MatConvert_Shell(); it should just assume the matrices

Re: [petsc-dev] MatComputeExplicitOperator

ey > ha scritto: > On Fri, Apr 19, 2019 at 5:58 PM Smith, Barry F. via petsc-dev > wrote: > > >I think MPIAIJ was selected because it provided the most parallel > functionality compared to MPIDENSE for which more operations were not written. >This may not be r

Re: [petsc-dev] concern about manpage example listings

Yeah this is done in lib/petsc/conf/rules # # Example usage for manual pages; adds each example that uses a function to that functions # manual page up to a limit of 10 examples. # manexamples: -@base=`basename ${LOCDIR}`; \ if [ "$${base}" = "tutorials" ] ; then \

Re: [petsc-dev] concern about manpage example listings

tered. In this case we could copy the tutorial to tests and keep only a > stripped-down, more didactic version in tutorials. Is this considered a right > way? > >> >> Out of curiosity, is there any non-historical argument to have this sort of >> logic in bash, as

Re: [petsc-dev] Something changed with SBAIJ on april 17?

Great, thanks Stefano for fixing them all > On Apr 23, 2019, at 12:40 AM, Éric Chamberland via petsc-dev > wrote: > > Hi Stefano, > > I confirm that your commit 0a16297aeba2de71 fixed all bugs we got since april > 17! > > Thanks a lot!!! :) > > Eric > > > > Le 19-04-22 à 22:42, Éric

[petsc-dev] alternatives to alt files

Scott and PETSc folks, Using alt files for testing is painful. Whenever you add, for example, a new variable to be output in a viewer it changes the output files and you need to regenerate the alt files for all the test configurations. Even though the run behavior of the code hasn't c

Re: [petsc-dev] PetscViewerASCIIPushSynchronized

Good question. I added the concept in 7b23a99a4cafc5f74ba930d377af92d6b7c0a4c1 and unfortunately didn't document why, nor could I find any mention of why in the mailing lists. The one thing I do remember is that there was a definite reason why it was needed (I just don't remember what). M

Re: [petsc-dev] PetscViewerASCIIPushSynchronized

nested manner (nor how to search for that ;)). After a few hours I'm becoming more convinced that the reason for the Allow/Push/Pop model is just to avoid the global synchronization. > > "Smith, Barry F. via petsc-dev" writes: > >> Good question. I added the c

Re: [petsc-dev] alternatives to alt files

Most packages that have good coverage with unit tests use a unit test system to manage the unit test code. I was actually surprised how many there are for C https://en.wikipedia.org/wiki/List_of_unit_testing_frameworks#C. But selecting evaluating and implementing a unit test environment

Re: [petsc-dev] PetscViewerASCIIPushSynchronized

remove the push/pop and only use the synch flush in the code when necessary. I'll give it a try. Barry > On May 2, 2019, at 11:08 PM, Jed Brown wrote: > > "Smith, Barry F." writes: > >>> On May 2, 2019, at 6:15 PM, Jed Brown wrote: >&

Re: [petsc-dev] alternatives to alt files

re the diff with the basic version against the stored diffs. > > Of course, petscdiff is in bash and we've talked about replacing > it with a python version. Matt has said he has a preliminary version > and I'd appreciate being able to use this as a starting point. > &

Re: [petsc-dev] alternatives to alt files

May 3, 2019, at 4:23 PM, Scott Kruger wrote: > > > > On 5/3/19 3:13 PM, Smith, Barry F. wrote: >>> On May 3, 2019, at 3:57 PM, Scott Kruger wrote: >>> >>> >>> >>> Sticking to the immediate issues and ignoring the other meta issues... >

Re: [petsc-dev] [petsc-maint] circular dependency [nightlybuilds did not catch]

> On May 3, 2019, at 5:00 PM, Hapla Vaclav wrote: > > > > OK, so index, idx, other idea? I'm not sure index is that informative (and not expansive enough). petscdm.h means nothing, maybe something short that doesn't mean anything? > > If we would have layout, is, sf, section in the sa

Re: [petsc-dev] [petsc-maint] circular dependency [nightlybuilds did not catch]

Ok > On May 4, 2019, at 12:45 AM, Václav Hapla wrote: > > > > 4. května 2019 1:08:09 GMT+03:00, "Smith, Barry F." > napsal: >> >> >>> On May 3, 2019, at 5:00 PM, Hapla Vaclav >> wrote: >>> >>> >>>

Re: [petsc-dev] [petsc-maint] circular dependency [nightlybuilds did not catch]

cture. > > Whereas e.g. Layout, SF, Section do not contain IS and also otherwise they > are basically unrelated except they all arrange some kind of index mapping. > And there are multiple utils ar different levels and nobody knows where to > put what. Plus all those hav

Re: [petsc-dev] [petsc-maint] circular dependency [nightlybuilds did not catch]

Note that if we accept an im level it won't affect the user API (except for those using multiple libraries who have to add a library), users shouldn't need to change anything including include files. im would just be there to clarify there is a layer completely below Vec (and completely abov

Re: [petsc-dev] [petsc-maint] circular dependency [nightlybuilds did not catch]

ple utils ar different levels and nobody knows where to > > put what. Plus all those have absolutely nothing in common with Vec. > > > > Vaclav > > > >> > >> "Smith, Barry F." writes: > >> > >>>

Re: [petsc-dev] PetscViewerASCIIPushSynchronized

do on this topic. > On May 3, 2019, at 4:36 PM, Hapla Vaclav wrote: > > > >> On 3 May 2019, at 17:34, Smith, Barry F. wrote: >> >> >> I think this thing maybe over-designed. When I wrote it I was obsessed with >> having a single Flush metho

[petsc-dev] Fwd: [ECP-PIs] Updates on the planned Aurora and Frontier exascale systems

ontier exascale systems Date: May 7, 2019 at 10:12:39 AM CDT To: "Smith, Barry F." mailto:bsm...@mcs.anl.gov>>, Ron Rahaman mailto:raha...@mcs.anl.gov>>, "Schanen, Michel" mailto:mscha...@anl.gov>>, "Zhang, Hong" mailto:hongzh...@anl.gov>>,

Re: [petsc-dev] do PETSC_VIEWER_{HDF5,BINARY}_ need to exist?

> On May 8, 2019, at 6:41 AM, Hapla Vaclav via petsc-dev > wrote: > > Hello > > I just encountered their manpages and it's a mess. I think in case of file > I/O, a user should be deliberate about filename and other settings. Sometimes > less is more and I think this is the case. Why anybod

[petsc-dev] Is bitbucket less responsive than it use to be?

Could be they're digging their own grave. I seem to be spending more time waiting after each click when previously I recall it was virtually instantaneous?

Re: [petsc-dev] Is bitbucket less responsive than it use to be?

> On May 14, 2019, at 9:06 PM, Jed Brown via petsc-dev > wrote: > > FWIW, mention of GitLab focuses on network effects, not the technical merits. > Network effects are real, though I think a monoculture is hazardous in the > long term. Monoculture is definitely hazardous to society over

[petsc-dev] Fwd: [DL-interest] The missing piece in deep learning?

Looks like that job is now done. Begin forwarded message: From: "Foster, Ian T. via DL-interest" mailto:dl-inter...@lists.cels.anl.gov>> Subject: [DL-interest] The missing piece in deep learning? Date: May 16, 2019 at 11:52:29 AM CDT To: "dl-inter...@lists.cels.anl.gov

Re: [petsc-dev] https://www.dursi.ca/post/hpc-is-dying-and-mpi-is-killing-it.html

- Torsten has a recent paper on demystifying ML with a graph based on >> published papers. Not the same, but interesting. >> >> On the health of HPC, sales figures are available (along with attendance at >> SC) and these show HPC is healthy if not growing at unsustaina

Re: [petsc-dev] https://www.dursi.ca/post/hpc-is-dying-and-mpi-is-killing-it.html

> On May 16, 2019, at 11:07 PM, Jed Brown wrote: > > "Smith, Barry F. via petsc-dev" writes: > >>> On May 16, 2019, at 6:16 PM, Mills, Richard Tran wrote: >>> >>> OK, so this thread is two months old but I saw some things recently that

Re: [petsc-dev] PETSc blame digest (next-tmp) 2019-05-20

Fixed. Ready to be merged back into next or next tmp > On May 20, 2019, at 3:28 PM, PETSc checkBuilds > wrote: > > > > Dear PETSc developer, > > This email contains listings of contributions attributed to you by > `git blame` that caused compiler errors or warnings in PETSc automated

Re: [petsc-dev] [petsc-checkbuilds] PETSc blame digest (next-tmp) 2019-05-20

I believe my fix includes fixing this. I added the ierr before the macro and CHKERRQ() after in the cdiagonal.c > On May 20, 2019, at 10:26 PM, Balay, Satish wrote: > > On Tue, 21 May 2019, Smith, Barry F. via petsc-checkbuilds wrote: > >> >> Fixed. Ready to be

[petsc-dev] (no subject)

Re: [petsc-dev] (no subject)

https://venturebeat.com/2019/05/20/microsoft-wants-to-apply-ai-to-the-entire-application-developer-lifecycle/ > On May 21, 2019, at 2:51 AM, Barry Smith wrote: >

Re: [petsc-dev] (no subject)

gt; On Tue, May 21, 2019 at 3:52 AM Smith, Barry F. via petsc-dev > wrote: > https://venturebeat.com/2019/05/20/microsoft-wants-to-apply-ai-to-the-entire-application-developer-lifecycle/ > > > > On May 21, 2019, at 2:51 AM, Barry Smith wrote: > > > > > >

Re: [petsc-dev] Cross-compiling/batch systems and getting rid of --know-sizeof- (or at least making it not required at all)

It would be fantastic if we could avoid the need for the known values and ideally the need for batch completely This is a great idea. > On May 22, 2019, at 5:02 AM, Lisandro Dalcin via petsc-dev > wrote: > > Barry/Satish, you know that making requests without patches is not my styl

Re: [petsc-dev] Cross-compiling/batch systems and getting rid of --know-sizeof- (or at least making it not required at all)

for running programs during ./configure (like hypre) and make xSDK builds on the DOE sites much less painful? Thanks everyone for these ideas! Barry > > [1] It's sometimes buggy. https://bugs.llvm.org/show_bug.cgi?id=41545 > > "Smith, Barry F. via petsc-dev"

Re: [petsc-dev] Bad use of defined(MPI_XXX)

MS-MPI has in their include file #define MPI_VERSION 2 #define MPI_SUBVERSION 0 Their last release was Oct 2018 https://docs.microsoft.com/en-us/message-passing-interface/microsoft-mpi-release-notes They also don't provide a mpi.mod file though they do provide mpif.h and Fortran stu

Re: [petsc-dev] PETSC_VIEWER_*_() vs PetscOptionsGetViewer()

I have concerns. Without the use of singletons -mat_view binary -vec_view binary will result in only the final object viewed being in the file binaryoutput? The idea behind the singletons is they provide continuity for the entire run. Note that currently when also creating and

Re: [petsc-dev] PETSC_VIEWER_*_() vs PetscOptionsGetViewer()

> On May 28, 2019, at 4:40 PM, Matthew Knepley wrote: > > On Tue, May 28, 2019 at 5:26 PM Smith, Barry F. via petsc-dev > wrote: > > I have concerns. > > Without the use of singletons > >-mat_view binary -vec_view binary > > will result i

Re: [petsc-dev] PETSC_VIEWER_*_() vs PetscOptionsGetViewer()

ent situation > On May 28, 2019, at 8:02 PM, Matthew Knepley wrote: > > On Tue, May 28, 2019 at 5:46 PM Smith, Barry F. wrote: > > > > On May 28, 2019, at 4:40 PM, Matthew Knepley wrote: > > > > On Tue, May 28, 2019 at 5:26 PM Smith, Ba

Re: [petsc-dev] Optional sowing?

When building PETSc from the tarball the fortran stubs and docs are prebuilt so sowing is not needed. If you configure without Fortran --with-fc=0 it should not get or compile sowing (plus he compile is faster because the Fortran modules) take a lot of time. Why don't you just turn off

Re: [petsc-dev] Is bitbucket less responsive than it use to be?

; >>> Any difficulty to switch over to GitHub? I like GitHub better than >>> bitbucket. >>> >>> Fande >>> >>> On Tue, May 14, 2019 at 9:41 AM Dave May via petsc-dev >>> wrote: >>> >>> >>> On Tue, 14 May 201

Re: [petsc-dev] PETSC_VIEWER_*_() vs PetscOptionsGetViewer()

ined for a different communicator than the one it was originally created for. Which may not be resolvable. > On May 29, 2019, at 6:11 AM, Hapla Vaclav wrote: > > > >> On 29 May 2019, at 01:00, Smith, Barry F. wrote: >> >> >> >&g

[petsc-dev] Bitbucket is doomed

I just got this same merged message sent to me three times. In recent days I've received several sent to me twice. It's not like we don't get enough email from Bitbucket already. Barry Begin forwarded message: From: Satish Balay mailto:pullrequests-re...@bitbucket.org>> Subject:

Re: [petsc-dev] SNESSetKSP and SNESDestroy

Yeah, this is a bug in the PETSc design. But I don't see any simple solution. Given the models of reset, SNESSetKSP() is dangerous because it only increases the reference count and has no control over the reset process. At times I've regretted SNESSetKSP() and been tempted to remove it.

Re: [petsc-dev] SNESSetKSP and SNESDestroy

> On May 30, 2019, at 2:15 PM, Pierre Jolivet > wrote: > >> >> On 30 May 2019, at 5:48 PM, Smith, Barry F. via petsc-dev >> wrote: >> >> >> Yeah, this is a bug in the PETSc design. But I don't see any simple >> solution. Given t

Re: [petsc-dev] Documenting types of examples

Cool stuff. This is kind of weird ex18.c single single single single I guess that example has no help string? > On May 31, 2019, at 8:35 AM, Patrick Sanan via petsc-dev > wrote: > > I guess right now it's just tags which can be of the form tag^sub-tag, and > you're only allowed

Re: [petsc-dev] Documenting types of examples

Fr., 31. Mai 2019 um 16:36 Uhr schrieb Smith, Barry F. > : > >Cool stuff. > >This is kind of weird > > ex18.c > single > single > single > single > >I guess that example has no help string? > > > On May 31, 2019, at 8:35 AM, Patric

<    1   2   3   4   5   6   7   8   >