[petsc-dev] PETSc 3.21 release

t Cowie Alex Lindsay Barry Smith Blanca Mellado Pinto David Andrs David Kamensky David Wells Fabien Evard Fande Kong Hansol Suh Hong Zhang Ilya Fursov James Wright Jed Brown Jeongu Kim Jeremy L Thompson Jeremy Theler Jose Roman Junchao Zhang Koki Sagiyama Lars Bilke Lisandro Dalcin Mark Adams

[petsc-dev] A context dependent PETSc tab completion would be enormously variable. Who remembers all the option and suboption names

‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍ ‍

[petsc-dev] Fwd: [petsc-maint] PETSc tutorial invite

> Begin forwarded message: > > From: Karthikeyan Chockalingam - STFC UKRI via petsc-maint > > Subject: [petsc-maint] PETSc tutorial invite > Date: February 14, 2024 at 5:35:44 AM EST > To: "petsc-ma...@mcs.anl.gov" > Cc: Alex Grant - STFC UKRI > Reply-To: Karthikeyan Chockalingam - STFC

[petsc-dev] Developer vote needed on a new naming convention https://gitlab.com/petsc/petsc/-/merge_requests/7206#note_1754514959

There is some disagreement on the introduction of a new naming convention in PETSc source code so I would like a quick voten at https://gitlab.com/petsc/petsc/-/merge_requests/7206#note_1754514959 Please vote there, not in email. Barry

Re: [petsc-dev] Having configure log what version of g++ the Intel compilers are utilizing?

ok, thanks > On Jan 9, 2024, at 12:16 PM, Pierre Jolivet wrote: > > > >> On 9 Jan 2024, at 6:08 PM, Barry Smith wrote: >> >> >>PETSc developers >> >>I cannot see in the configure.log information about what version of g++ >&

Re: [petsc-dev] correspondence between include file and library ?

To make this a bit more complicated, in Fortran when modules need to be used the ksp module will need to be used, not just the mat one. So some possible inconsistencies between the language usage. Barry > On Dec 21, 2023, at 10:28 PM, Barry Smith wrote: > > >

[petsc-dev] correspondence between include file and library ?

Certain Mat implementations (and associated utility user-level functions) need to go in the KSP library because they use KSP even though, from the user point of view, they only have a Mat-level API. Where should the information needed in the include files go? For MATLMVM they are mixed up

Re: [petsc-dev] Matshell with PETSs solvers using GPU

Are you thinking CUDA Fortran or some other "Fortran but running on the GPU"? > On Dec 12, 2023, at 8:11 PM, Jed Brown wrote: > > Han Tran writes: > >> Hi Jed, >> >> Thank you for your answer. I have not had a chance to work on this since I >> asked. I have some follow-up questions.

Re: [petsc-dev] PetscHMapI passing

What errors do you get? > I am trying to develop a function where the user can specify an empty > PetscHMapI variable and the function will retrieve the information attached > to the DMPlex. However, when I try something like ... > > PETSC_EXTERN PetscErrorCode DMPlexGetGeomInfo(DM dm,

Re: [petsc-dev] Petsc compilation issues with Xcode 15 on macOS Sonoma

Please send configure.log (best to petsc-ma...@mcs.anl.gov). > On Nov 13, 2023, at 11:41 AM, Abhinav Singh wrote: > > Dear Petsc devs, > > I have been having issues lately when compiling petsc on MacOS with various > libraries. This is probably due to the updated linker in MacOS and >

[petsc-dev] Fwd: Request for Information: TAO: Toolkit for Advanced Optimization and PETSc

I suspect we are going to receive more of these requests as apparently all US agencies now need to do this assessment on all software that they use. We should try to be pro-active. Are there currently any web-based testing systems that run on PETSc or could run on PETSc ? We should

[petsc-dev] Spring 2024 PETSc meeting and release announcement 3.20

Hamilton Albert Cowie Barry Smith Blaise Bourdin Connor Ward David Andrs David Wells Duncan Campbell Hansol Suh Hong Zhang Jacob Faibussowitsch James Wright Jed Brown jeremy theler Joseph Pusztay Jose Roman Junchao Zhang Lisandro Dalcin Mark Adams Matthew Knepley Mr. Hong Zhang

Re: [petsc-dev] EXTERNAL: Re: PETSc optimization

https://gitlab.com/petsc/petsc/-/merge_requests/6805 Add hints to discussion of Spack installs for optimization to docs. (!6805) · Merge requests · PETSc / petsc · GitLab gitlab.com > On Aug 8, 2023, at 4:55 PM, Liu Wei AWE via petsc-dev > wrote: > >> I see 'spack install cflags=-O3' is

Re: [petsc-dev] [petsc-users] CUDA error trying to run a job with two mpi processes and 1 GPU

Should a default build of PETSc configure both with and without debugging and compile both sets of libraries? Increases the initial build time for people but simplifies life. > On Aug 11, 2023, at 10:52 AM, Junchao Zhang wrote: > > Hi, Marcos, > Could you build petsc in debug mode

Re: [petsc-dev] EXTERNAL: Re: PETSc optimization

This is a good idea. We can put a couple of specific examples of spack commands for PETSc builds in our instructions. Thanks Barry > On Aug 8, 2023, at 4:55 PM, Liu Wei AWE via petsc-dev > wrote: > >> I see 'spack install cflags=-O3' is working - but not spack install >>

Re: [petsc-dev] PETSc optimization

The space of "best" choices for optimization flags for PETSc is huge; each OS, each compiler, and each particular piece of hardware may have different "best" choices, in addition, the previous choice may not even allow compiling with any small change in any of these things. Finally

[petsc-dev] Fwd: NumFOCUS Project Summit - Call for Attendees

Begin forwarded message:From: Arliss Collins Subject: Fwd: NumFOCUS Project Summit - Call for AttendeesDate: August 3, 2023 at 3:34:00 PM EDTTo: Barry Smith Message-Id: Hello Barry,I hope you are well.I'm reaching out to share our invite to the NumFOCUS 2023 Project Summit.  We would love to have

Re: [petsc-dev] [petsc-users] compiler related error (configuring Petsc)

Only four more years of this nonsense! One of the (now ancient) selling points of Unix was that it could be more nimble and evolve more rapidly than IBM's mainframe operating systems. Jacob, Can't we have configure tell users explicitly the situation when they encounter this case

Re: [petsc-dev] fixing bugs in resolution of TSEvent's

We are aware of "issues" with TSEvent and appreciate you working on it. Another user reported problems last week https://gitlab.com/petsc/petsc/-/issues/1414 which we resolved in an associated MR, you might want to check those changes to see how/if they would interact with your MR. As

Re: [petsc-dev] petsc4py doc problem

On Wed, 28 Jun 2023 at 08:09, Barry Smith <mailto:bsm...@petsc.dev>> wrote: >> >> Generally, I like Python a great deal and think Python developers make >> good decisions, but their love of the 80-character limit is absurdly out of >> character and so fundamenta

Re: [petsc-dev] petsc4py doc problem

Generally, I like Python a great deal and think Python developers make good decisions, but their love of the 80-character limit is absurdly out of character and so fundamentally wrong. > On Jun 28, 2023, at 1:03 AM, Satish Balay via petsc-dev > wrote: > > >

Re: [petsc-dev] make checkclangformat checkbadSource dependencies

Urgg, precommit does not appear to play well with git gui. I am getting git gui hanging on call pre-commit hook > On Jun 19, 2023, at 9:17 AM, Barry Smith wrote: > > > I just found out my script was woefully incomplete. It is probably still > wrong even with this c

Re: [petsc-dev] Inquiry about a change in petsc version 3.19.1

ion 3.19.0 does it mean that the bt line search won't > function properly? > > Thank you. > Best, > Nabil > From: Barry Smith mailto:bsm...@petsc.dev>> > Sent: Tuesday, June 20, 2023 12:55 PM > To: Nabil Abboud mailto:nabil.abb...@ansys.com>> > Cc: petsc-dev@mcs.

Re: [petsc-dev] Inquiry about a change in petsc version 3.19.1

Looks like a fatally flawed change I should never have made. I have an MR to revert it https://gitlab.com/petsc/petsc/-/merge_requests/6620 Should get into release and main by tommorow. Barry > On Jun 19, 2023, at 4:37 PM, Barry Smith wrote: > > > Sorry about this, we'll

Re: [petsc-dev] Inquiry about a change in petsc version 3.19.1

Sorry about this, we'll take a look and get back to you. > On Jun 19, 2023, at 4:05 PM, Nabil Abboud via petsc-dev > wrote: > > Dear all, > > We were trying to update the petsc version we use in our code to the version > 3.19.1 when we noticed that some of the unit tests in our code

Re: [petsc-dev] make checkclangformat checkbadSource dependencies

I just found out my script was woefully incomplete. It is probably still wrong even with this change but needs current_source=$(git diff --staged --name-only | egrep "(\.[chF]'|\.F90|\.hpp|\.cpp|\.cxx|\.cu)" | tr '\n' ' ') > On Jun 18, 2023, at 7:51 PM, Barry

Re: [petsc-dev] make checkclangformat checkbadSource dependencies

-diff > (https://clang.llvm.org/docs/ClangFormat.html#script-for-patch-reformatting). > > I floated the idea of adding git hooks ages ago, but it was shot down for > some reason. > > Best regards, > > Jacob Faibussowitsch > (Jacob Fai - booss - oh - vitch) > >>

[petsc-dev] make checkclangformat checkbadSource dependencies

I have never understood how to do make rule dependencies when one is not explicitly generating new files from old ones. For example, .o from .c I want to automatically run make checkclangformat checkbadSource before every git push (because I am an idiot and have too many silly failed CIs

Re: [petsc-dev] building sphinx doc only

Takes 10 minutes on my Apple M2 laptop. As Satish notes, it has several stages, each of which takes some nontrivial time. Hence, it is unclear if any simple change to the process could reduce the time significantly, but I think 30 minutes in the CI is too long, and it would be nice if

Re: [petsc-dev] GCov CI problem

Strange this never bit before, you could put in requires: for this example no gcov > On Jun 14, 2023, at 2:37 PM, Satish Balay via petsc-dev > wrote: > > not ok vec_pf_impls_string_tests-ex1_1 # Error code: 65 > # [0]PETSC ERROR: - Error Message >

Re: [petsc-dev] How to add strangers as MR reviewers?

Jed Brown wrote: > > Probably adding them as guests (or developers) would be the way to go. My > guess is it's to cut down on accidental assignments, but these policies > always have side-effects. > > Barry Smith writes: > >> Is there a way to add people not in so

[petsc-dev] How to add strangers as MR reviewers?

Is there a way to add people not in some magic inner circle as an MR reviewer? For example, I try to add James Wright (@jrwrigh ) with @jrwrigh or jrwrigh as an assignee or reviewer to my MR, and it cannot find them. But on the other hand, if THEY started an MR in a fork then I can add

Re: [petsc-dev] Latest Pull breaks the 'test' target

AM, Barry Smith wrote: > > > Ahh, are you using the default make that comes from Apple or do you use a > modern gnumake (such as from brew?) > > I get Jed's results with the brew one (installed as gmake) and your results > with the Apple one /usr/bin/make > > >

Re: [petsc-dev] Latest Pull breaks the 'test' target

; CC arch-master-debug/tests/snes/tutorials/ex5.o >> CLINKER arch-master-debug/tests/snes/tutorials/ex5 >>TEST arch-master-debug/tests/counts/snes_tutorials-ex5_1.counts >> ok snes_tutorials-ex5_1 >> ok diff-snes_tutorials-ex5_1 >> >> Tha

Re: [petsc-dev] Latest Pull breaks the 'test' target

Sure, I do also with make all; make test s="something" I have no idea how gmakefile.test dependencies work, you'll need to get Jed to fix the problem. > On May 23, 2023, at 10:22 AM, Matthew Knepley wrote: > > On Tue, May 23, 2023 at 10:22 AM Barry Smith <m

Re: [petsc-dev] Latest Pull breaks the 'test' target

I never knew there was such a dependency; I always ran make all ; make tests The gnumake stuff is still confusing to me so I have no idea how it works or why. > On May 23, 2023, at 9:34 AM, Matthew Knepley wrote: > > The 'test' target no longer depends on 'libs' somehow so when I change

Re: [petsc-dev] PetscOptionsXXX, PetscOptionsGetXX, and PetscBag in Fortran

Using block might be possible, but I would say is likely overkill; better just to skip the "local scope" that the C versions of the routines have. No one ever used the GUI interface, so that code is all unnecessary plus a Fortran programmer would never use a GUI anyways :-)

Re: [petsc-dev] So CFLAGS no longer works!!!! Major crisis

ab.com/petsc/petsc/-/merge_requests/6382 > > Satish > > On Wed, 26 Apr 2023, Satish Balay via petsc-dev wrote: > >> On Wed, 26 Apr 2023, Barry Smith wrote: >> >>> >>> >>> Urg, so user makefiles that worked for 25+ years suddenly don't

Re: [petsc-dev] So CFLAGS no longer works!!!! Major crisis

bug lurking here.. > > -PETSC_CCOMPILE_SINGLE = ${CC} -o $*.o -c ${CC_FLAGS} ${FLAGS} ${CPPFLAGS} > +PETSC_CCOMPILE_SINGLE = ${CC} -o $*.o -c ${CC_FLAGS} ${CFLAGS} ${CPPFLAGS} > > Satish > > On Wed, 26 Apr 2023, Barry Smith wrote: > >> >> $ make ex1 >&

[petsc-dev] So CFLAGS no longer works!!!! Major crisis

$ make ex1 mpicc -Wl,-bind_at_load -Wl,-multiply_defined,suppress -Wl,-multiply_defined -Wl,suppress -Wl,-commons,use_dylibs -Wl,-search_paths_first -Wl,-no_compact_unwind -Wall -Wwrite-strings -Wno-unknown-pragmas -Wno-lto-type-mismatch -Wno-stringop-overflow -fvisibility=hidden -g3 -O0

[petsc-dev] Fwd: Thank you for filling out Project Application to Join NumFOCUS

ap/ > > URL to “how to get started as a contributor” documentation: > https://petsc.org/release/developers/contributing/ > > The names and email addresses of five people willing to act as signatories > for your project: > bsm...@petsc.dev, j...@jedbrown.org, > knep...@gmail.com,ste

[petsc-dev] The PETSc code of conduct does not appear on the PETSc website

Because it is just a .md file at the top of the PETSc directory structure.

Re: [petsc-dev] Matrix Manipulation Question

There is a bug in the design of MATLRC, it should have a MatLRCSetMats() that takes Mat U, Vec c, Mat V. Then the convenience constructor MatCreateLRC() would call this method so no code duplication. Your code would then properly be TSComputeIJacobian(ts, ..., A0, B, ...) >

[petsc-dev] manual page organization wrt all those things

So https://petsc.org/release/manualpages/SPACE/ and https://petsc.org/release/manualpages/DUALSPACE/ have their own manual page sections but the Petsc[Dual]Space type definitions and function prototypes are in petscfe.h so the type manual pages (e.g. PetscSpace) appear in

[petsc-dev] numFocus membership and needed new webpages

https://gitlab.com/petsc/petsc/-/merge_requests/6291 Write a PETSc roadmap and governance document; this is required by NumFocus membership (!6291) · Merge requests · PETSc / petsc · GitLab gitlab.com

[petsc-dev] PETSc release announcement and reminder to register for the PETSc annual meeting

/community/meetings/2023/#meeting We recommend upgrading to PETSc 3.19.0 soon. As always, please report problems to petsc-ma...@mcs.anl.gov and ask questions at petsc-us...@mcs.anl.gov This release includes contributions from Aidan Hamilton Alp Dener Ashish Patel Barry Smith Blaise Bourdin danofinn

[petsc-dev] I will be converting .rst files to .md; let me know if you have any outstanding MR with changes

I will be converting .rst files to .md; please let me know if you have any outstanding MR with changes so there are no conflicts. Barry

Re: [petsc-dev] Request to add a PETSc-MUMPS API for null pivot rows

Indeed yes. On the GitLab page for your fork there should be a button or something at the top to Submit a Merge Request. We have instructions for submitting MR at https://petsc.org/main/developers/integration/. Barry > On Mar 23, 2023, at 5:30 PM, Ashish Patel wrote: > > Dear Petsc

Re: [petsc-dev] SNESNEWTONLS

The newton step being taken in the slide I sent is 2.7e10. > > Thank you. > > -Justin > > From: Barry Smith mailto:bsm...@petsc.dev>> > Date: Tuesday, March 7, 2023 at 9:34 AM > To: "Angus, Justin Ray" mailto:ang...@llnl.gov>> > Cc: Matthew Kne

Re: [petsc-dev] SNESNEWTONLS

code-users Barry > > -Justin > > From: Matthew Knepley mailto:knep...@gmail.com>> > Date: Tuesday, March 7, 2023 at 9:16 AM > To: "Angus, Justin Ray" mailto:ang...@llnl.gov>> > Cc: Barry Smith mailto:bsm...@petsc.dev>>, > "petsc-dev@mcs.a

Re: [petsc-dev] SNESNEWTONLS

> On Mar 7, 2023, at 11:36 AM, Angus, Justin Ray via petsc-dev > wrote: > > Hello, > > I’ve been using the default newton line search nonlinear solver in petsc. I > recently discovered that the default line search method is bt – backtracking. > I have two questions. > > How exactly does

[petsc-dev] How come petsc4py objects do not handle attributes in the "standard" way?

How come petsc4py has the (nonstandard?) v.setAttr('name',value) and v.getAttr('name') instead of v.name notation? Could they be refactored to have "normal" attribute behavior? If not, could a v.hasAttr('name') be added? Similarly, how come numpy arrays seem to have no way to set

[petsc-dev] gcov tests on my machine before CI

Jacob, When I am adding code it makes sense that the new code I just added is tested, at least to some degree, on my machine before I create an MR. This means that my running appropriate gcov on just my local machine should provide enough information to indicate that my new code is NOT

Re: [petsc-dev] Putting more menu items at the top of petsc.org pages (how to?)

>> can create our own fork for this theme and customize it. >> >> Hong (Mr.) >> >>> On Feb 19, 2023, at 6:01 PM, Barry Smith wrote: >>> >>> >>> Googling "magic words sphinx menu" didn't help me so I ask here. Is there >>>

[petsc-dev] Putting more menu items at the top of petsc.org pages (how to?)

Googling "magic words sphinx menu" didn't help me so I ask here. Is there a way to have more menu items at the top of the petsc.org pages instead of immediately going to More? I think I saw a way before but cannot find the magic words. 

[petsc-dev] Rig the search icon in petsc.org to also search the PETSc users archives (and other stuff?)

Can we rig the search icon in petsc.org to also search the PETSc archives? This way we can recommend users search in petsc.org instead of using the google and getting outdated information.

[petsc-dev] Now put PETSc docs updates into main branch

Until the next PETSc release please put documentation updates in the main PETSc branch (instead of the standard release). This is to allow some refactoring of the documentation and the use of Jacob's very cool lint for manual pages to dramatically improve the manual pages. Barry

Re: [petsc-dev] PETSC_VIEWER_FAILED

It is not possible because KSPConvergedReasonViewFromOptions() gets its format directly from the command line each time it is called and KSPConvergedReasonViewFromOptions() is called (wildly incorrectly; no function that processes the options database should be called from compute code)

Re: [petsc-dev] xlocal = da.getLocalVec() .. da.restoreLocalVec(xlocal) skip the restore

Jed, Thanks for the pointer, I got it working. > On Feb 2, 2023, at 1:11 PM, Jed Brown wrote: > > Barry Smith writes: > >>> On Feb 1, 2023, at 9:17 PM, Matthew Knepley wrote: >>> >>> On Wed, Feb 1, 2023 at 9:06 PM Barry Smith >> <

Re: [petsc-dev] xlocal = da.getLocalVec() .. da.restoreLocalVec(xlocal) skip the restore

> On Feb 1, 2023, at 9:17 PM, Matthew Knepley wrote: > > On Wed, Feb 1, 2023 at 9:06 PM Barry Smith <mailto:bsm...@petsc.dev>> wrote: >> >> Hmm, When I do >> >>def somePythonfunction(): >>... >>x = da.createLo

Re: [petsc-dev] xlocal = da.getLocalVec() .. da.restoreLocalVec(xlocal) skip the restore

() instead of x.destroy(). Note specifically parallelism doesn't play a role here because x is local. Barry > On Feb 1, 2023, at 8:07 PM, Matthew Knepley wrote: > > On Wed, Feb 1, 2023 at 6:33 PM Barry Smith <mailto:bsm...@petsc.dev>> wrote: >> >> Would it be

[petsc-dev] xlocal = da.getLocalVec() .. da.restoreLocalVec(xlocal) skip the restore

Would it be possible to rig the xlocal obtained from self.da.getLocalVec() to automatically trigger the da.restoreLocalVec() when the xlocal goes out of scope so that the user does not need to explicitly make the call. If so, how should I go about implementing it? Barry

Re: [petsc-dev] PetscOptionsGetViewer() problems with multiple usage on the same object but different options databases

tch) > >> On Jan 22, 2023, at 20:12, Barry Smith wrote: >> >> >> One can turn on a multitude of viewers with ad hoc names at the same time >> like -ksp_view_solution. >> >> My eventual hope is to consolidate them with an additional part of the

Re: [petsc-dev] PetscOptionsGetViewer() problems with multiple usage on the same object but different options databases

> viewer type that does nothing. I don't like the out-of-band -xxx_view_cancel. > > Barry Smith writes: > >> ALL the other options are sticky. Calling setFromOptions() twice does not >> change the value of rtol etc etc etc that was set the last time and eve

Re: [petsc-dev] PetscOptionsGetViewer() problems with multiple usage on the same object but different options databases

n 22, 2023 at 1:06 PM Barry Smith wrote: >> >>> >>> That makes incrementally adding new options to an existing object >>> difficult, since each call to setFromOptions() screws up previous calls. >>> >>> We already have >>> >>&g

Re: [petsc-dev] PetscOptionsGetViewer() problems with multiple usage on the same object but different options databases

t, Jan 21, 2023 at 4:34 PM Barry Smith <mailto:bsm...@petsc.dev>> wrote: >> >> If I run KSPSetFromOptions() on an options database that contains >> -ksp_view and then push another options database that does not contain >> -ksp_view and call KSPSetFromOpti

[petsc-dev] PetscOptionsGetViewer() problems with multiple usage on the same object but different options databases

If I run KSPSetFromOptions() on an options database that contains -ksp_view and then push another options database that does not contain -ksp_view and call KSPSetFromOptions() again it undoes the previous setting of that viewer. So -ksp_view is not used. I think this is the wrong model,

Re: [petsc-dev] bad cpu/MPI performance problem

; > > I cannot speculate on how it got into this state (since my last conclusion > was so wrong :-)). > > Mark, > > What happens if you run the same problem (same number ranks etc etc) but do > not use -dm_refine_hierarchy 6 (so the coarse DM is the only dm).

Re: [petsc-dev] bad cpu/MPI performance problem

s wrote: > > OK, here is a timeout one with 4K processors. > > On Mon, Jan 9, 2023 at 3:13 PM Barry Smith <mailto:bsm...@petsc.dev>> wrote: >> >> >>> On Jan 9, 2023, at 12:13 PM, Mark Adams >> <mailto:mfad...@lbl.gov>> wrote: &

Re: [petsc-dev] bad cpu/MPI performance problem

solver, the vec norms, on 128 nodes (and 64). > > Thanks, > Mark > > > On Sun, Jan 8, 2023 at 8:07 PM Barry Smith <mailto:bsm...@petsc.dev>> wrote: >> >> Rather cryptic use of that integer variable for anyone who did not write >> the code, but

Re: [petsc-dev] bad cpu/MPI performance problem

being called on some ranks. Barry >>>>> DMLabelGather > On Jan 8, 2023, at 4:32 PM, Mark Adams wrote: > > > On Sun, Jan 8, 2023 at 4:13 PM Barry Smith <mailto:bsm...@petsc.dev>> wrote: >> >>There is a bug in the routine DMPlexLabelCom

Re: [petsc-dev] bad cpu/MPI performance problem

problem but this doesn't change the fact that the current code is buggy and needs to be fixed before blaming some other bug for the problem. > On Jan 8, 2023, at 4:04 PM, Mark Adams wrote: > > > > On Sun, Jan 8, 2023 at 2:44 PM Matthew Knepley <mailto:knep...@gmail.com>&

Re: [petsc-dev] bad cpu/MPI performance problem

> On Jan 8, 2023, at 2:44 PM, Matthew Knepley wrote: > > On Sun, Jan 8, 2023 at 9:28 AM Barry Smith <mailto:bsm...@petsc.dev>> wrote: >> >> Mark, >> >> Looks like the error checking in PetscCommDuplicate() is doing its job. It >>

Re: [petsc-dev] bad cpu/MPI performance problem

Mark, Looks like the error checking in PetscCommDuplicate() is doing its job. It is reporting an attempt to use an PETSc object constructer on a subset of ranks of an MPI_Comm (which is, of course, fundamentally impossible in the PETSc/MPI model) Note that nroots can be negative on a

[petsc-dev] https://petsc.org/release/docs/manualpages/PC/PCFIELDSPLIT/ is a mess!

The formatting of https://petsc.org/release/docs/manualpages/PC/PCFIELDSPLIT/ is a mess. I am not sure why or how to debug it in a non-time wasting way. Is there anything obviously wrong with it? Any thoughts?

Re: [petsc-dev] Potential memory leak in PETSc - hypre interface when using Euclid

My quick examination of hypre.c shows the only relevant code in PETSc is PetscCall(PetscOptionsEList("-pc_hypre_boomeramg_smooth_type", "Enable more complex smoothers", "None", HYPREBoomerAMGSmoothType, PETSC_STATIC_ARRAY_LENGTH(HYPREBoomerAMGSmoothType), HYPREBoomerAMGSmoothType[0], ,

Re: [petsc-dev] petsc4py, numpy's BLAS and PETSc's BLAS

dom/mtrand.cpython-311-x86_64-linux-gnu.so > $ locate numpy |grep \.so$ |grep python3.11 |xargs ldd |grep = | cut -d = -f > 2 | cut -d " " -f 2 | sort | uniq > /lib64/libc.so.6 > /lib64/libflexiblas.so.3 > /lib64/libgcc_s.so.1 > /lib64/libgfortran.so.5 > /lib64/libm

Re: [petsc-dev] Manualpage TOC

an easily parse by Petsc object type of functionality > > > Regards, > Blaise > >> On Oct 10, 2022, at 11:56 AM, Barry Smith > <mailto:bsm...@petsc.dev>> wrote: >> >> >> Oh yes, thanks. Maybe the material at the bottom could be reordered and

[petsc-dev] petsc4py, numpy's BLAS and PETSc's BLAS

When PETSc is built with petsc4py this brings along, in some way, the BLAS/LAPACK that numpy is using. Yet PETSc is free to bring in its own BLAS/LAPACK libraries. To be completely proper should we be having configure (when used with petsc4py) determine the BLAS/LAPACK that numpy is

Re: [petsc-dev] Manualpage TOC

removed. I assumed it wasn't easy to migrate that to rst format. > > prev: > https://petsc.gitlab.io/-/petsc/-/jobs/3147219016/artifacts/public/html/docs/manualpages/index.html > current: https://petsc.org/release/docs/manualpages/ > > Satish > > > On Mon, 10 Oct 2022, Bar

Re: [petsc-dev] Manualpage TOC

What is worse about it? What did it look like before? How would you like it to look? The left hand side on this page is broken and I do not know how to fix it. But the middle panel can be changed to whatever is better > On Oct 10, 2022, at 8:47 AM, Matthew Knepley wrote: > > The new

[petsc-dev] PETSc 2023 User Meeting and New Release 3.18

ludes contributions from AdelekeBankole Aidan Hamilton Albert Cowie Alexis Marboeuf Barry Smith Blaise Bourdin Dave May David Andrs David Wells Fande Kong ftrigaux Getnet Betrie Hong Zhang Jacob Faibussowitsch James Wright JDBetteridge Jed Brown Jeremy L Thompson Joe Wallwork Jose Roman Junchao Zh

Re: [petsc-dev] Python garbage collector broken?

Posted to https://gitlab.com/petsc/petsc/-/merge_requests/4619#note_1122550807 > On Oct 3, 2022, at 11:13 AM, Stefano Zampini > wrote: > > Just reconfigured today with release and got this > > [szampini@localhost

[petsc-dev] final decision on 2023 User group meeting and location

PETSc folks, We are close to finalizing the time of the PETSc 2023 User Meeting as June 5-7 at IIT in Chicago. If you have serious concerns about the timing (or location) please let us know immediately so we can rethink the plans. Thanks Barry

Re: [petsc-dev] do all MIS algorithms require a symmetric structure?

Right, but I want to run with the old options MIS (instead of MIS-2) and get the same times as before. But instead I am getting much larger times. > On Sep 18, 2022, at 6:58 PM, Mark Adams wrote: > > > > On Sun, Sep 18, 2022 at 6:19 PM Barry Smith <mailto:bsm...

Re: [petsc-dev] do all MIS algorithms require a symmetric structure?

default options. > On Sep 18, 2022, at 4:21 PM, Mark Adams wrote: > > > > On Sun, Sep 18, 2022 at 4:02 PM Barry Smith <mailto:bsm...@petsc.dev>> wrote: > > Mark, > >Do all MIS algorithms in PETSc require a symmetric graph structure? And > par

Re: [petsc-dev] do all MIS algorithms require a symmetric structure?

. Is there a parallel coarse grid point selector that would be faster and not have the parallel bottle necks that could be coded up relatively easily? Barry > On Sep 18, 2022, at 4:21 PM, Mark Adams wrote: > > > > On Sun, Sep 18, 2022 at 4:02 PM Barry Smith <mailto:bsm...

[petsc-dev] do all MIS algorithms require a symmetric structure?

Mark, Do all MIS algorithms in PETSc require a symmetric graph structure? And parallel ones can hang if not structurally symmetric? When used sequentially I guess it never hangs but it may not produce a "correct" MIS if the matrix structure is not symmetric? But like the MIS is

Re: [petsc-dev] large cost of symmetrizing for GAMG?

Keyes had a PD > doing this in 2004). > And, this would be a way to get someone rewarded/motivated as it is easy to > publish anything with ML. > > On Sun, Sep 18, 2022 at 11:12 AM Barry Smith <mailto:bsm...@petsc.dev>> wrote: > > I think it should default

Re: [petsc-dev] large cost of symmetrizing for GAMG?

t; > On Sat, Sep 17, 2022 at 5:52 PM Barry Smith <mailto:bsm...@petsc.dev>> wrote: > > It is essentially doing AMR each time-step, and for the given application, > I don't think that is pathological. It is an app built on Randy LeVeque's > Clawpack stuff. The linear sol

Re: [petsc-dev] large cost of symmetrizing for GAMG?

al. > I'm doing an MR right now, maybe I should change the default for > -pc_gamg_reuse_interpolation? > > Mark > > > > On Sat, Sep 17, 2022 at 10:12 AM Barry Smith <mailto:bsm...@petsc.dev>> wrote: > > Sure, but have you ever seen such a large jump in t

Re: [petsc-dev] large cost of symmetrizing for GAMG?

raph make a transpose and then adds them. > I imagine adding two different matrices is expensive. > > On Fri, Sep 16, 2022 at 8:30 PM Barry Smith <mailto:bsm...@petsc.dev>> wrote: > > Mark, > >I have runs of GAMG on one and two ranks with -pc_gamg_symmetrize_graph >

Re: [petsc-dev] PetscLogEventRegister() is problematic since it must be call in exactly the same order on all ranks

be called in the same order? > >Matt > > On Fri, Sep 16, 2022 at 9:05 PM Barry Smith <mailto:bsm...@petsc.dev>> wrote: > PetscLogEventRegister() is problematic since it must be call in exactly the > same order on all ranks. So for any computing beyond the triv

[petsc-dev] PetscLogEventRegister() is problematic since it must be call in exactly the same order on all ranks

PetscLogEventRegister() is problematic since it must be call in exactly the same order on all ranks. So for any computing beyond the trivial we've been doing for 30 years -log_view is worthless

[petsc-dev] large cost of symmetrizing for GAMG?

Mark, I have runs of GAMG on one and two ranks with -pc_gamg_symmetrize_graph because the matrix is far from symmetric and some of GAMG is taking a huge amount more time with 2 ranks than one. (While other stuff like VecNorm shows improvement with two ranks). I've attached the two files

Re: [petsc-dev] Still unable to provide link from manual page into users manual after Sphinx

Lawrence, Thanks, I'm going to go with the [optional text](sec_matcreate) syntax > On Aug 28, 2022, at 2:42 PM, Lawrence Mitchell wrote: > > On Sun, 28 Aug 2022 at 18:40, Barry Smith wrote: >> >> >> >> On Aug 28, 2022, at 8:10 AM, Lawrence Mitch

[petsc-dev] Reminder: PETSc release in less than one month

Reminder: There will be a PETSc release in less than one month. Best to get everything that should be in that release organized and ready before that time. Barry

Re: [petsc-dev] proposed minor PetscPartitioner changes

You can use PetscObjectSetOptionsPrefix((PetscObject) partitioner,... > On Aug 31, 2022, at 10:21 AM, Eric Chamberland > wrote: > > Anyone have something to say about this? > > Thanks, > > Eric > > On 2022-07-06 22:32, Eric Chamberland wrote: >> Hi, >> >> I was looking for

Re: [petsc-dev] Still unable to provide link from manual page into users manual after Sphinx

> On Aug 28, 2022, at 8:10 AM, Lawrence Mitchell wrote: > > On Thu, 25 Aug 2022 at 13:37, Barry Smith wrote: >> >> >> That would be great, thanks. Perhaps I am just not passing the label in the >> correct format in the .md file, I tried everything I c

Re: [petsc-dev] Still unable to provide link from manual page into users manual after Sphinx

to be a label or b) it complained that the label I provided did not exist. Barry > On Aug 25, 2022, at 5:56 AM, Lawrence Mitchell wrote: > > Hi Barry, > > On Sun, 21 Aug 2022 at 20:56, Barry Smith wrote: >> >> >> To me, one of the best arguments to move t

  1   2   3   4   5   6   7   8   9   10   >