https://gitlab.com/petsc/petsc/-/commit/d7dd068b66a8daa3a37c9e1556b34bd8def54922
On Thu, Jun 24, 2021, at 11:40 AM, Mark Adams wrote:
> How does one view a commit on gitlab?
> I would like to look at d7dd068b66a8daa3a37c9e1556b34bd8def54922
>
> On Thu, Jun 24, 2021 at 9:58 AM Mark Adams wrote:
Looks like this is the relevant code.
for (d = 0; d < dim; ++d) {
if (cgrad[0]) cgrad[0][pd*dim+d] += fg->grad[0][d] * delta;
if (cgrad[1]) cgrad[1][pd*dim+d] -= fg->grad[1][d] * delta;
}
I ran in a debugger and found there was already nan here:
Thread 1 "ex11"
This has been brought up to date every day.
On Wed, Jun 9, 2021 at 5:41 PM Jed Rothwell wrote:
> See:
>
> http://ikkem.com/iccf-23_oralab.php
>
See:
http://ikkem.com/iccf-23_oralab.php
I never used basic auth with Bob on nginx, but other people have and the
thing that is probably missing is proxying websockets.
The information here should cover it
http://nginx.org/en/docs/http/websocket.html
I am hoping that the day job will slow down enough soon so I can get back
to
I'll ahve to look it up, but it's often called amazon basic cables.
it has like a rope coating around the outside, and it outlasts
everything I've ver had.
On 6/6/21, Joshua Hendrickson wrote:
> Anker also makes great iPhone cables as well.
>
> On 6/5/21, Don Ball wrote:
>> you can find good
ICCF23 starts on June 8, 2021, or on June 9, depending on your time zone.
The preliminary program is here:
http://ikkem.com/iccf-23_program.php
Registration is free, but you have to register to see the presentations.
Matthew Knepley writes:
> On Fri, May 28, 2021 at 12:05 PM Mark Adams wrote:
>
>> On Fri, May 28, 2021 at 11:53 AM Lawrence Mitchell wrote:
>>
>>>
>>>
>>> > On 28 May 2021, at 16:51, Mark Adams wrote:
>>> >
>>> > It sounds like I should get one branch settled, use it, and keep that
>>> branch
Patrick Sanan writes:
>> Am 26.05.2021 um 18:39 schrieb Jed Brown :
>>
>> Patrick Sanan mailto:patrick.sa...@gmail.com>>
>> writes:
>>
>>>> Am 25.05.2021 um 22:58 schrieb Barry Smith :
>>>>
>>>>
>>>>
Andy Grove writes:
>
> Looking at this purely from the DataFusion/Ballista point of view, what I
> would be interested in would be having a branch of DF that uses arrow2 and
> once that branch has all tests passing and can run queries with performance
> that is at least as good as the original
Patrick Sanan writes:
>> Am 25.05.2021 um 22:58 schrieb Barry Smith :
>>
>>
>> Now that the users manual is html and we can properly link into it, it
>> would be great to have links from the manual pages to appropriate locations
>> in the users manual. For example SNESSetFunction.html
Michael Foster wrote:
> Everyone just assumes that these visitors must be from civilizations far
> advanced from our own. That may or may not be true.
>
If they are actually visitors from other civilizations, they have to be far
advanced. They cannot be from anywhere in the solar system. Our
I wrote:
> I think there is no likelihood aliens would need help from us, and no
> likelihood they crashed or their equipment failed. A technology capable of
> crossing interstellar space with devices as large as this would be
> "indistinguishable from magic" (Clarke) and it would be hundreds or
Jones Beene wrote:
In that case, the most likely thing ET would need to continue their mission
> is replacement of advanced chips and electronics. To get these parts,
> however, they might first need to intervene somehow in the normal process
> of R on earth by influencing progress and directing
You may be interested in discussion of computing and representing Newton
linearizations for hyperelasticity starting here:
https://libceed.readthedocs.io/en/latest/examples/solids/#id4
Kaushik Vijaykumar writes:
> Thanks Matt, for pointing me in the right direction.
>
>
>
> On Wed, May 19,
I don't follow the advantage over lightweight clones, such as:
$ git clone --branch=release --reference petsc gitlab:petsc/petsc petsc-release
Cloning into 'petsc-release'...
remote: Enumerating objects: 261, done.
remote: Counting objects: 100% (261/261), done.
remote: Compressing objects: 100%
several combinations using the index.html "dev"
> source
> * airflow works out-of-the box in all those combinations
>
> I also see the changes coming from Jed which are fixing the documentation
> about the env vars which look really good.
>
> Fantastic job!
>
&
If you wish to skip to the working demo where you can
https://ooktech-tw.gitlab.io/plugins/tiddly-block-wiki-chain/
By popular demand I have created a TiddlyWiki-based blockchain that runs
completely inside your browser: the *Coud-Enabled TiddlyBlock WikiChain
3.0, IoT Edition*, the worlds
ated.
>
> Cheers,
> Hans
>
> On Monday, May 10, 2021 at 5:14:52 AM UTC-4 inmy...@gmail.com wrote:
>
>> or perhaps I am being too hard on the idea. Instead if you all want I can
>> add blockchain to tiddlywiki and sell NFTs pointing to wikis that I made,
>> like
or perhaps I am being too hard on the idea. Instead if you all want I can
add blockchain to tiddlywiki and sell NFTs pointing to wikis that I made,
like the original twederation wiki or the interaction fiction wiki.
On Monday, May 10, 2021 at 10:54:03 AM UTC+2 Jed Carty wrote:
>
Yes, the central question is could blockchain be useful to tiddlywiki. And
so far the only answer has been to use it as a proof of existence by
storing what is in one blockchain (file hashes in git) in a different from
in another block chain.
Also, traceability in a blockchain is guaranteed
The first, and really only, question about all of this is, what would be
improved by adding a blockchain or NFTs?
And then, if somehow there is something to improve, is the improvement get
us more than the cost in complexity and real-word resources required to
build and maintain the chain?
+1 (non-binding)
On Wed, May 5, 2021 at 1:21 PM Kaxil Naik wrote:
> +1 (binding)
>
> On Wed, May 5, 2021, 20:11 wrote:
>
>> +1
>>
>> śr., 5 maj 2021 o 20:59 Tomasz Urbaszek
>> napisał(a):
>> >
>> > +1, checked checksums, signatures and licenses
>> >
>> > On Wed, 5 May 2021 at 20:50,
I wrote:
> Ed Storms worked on the conventional fission rockets shown in this video.
> I asked him if he thinks this is plausible.
>
He does not think it is plausible, for reasons too complicated to describe
briefly.
- Jed
I like it!
Ed Storms worked on the conventional fission rockets shown in this video. I
asked him if he thinks this is plausible.
The paper is linked from the video discussion, here:
https://arc.aiaa.org/doi/abs/10.2514/6.1990-2371
Here is a *fascinating* look at the Pfizer production lines. Amazing! It
looks a lot like a top-quality experiment. Which it is. See:
https://www.nytimes.com/interactive/2021/health/pfizer-coronavirus-vaccine.html
This has both text and short, high resolution video portions. It shows
close-ups
https://petsc.org/main/docs/manualpages/Vec/VecGetArrayAndMemType.html
Mark Adams writes:
> Have we abstracted VecCUDAGetArray[Read] ?
>
> VecDeviceGetArray?
>
> Mark
t's on
> the front page - in the interests of simplicity and focusing on getting the
> build stable, I haven't been focusing on it, but there is still discussion to
> be had about whether and how to make a prettier front/landing page.
>
>> Am 26.04.2021 um 21:05 schrieb Jed Brown :
>
The sphinx-pydata-theme has great mobile support and lots of development energy
behind it. I don't want to switch themes again based on a sidebar sizing
concern. If the sidebar width is super important, we can adjust the CSS. The
standard CSS has this, which I think is what we'd want to adjust.
in them though to continue to the next generation I’m sure many
of you will feel blessed to know.
Thanks
Jed
Mocksville, NC
Sent from my iPhone
> On Apr 13, 2021, at 12:39 PM, wbmutbb-requ...@wbmutbb.com wrote:
>
> Send WBMUTBB mailing list submissions to
>wbmutbb
+1 (non-binding).
Ran through some simple scenarios with LocalExecutor and KubernetesExecutor.
On Mon, Apr 19, 2021 at 9:04 AM Daniel Imberman
wrote:
> +1 (Binding)
>
> On Mon, Apr 19, 2021 at 6:31 AM, Elad Kalif wrote:
>
> +1 non binding
> tested on several of my dags
>
> On Mon, Apr 19,
Andy Grove writes:
> We started looking at the documentation for git filter-branch and it
> recommends not to use it. It states that "git-filter-branch is riddled with
> gotchas resulting in various ways to easily corrupt repos or end up with a
> mess worse than what you started with:".
I've
One option is to work on the throw-away combined branch as above, keep your
commits for the two topics distinct, then cherry-pick out into the separate
topic branches.
If you are committing in the topics and respinning the throw-away branch, I
would recommend rerere, so you don't have to
Blaise A Bourdin writes:
> Thanks for the reference timing. I can use this to talk to the vendor (or
> switch vendor…).
>
> I am on a 2 socket system. It looks like the node the vendor built for me has
> 4 DIMMS, possibly all connected to the same socket?
>
> [amduser@gigi ~]$ numactl -H
>
sure you see that thread and can join if you are able.
Jed
On Fri, Apr 16, 2021 at 4:18 PM Alexander Ursu
wrote:
> Hi, I was encouraged to send a message to this mailing list in a
> discussion I opened on the Airflow GitHub here
> https://github.com/apache/airflow/discussions/14936
>
Blaise A Bourdin writes:
> Hi,
>
> I am test-driving hardware for a new machine for my group and having a hard
> time making sense the output of the stream test:
>
> I am attaching the results and my reference (xeon 8260 nodes on QueenBee 3 at
> LONI).
>
> If I understand correctly, on the AMD
Wes McKinney writes:
> I think we should take a more serious look at Buildkite for some of our CI.
>
> * First of all, it's very easy to connect self-hosted workers and
> supports ephemeral cloud workers in a way that would be difficult or
> impossible with GHA. No need to have Infra fiddle with
The furnace is in the crawlspace, so I don't know if a leak from the flu
would come into the house. It sure would if the furnace were installed in a
closet in the house. Anyway, they replaced the whole kit and caboodle. I
prefer it that way. I now have faith in the CO alarm, but not too much
bobcook39...@hotmail.com wrote:
Did your old furnace have a closed combustion system with a separate
> fresh air pipe and combustion gas exhaust?
>
They all do, as far as I know. I don't recall the model and it is now out
the door. The new one is a Trane S8B1:
I strongly recommend that readers equip their houses with alarms for smoke
and carbon monoxide. A carbon monoxide alarm may have saved my life a few
days ago. Some of the things it did surprised me, and made me think it was
a false alarm, so let me describe what happened. If you ignore what you
I wrote:
> There are no gas stations in the middle of nowhere either. Granted, gas
> stations are much more prevalent than chargers. Also, when a gasoline car
> runs out of fuel, you can park it somewhere, get a ride to a gas station,
> bring back a gallon of fuel in a plastic tank, and refuel
Terry Blanton wrote:
There's virtually no maintenance...just brakes and tires and very little of
> the former.
>
The brakes do not wear down because they have regenerative braking. Prius
brakes last a long time for the same reason.
CB Sites wrote:
It's interesting Jed, there is a 12V car battery in the back of the car
> that is charged from the Li batteries, which is charged from the engine.
> The 12V is used for the car electronics. I did see a youtube video of a
> guy that used a 2000W 12V inverter for emerge
CB Sites wrote:
> When home, I plug it in with the 115V charger device that plugs into a
> standard 3 prong outlet. Nothing special. It takes about 6-8 hrs for a
> full charge. Most commutes for me are about 30miles so I never see the
> gas engine. Last year my TOTAL gas consumption for
AlanG wrote:
I think a better question is how the Nissan is better than the Chevy Volt,
> which was discontinued after 5 years for disappointing sales, possibly from
> failing to meet efficiency expectations.
>
It has not been discontinued. It is still for sale:
Matthew Knepley writes:
> We use it to identify that the mesh is periodic and in what directions, and
> use the length if we have to figure out the coordinates.
>
>> Jed may argue that he wants you to retain the far point and use L2G to
>> eliminate it, but that sounds
Satish Balay via petsc-dev writes:
> On Wed, 31 Mar 2021, Lisandro Dalcin wrote:
>
>> On Wed, 31 Mar 2021 at 18:07, Satish Balay wrote:
>>
>> > And we just use 2 level workflow, and have branches for each of the
>> > 'releases' [as we move from one to the other]
>> >
>>
>> Maybe I'm not
Satish Balay via petsc-dev writes:
>
> https://semver.org/
>
> Given a version number MAJOR.MINOR.PATCH, increment the:
>
> MAJOR version when you make incompatible API changes,
> MINOR version when you add functionality in a backwards compatible
> manner, and
> PATCH version
t; --Junchao Zhang
>
>
> On Sun, Mar 28, 2021 at 3:34 PM Jed Brown wrote:
>
>> I take it this was using MAT_SUBSET_OFF_PROC_ENTRIES. I implemented that
>> to help performance of PHASTA and other applications that assemble matrices
>> that are relatively cheap to solve (s
I take it this was using MAT_SUBSET_OFF_PROC_ENTRIES. I implemented that to
help performance of PHASTA and other applications that assemble matrices that
are relatively cheap to solve (so assembly cost is significant compared to
preconditioner setup and KSPSolve) and I'm glad it helps so much
Cameron Smith writes:
> Hello,
>
> I'm debugging our use of DMLabel to mark the mesh vertices in a 2d
> triangular mesh on the geometric model boundary.
>
> From what I understand, the latex/tikz and glvis viewers support
> rendering user labels via the following options:
>
> tikz:
> -dm_view
News report:
https://spectrum.ieee.org/tech-talk/energy/nuclear/cold-fusion-or-low-energy-nuclear-reactions-us-navy-researchers-reopen-case
Whether Cold Fusion or Low-Energy Nuclear Reactions, U.S. Navy Researchers
Reopen Case
Spurred on by continued anomalous nuclear results, multiple labs now
Matthew Knepley writes:
>> PetscSectionSetUp currently calculates offsets by walking the points in
>> order. I'd like to be able to walk them in a different ordering, perhaps
>> specified via an IS permutation, which could be computed using
>> MATORDERINGRCM or directly via BFS of a closure
e same test on LSU
> machines (Xeon 8260).
> Blaise
>
>
> On Mar 19, 2021, at 10:27 AM, Jed Brown
> mailto:j...@jedbrown.org>> wrote:
>
> Blaise A Bourdin mailto:bour...@lsu.edu>> writes:
>
> Hi,
>
> I am pricing out a new small cluster for my group a
Matthew Knepley writes:
> On Fri, Mar 19, 2021 at 2:21 PM Jed Brown wrote:
>
>> Matthew Knepley writes:
>>
>> >> Notice how the permutations are contained within the vertices {0, ...,
>> 8},
>> >> edges {9, ..., 24}, and cells {25, ..., 32}. I
Matthew Knepley writes:
>> Notice how the permutations are contained within the vertices {0, ..., 8},
>> edges {9, ..., 24}, and cells {25, ..., 32}. I would like to get rid of
>> that restriction, but you've said it would have significant non-local
>> consequences so I haven't tried.
>>
>
>
Lawrence Mitchell writes:
>> On 19 Mar 2021, at 14:21, Jed Brown wrote:
>>
>> Notice how the permutations are contained within the vertices {0, ..., 8},
>> edges {9, ..., 24}, and cells {25, ..., 32}. I would like to get rid of that
>> restriction, but you've
Matthew Knepley writes:
> On Fri, Mar 19, 2021 at 7:30 AM Lawrence Mitchell wrote:
>
>> > On 19 Mar 2021, at 03:51, Jed Brown wrote:
>> >
>> > It's a notable weakness of DMPlex that it does not apply such an
>> ordering of dofs and I've complained to Mat
Note that this is specific to the node numbering, and that node numbering tends
to produce poor results even for MatMult due to poor cache reuse of the vector.
It's good practice after partitioning to use a locality-preserving ordering of
dofs on a process (e.g., RCM if you use MatOrdering).
I'm interested in providing some path to make this extensible. To pick an
example, suppose the user wants to compute the first k principle components.
We've talked [1] about the possibility of incorporating richer communication
semantics in Ballista (a la MPI sub-communicators) and numerical
Hey guys,
So right off the bat I'm having an issue with this blind drive game.
It said something about sign out of game center. I click on the OK
button, and it does nothing. Any ideas?
On 3/17/21, Johna Gravitt wrote:
> Also if you search the ap store for blind fold games the app will come up
Barry Smith writes:
>> On Mar 12, 2021, at 6:58 PM, Jed Brown wrote:
>>
>> Barry Smith writes:
>>
>>> I think we should start porting the PetscFE infrastructure, numerical
>>> integrations, vector and matrix assembly to GPUs soon. It i
Barry Smith writes:
> I think we should start porting the PetscFE infrastructure, numerical
> integrations, vector and matrix assembly to GPUs soon. It is dog slow on CPUs
> and should be able to deliver higher performance on GPUs.
IMO, this comes via interfaces to libCEED, not rolling
writes:
> Jed,
>
> Thanks for the insight.
>
> Maybe Hong and his Ellpack format? Or his independent set algorithm?
>
> Maybe Stefano and his COO matrix assembly on GPUs?
>
> Others?
>
> Barry
>
>
>> On Mar 12, 2021, at 4:37 P
I helped with one of these a couple years ago. It's important to go in with a
well-defined problem and mini-app. If "PETSc" is the topic, then you should
start with a representative benchmark problem that runs in no more than a
couple minutes. It could be two problems, one that we think is good
Says the pipeline was canceled. The branch comes from a fork so it should need
approval to run.
https://gitlab.com/petsc/petsc/-/merge_requests/3707
Matthew Knepley writes:
> https://gitlab.com/danfinn/petsc/-/pipelines/269297070
>
> Thanks,
>
> Matt
>
> --
> What most experimenters
There is some use of Iscatterv in SF implementations (though it looks like
perhaps not PetscSFBcast where the root nodes are consolidated on a root rank).
We should perhaps have a function that analyzes the graph to set the type
rather than requiring the caller to PetscSFSetType.
Barry Smith
The one value-add that comes from ReadTheDocs is its version switcher, which
we'd need to do ourselves.
I've been using this strategy (for stand-alone preview) on a different project
and it's working great. We can decide how to merge it (i.e., where the doc job
should run).
If you're in Emacs, Magit (https://github.com/magit/magit) is excellent for
much the same things, and works over remote (i.e., I'm editing
"ssh:thathost:path/to/file.c" and invoke magit).
There's also a (partial) magit clone for vscode.
I wonder if gfortran has a similar "bug" but larger capacity that would explain
why it's so much more expensive to compile the Fortran interface files than to
compile all of PETSc.
Barry Smith writes:
>PETSc stacks the Fortran modules in the same way it stacks the C include
> files. So
Satish Balay via petsc-dev writes:
> On Wed, 3 Mar 2021, Blaise A Bourdin wrote:
>
>> Hi,
>>
>> This is not technically a petsc question.
>> It would be great to have a short section in the PETSc integration workflow
>> document explaining how to squash commits in a MR for git-impaired
>>
Don't fret about it. We have thick skin in this business. Welcome back!
On Mon, Feb 22, 2021 at 10:10 PM Kyle Mcallister
wrote:
> Hello again, Vortexians.
>
> It's been a long time, perhaps 10 years or so since I've been here. I
> can't recall exactly, but that was another life. You'd be
split_1_lsc_pc_type mat" ?
>
> Elena
>
> Il giorno mer 24 feb 2021 alle ore 06:04 Jed Brown ha
> scritto:
>
>> If you've already attached a MatShell, you could presumably use
>> -fieldsplit_1_lsc_pc_type mat to just call its MatMult.
>>
>> T
If you've already attached a MatShell, you could presumably use
-fieldsplit_1_lsc_pc_type mat to just call its MatMult.
The sense I've gotten when I wrote PCLSC and was experimenting with these
methods is that the main selling point of LSC (for most discretizations) is
that it's more algebraic
Note that one of the NYT projections also shows April as the date herd
immunity begins. Look at the graph with three choices labeled "CHOSE A
SCENARIO." Select the third choice:
Huge supply increase
5 million shots per day
The text changes to:
It’s a stretch, but if the pace increases to 5
I wrote:
Taking into account one thing and another, the WSJ and the NYT estimates
> are not far apart.
>
WSJ predicts April, NYT predicts July. A 3-month difference is not gigantic
given all the unknowns. For example, what percent of the population will it
take for herd immunity to begin? The
Taking into account one thing and another, the WSJ and the NYT estimates
are not far apart. Herd immunity is not an absolute condition, and it does
not turn on all at once over a certain threshold. The gradations in orange
color at the top of the NYT graph show that it emerges gradually.
The WSJ article is behind a paywall. I hope this doctor is right. Other
estimates put herd immunity sometime around August. See:
https://www.nytimes.com/interactive/2021/02/20/us/us-herd-immunity-covid.html
(I think this NYT article is not behind the paywall.)
On Fri, Feb 19, 2021 at 9:13 PM
Patrick Sanan writes:
> Aside: it's been on the list of good things to do, docs-wise, to be able to
> label parts of the API as more or less stable, so I'm hoping we'll get to
> that (though I think it makes sense to wait until we've finished some of the
> current migrations tasks).
Yes, I
ISCUDA isn't even right (perhaps ISGENERALCUDA, ISBLOCKCUDA). I agree that this
isn't a priority, but I could see it being needed in the next few years to
avoid bottlenecks in adaptive mesh refinement or other adaptive algorithms.
It's not a small amount of work, but I think all the index
My research group has openings for a Research Software Engineer and a Postdoc.
Details and application links below; feel free to email me with questions.
## Research Software Engineer
CU Boulder’s PSAAP Multidisciplinary Simulation Center for Micromorphic
Multiphysics Porous and Particulate
My research group has openings for a Research Software Engineer and a Postdoc.
Details and application links below; feel free to email me with questions.
## Research Software Engineer
CU Boulder’s PSAAP Multidisciplinary Simulation Center for Micromorphic
Multiphysics Porous and Particulate
Roland Richter writes:
> Hei,
>
> the compilation line is (as shown below)
>
> //usr/lib64/mpi/gcc/openmpi3/bin/mpicxx -DBOOST_ALL_NO_LIB
> -DBOOST_FILESYSTEM_DYN_LINK -DBOOST_MPI_DYN_LINK
> -DBOOST_PROGRAM_OPTIONS_DYN_LINK -DBOOST_SERIALIZATION_DYN_LINK
> -DUSE_CUDA
>
There is no getting through to people like the editors at Physics Today. I
expect that even if everyone here were to write to them, they would reject
every message.
They think of themselves as fair, objective and open minded. Perhaps they
are open minded about some subjects, but not cold fusion.
It's entirely possible, especially if libgomp is being mixed with libiomp.
Roland hasn't show us the compilation line (just linker), because `omp
parallel` shouldn't do anything with just -fopenmp-simd and no -fopenmp.
Matthew Knepley writes:
> Jed, is it possi
the right kind of scientists to be
doing the work. In neither case was it enough, at the time, simply to say
the results weren’t replicated, even though that is how we describe it in
retrospect."
I posted the following response, which was removed.
Jed Rothwell <https://disqus.com/by/disqu
Roland Richter writes:
> Hei,
>
> I replaced the linking line with
>
> //usr/lib64/mpi/gcc/openmpi3/bin/mpicxx -march=native -fopenmp-simd
> -DMKL_LP64 -m64
> CMakeFiles/armadillo_with_PETSc.dir/Unity/unity_0_cxx.cxx.o -o
> bin/armadillo_with_PETSc
>
You're using an MKL linked to Intel's OpenMP. I could imagine there being
symbol conflicts causing MKL to compute wrong results if libgomp symbols are
picked up.
Note that -fopenmp-simd does not require linking -- it just gives the compiler
hints about how to vectorize. So you can probably
make libs should do that.
Blaise A Bourdin writes:
> Hi,
>
> Is there a way to rebuild the petsc library only, skipping rebuilding mpi4py
> and petsc4py if petsc is configured with them? I know I can ctrl-C this step
> if all I want is to rebuild the lib, but I would not mind a more elegant
Pierre Jolivet writes:
> I’m playing the Devil’s advocate since the beginning, we’ve had a
> --enable-generic (off by default) which turns -march=native into
> -march=generic for 20+ years (I’m seeing references to PPC7450 and Intel
> Coppermine in our configure…).
> We turn this flag on when
Jacob Faibussowitsch writes:
>> working out dispatch in MatCreate_XXX() instead of for each function.
>
> Or use compiler extensions for multiversioned functions (I recall GCC has
> something similar):
> https://clang.llvm.org/docs/AttributeReference.html#target
>
Barry Smith writes:
>> On Feb 14, 2021, at 12:13 PM, Jed Brown wrote:
>>
>> Barry Smith writes:
>>
>>>> This is a reasonable message to print on the screen, but I don’t think
>>>> this is a reasonable flag to impose by default.
>>>>
Barry Smith writes:
>My feeling is 90+% of users don't care about portability, they want to get
> fast performance on the machine they are compiling with (or a collection of
> machines they have around).
This is an exclusionary view of users. PETSc could and would be used in more
Barry Smith writes:
>> This is a reasonable message to print on the screen, but I don’t think this
>> is a reasonable flag to impose by default.
>> You are basically asking all package managers to add a new flag
>> (-march=generic) which was previously not needed.
>
> This is a tough
(yet trivial to implement) option might also be to just alert the
>>> user that these flags exist in the usual message about using default
>>> optimization flags. Something like this would encourage users to do what
>>> Jed is doing:
>>>
>>> *
er.
>
> Barry
>
> I run ./configure --with-debugging=0 and I get none of the stuff added by
> Intel for 15+ years?
>
>
>> On Feb 13, 2021, at 11:26 PM, Jed Brown wrote:
>>
>> Use -march=native or similar. The default target is basic x86_64, which has
&
Use -march=native or similar. The default target is basic x86_64, which has
only SSE2.
Barry Smith writes:
> PETSc source has code like defined(__AVX2__) in the source but it does not
> seem to be able to find any of these macros (icc or gcc) on the petsc-02
> system
>
> Are these macros
U.S. wind generation sets new daily and hourly records at end of 2020
https://www.renewableenergyworld.com/wind-power/u-s-wind-generation-sets-new-daily-and-hourly-records-at-end-of-2020/
QUOTE:
On April 10, 2019, daily electricity generation from wind turbines in the
United States (excluding
Sepideh Kavousi writes:
> I am not running an specific example. Attached is my code. and when I wun
> with
> ./step5.out -snes_monitor -snes_fd_color -ts_monitor -snes_converged_reason
> -pc_type lu
>
> it seems it does not solve anything because the output is like:
>
> 0 SNES Function
Sepideh Kavousi writes:
> Hello,
> I have a very stupid problem that I am really ashamed of asking but it has
> been with me for days and I do not know what to do. I want to solve the
> Javier stokes equation with finite difference method.
Could you run with -snes_monitor
901 - 1000 of 29974 matches
Mail list logo