Hi
We need people running tests on various machines. See below for a (probably not complete) list of machines that we don't have even halfway recent results online, but should. Pick and choose some by replying to this email. This includes not only actually running the tests, but potentially trying to fix problems if any arise - so simply running 'distribute' might not be all that is needed, and not everyone has a login everywhere.
bluewaters hopper kraken stampede supermuc titan zwicky
I do/did
queenbee supermike tezpur spine
Frank
On 12 Nov 2013, at 21:47, Frank Loeffler knarf@cct.lsu.edu wrote:
Hi
We need people running tests on various machines. See below for a (probably not complete) list of machines that we don't have even halfway recent results online, but should. Pick and choose some by replying to this email.
I am looking at stampede.
On 11/13/2013 03:35 PM, Ian Hinder wrote:
On 12 Nov 2013, at 21:47, Frank Loeffler knarf@cct.lsu.edu wrote:
Hi
We need people running tests on various machines. See below for a (probably not complete) list of machines that we don't have even halfway recent results online, but should. Pick and choose some by replying to this email.
I am looking at stampede.
I would like to run on supermuc once you all have decided to replace or not the Exact tests for EinsteinExact.
Thanks, Bruno.
Users mailing list Users@einsteintoolkit.org http://lists.einsteintoolkit.org/mailman/listinfo/users
On 14 Nov 2013, at 12:03, Bruno Coutinho Mundim bcmsma@astro.rit.edu wrote:
On 11/13/2013 03:35 PM, Ian Hinder wrote:
On 12 Nov 2013, at 21:47, Frank Loeffler knarf@cct.lsu.edu wrote:
Hi
We need people running tests on various machines. See below for a (probably not complete) list of machines that we don't have even halfway recent results online, but should. Pick and choose some by replying to this email.
I am looking at stampede.
I would like to run on supermuc once you all have decided to replace or not the Exact tests for EinsteinExact.
I suggest that you run anyway. It's likely there will be failures (all intel-compiler-based systems are currently showing failures in GRHydro and other tests), so you may as well set up your tree and command lines etc. Once we sort out all the problems, you should just be able to run again to get the new results.
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1
Hello all,
I suggest that you run anyway. It's likely there will be failures (all intel-compiler-based systems are currently showing failures in GRHydro and other tests), so you may as well set up your tree and
Not all intel systems show the same behaviour. Intel 12/13 based systems seem to have few tests that fail and those that fail fail due to tolerances being possibly too large.
Intel 11 system on the other hand crash catastrophically, from what I can tell so far from the compiler not handling Cray pointers correctly (eg the Hydro_InitExcision gives a segfault). So far I have no good workaround for the issue. I will have to check if all usage of Cray pointers is affected or only the Reconstruction drivers (which is where the segfault happens) since they use array slices.
These are not the usual GRHydro failures unfortunately but instead a compiler bug. A workaround that does not fail on other compilers is required (one workaround is eg to set the size of the leftmost dimension of the pointee in question to zero, it almost seems as if the compiler actually allocates space for the pointees).
Yours, Roland
- -- My email is as private as my paper mail. I therefore support encrypting and signing email messages. Get my PGP key from http://keys.gnupg.net.
On 14 Nov 2013, at 16:43, Roland Haas roland.haas@physics.gatech.edu wrote:
Signed PGP part Hello all,
I suggest that you run anyway. It's likely there will be failures (all intel-compiler-based systems are currently showing failures in GRHydro and other tests), so you may as well set up your tree and
Not all intel systems show the same behaviour. Intel 12/13 based systems seem to have few tests that fail and those that fail fail due to tolerances being possibly too large.
Intel 11 system on the other hand crash catastrophically, from what I can tell so far from the compiler not handling Cray pointers correctly (eg the Hydro_InitExcision gives a segfault). So far I have no good workaround for the issue. I will have to check if all usage of Cray pointers is affected or only the Reconstruction drivers (which is where the segfault happens) since they use array slices.
These are not the usual GRHydro failures unfortunately but instead a compiler bug. A workaround that does not fail on other compilers is required (one workaround is eg to set the size of the leftmost dimension of the pointee in question to zero, it almost seems as if the compiler actually allocates space for the pointees).
If there is a workaround, that is of course good, but another alternative would be to say that Intel 11 is unsupported with the new features in grhydro, and to update the optionlists to a newer version where cray pointers work. On some machines, this won't be possible, e.g. tezpur, where intel11 is the latest version available.
In any case, an autoconf test, or a runtime test, that cray pointers are working correctly, would be very nice to have.
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1
Hello all,
I am looking at stampede.
To clarify: do we have a list of machines for which tests were already run anywhere? I checked out Ian's repository http://git.barrywardell.net/EinsteinToolkitDaturaTestResults.git which seems to contain results only for datura, kraken, redshift and stampede . Are these all that the tests were run on? If so then we need to run on the other machines, if not is it possible to put the results of the tests somewhere accessible?
Yours, Roland
- -- My email is as private as my paper mail. I therefore support encrypting and signing email messages. Get my PGP key from http://keys.gnupg.net.
On Thu, Nov 14, 2013 at 07:47:14AM -0800, Roland Haas wrote:
To clarify: do we have a list of machines for which tests were already run anywhere? I checked out Ian's repository
As always:
http://einsteintoolkit.org/release-info/parse_testsuite_results.php
Frank
On 14 Nov 2013, at 16:47, Roland Haas roland.haas@physics.gatech.edu wrote:
Signed PGP part Hello all,
I am looking at stampede.
To clarify: do we have a list of machines for which tests were already run anywhere? I checked out Ian's repository http://git.barrywardell.net/EinsteinToolkitDaturaTestResults.git which seems to contain results only for datura, kraken, redshift and stampede . Are these all that the tests were run on? If so then we need to run on the other machines, if not is it possible to put the results of the tests somewhere accessible?
The release-info repository is still the best central location for this. Erik and I are working on sending data from the distribute script to the automated jenkins system, but this is not ready yet. I am updating the release-info repository when I have new results manually at the moment.
users@lists.einsteintoolkit.org
-
Bruno Coutinho Mundim -
Frank Loeffler -
Ian Hinder -
Roland Haas