Users May 2015

users@lists.einsteintoolkit.org

23 participants
38 discussions

Meeting Minutes
by Frank Loeffler 18 May '15

18 May '15

Hi, Present today were Erik, Peter, Steven, Frank, Matt, Eloisa, Ian, and Christine. The new release is now almost good to go, and will be release today, after a few minor things are handled. Boost might be added as thorn in the future, but will be disabled by default, at least until an ET actually needs Boost. At that point we will again pick up the discussion how to handle the size of Boost. The next Einstein Toolkit Meeting will be in *two* weeks, on June 1st. Frank Loeffler

1 0

release branches created
by Frank Loeffler 15 May '15

15 May '15

Hi, The release branches and tags have now been created. This means that every change that should make it into the release now has to be committed to this branch (in addition to possibly being committed to trunk/master). Also, the release tag should be reset in that case. These two should only differ after the release (if at all). This also means that the development branch is now open again. Frank

3 4

Einstein Toolkit Meeting Reminder
by Frank Loeffler 15 May '15

15 May '15

1 0

Simfactory: Retired machines
by Erik Schnetter 15 May '15

15 May '15

Note: The two machines SHC (Caltech) and Trestles (SDSC) have been retired in the past month and are not accessible any more. Trestles has been replaced by Comet, an off-the-shelf petascale machine (if such a thing is possible) -- with that I want to say that it should be very easy to use. -erik -- Erik Schnetter <schnetter(a)cct.lsu.edu> http://www.perimeterinstitute.ca/personal/eschnetter/

1 0

Einstein Toolkit Meeting Reminder
by Frank Loeffler 14 May '15

14 May '15

Hi Please consider joining the weekly Einstein Toolkit phone call at 10 am US central time on Mondays. As usual, you can find instructions how to join on the following web site: http://einsteintoolkit.org/community/support/ I short: the number is (+1) 225-578-4942 or (+1) 866-573-0359 and the conference id is 118682#. My agenda contains: - Fall workshop - PLEASE let us know if you come [1]! - Hotel booking - Release planning - release date: Mon Oct 24 2011 - freeze date: Mon Sep 26 - the day of the call! - branch name: ET_2011_10 - List of release-concerning bugs [2] - ET paper: proposed "freeze" by Oct 3rd (Mon after this call) As always: feel free to add to this list. Frank Loeffler [1] https://docs.einsteintoolkit.org/et-docs/ET_Workshop_Fall_2011#Fall_Einstei… [2] https://trac.einsteintoolkit.org/query?status=!closed&milestone=ET_2011_11&…

10 31

Test case requiring strict floating point operation ordering
by Ian Hinder 13 May '15

13 May '15

Hi, The test case test_local_interp_2 in LocalInterp2 is only supposed to pass if the compiler generates code strictly conforming to the ordering dictated by the parentheses in the source code. While this is a part of the C standard, we usually don't insist on this, and use optimisation settings which allow the compiler to reorder expressions if it can be made faster. In a test of the McLachlan RHSs that I did in 2013, I measured a 25% speed reduction from insisting on source-level operation ordering. The ordering of the expressions in the source is usually not meaningful, so reordering does not make it less correct, physically-speaking. The test_local_interp_2 test is specifically testing code which is designed to exactly reproduce symmetries, even including floating point roundoff, and so needs to have strict ordering of operations to be correct. Given that we do not require this ordering in general, having a test which only passes when it is respected is problematic. This raises the question of what to do about this test. I see the following options: 1. Force the compiler to use strict ordering on that section of the code or that file (I don't know how to do this) 2. Disable the test when strict ordering is not available 3. Remove the test entirely 4. Allow the test to fail on machines whose optionlists do not respect IEEE semantics in decreasing order of my own preference. -- Ian Hinder http://members.aei.mpg.de/ianhin

5 6

OpenCL OpenCLRuntime
by Christopher Ramirez 11 May '15

11 May '15

Hello All, I'm trying to include the OpenCL thorns to try and get WaveToyOpenCL to run. When compiling, I run into the following errors. COMPILING arrangements/CactusUtils/OpenCLRunTime/src/kernel-info.cc "/home/ram0311/Cactus/arrangements/Carpet/CarpetLib/src/typeprops.hh", line 62: warning: statement is unreachable return -1; ^ "/home/ram0311/Cactus/arrangements/Carpet/CarpetLib/src/typeprops.hh", line 73: warning: statement is unreachable return -1; ^ "/home/ram0311/Cactus/arrangements/Carpet/CarpetLib/src/typeprops.hh", line 84: warning: statement is unreachable return -1; ^ "/home/ram0311/Cactus/arrangements/CactusUtils/OpenCLRunTime/src/device.hh", line 19: catastrophic error: cannot open source file "CL/opencl.h" # include <CL/opencl.h> ^ 1 catastrophic error detected in the compilation of "/home/ram0311/Cactus/configs/opencl/build/OpenCLRunTime/kernel-info.cc". Compilation terminated. make[3]: *** [kernel-info.cc.o] Error 2 make[2]: *** [make.checked] Error 2 make[1]: *** [/home/ram0311/Cactus/configs/opencl/lib/libthorn_OpenCLRunTime.a] Error 2 I've removed the comments from the einsteintoolkit manifest to update to include everything in the thorns. I had the same error when compiling the OpenCL thorn as well.

2 5

Looking at all open tickets?
by Erik Schnetter 11 May '15

11 May '15

There used to be a link on the ET trac that lists all open tickets. Was this removed? I found this quite useful. -erik -- Erik Schnetter <schnetter(a)cct.lsu.edu> http://www.perimeterinstitute.ca/personal/eschnetter/

3 4

Re: [Users] [ET Trac] [Einstein Toolkit] #1764: Error with compilation of HWLOC
by Zach Etienne 11 May '15

11 May '15

Just to add my own data point: I am using my own build script in Ubuntu with OpenMPI, and I have performed many MPI-based runs (on my desktop and on clusters) with no hitch. While I'm not pushing for a switch to OpenMPI, an ubuntu-openmpi.cfg script would be convenient... -Zach * * * Zachariah Etienne Assistant Professor of Mathematics West Virginia University On Mon, May 11, 2015 at 10:09 AM, Einstein Toolkit < trac-noreply(a)einsteintoolkit.org> wrote: > #1764: Error with compilation of HWLOC > > ------------------------------------+--------------------------------------- > Reporter: maxim.barkov@… | Owner: eschnett > Type: defect | Status: assigned > Priority: blocker | Milestone: ET_2015_05 > Component: EinsteinToolkit thorn | Version: development version > Resolution: | Keywords: HWLOC > > ------------------------------------+--------------------------------------- > > Comment (by eschnett): > > Is there a reason to switch to OpenMPI? If MPICH works fine, then let's > stick with it for the release. Everything is open again one or two weeks > from now. > > Regarding Boost: I don't think we need to add such a comment. If people > want Boost, then they'll figure out that they either have to install it or > to build it themselves (maybe via Cactus). Also, Boost 1.50 is quite > outdated; Boost 1.58 is current, and with two releases per year this makes > it four years old. I expect many packages to simply not work with Boost > 1.50. > > We are very shortly before a release. Now is not the time to clean up > things. Now is the time to test things, and to fix important things that > can't be worked around. > > -- > Ticket URL: <https://trac.einsteintoolkit.org/ticket/1764#comment:18> > Einstein Toolkit <http://einsteintoolkit.org> > The Einstein Toolkit > _______________________________________________ > Trac mailing list > Trac(a)einsteintoolkit.org > http://lists.einsteintoolkit.org/mailman/listinfo/trac >

1 0

Einstein Toolkit Meeting Reminder: Release
by Frank Loeffler 10 May '15

10 May '15

Hi Please consider joining the weekly Einstein Toolkit phone call at 10 am US central time on Mondays. As usual, you can find instructions how to join on the following web site: http://einsteintoolkit.org/community/support/ In short: the number is (+1) 225-578-4942 and the conference id is 118682#. All issues are welcome. The most important issue will be the upcoming release. In particular, we need to take care of all known issues that hold the release back. Please test the current state of the development version in any way you like, on machines you depend on, and report your findings. Frank Löffler

1 0

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

Users May 2015