Trac May 2012

trac@lists.einsteintoolkit.org

2 participants
239 discussions

[Einstein Toolkit] #850: New thorns ML_WaveToy and ML_WaveToy_CL
by Einstein Toolkit 25 May '12

25 May '12

#850: New thorns ML_WaveToy and ML_WaveToy_CL -----------------------------------+---------------------------------------- Reporter: eschnett | Owner: Type: enhancement | Status: new Priority: major | Milestone: Component: EinsteinToolkit thorn | Version: Keywords: | -----------------------------------+---------------------------------------- I suggest to add two new thorns to the Einstein Toolkit: ML_WaveToy and ML_WaveToy_CL. Both are generated by Kranc and distributed as part of McLachlan. The former is a standard WaveToy example, showing how a Kranc script looks like that is much simpler than that for the BSSN equations. The latter is essentially the same script, but generates OpenCL code, demonstrating the Cactus OpenCL capabilities. The Kranc script is WaveToy.m, and is already distributed as part of the standard McLachlan distribution. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/850> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 2

[Einstein Toolkit] #805: Add thorn OpenCLRunTime to Einstein Toolkit
by Einstein Toolkit 25 May '12

25 May '12

#805: Add thorn OpenCLRunTime to Einstein Toolkit ----------------------+----------------------------------------------------- Reporter: eschnett | Owner: Type: task | Status: new Priority: major | Milestone: Component: Other | Version: Keywords: | ----------------------+----------------------------------------------------- -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/805> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 2

[Einstein Toolkit] #926: ADMBase variable initialization not thread-safe
by Einstein Toolkit 25 May '12

25 May '12

#926: ADMBase variable initialization not thread-safe --------------------+------------------------------------------------------- Reporter: knarf | Owner: Type: defect | Status: new Priority: major | Milestone: ET_2012_05 Component: Other | Version: development version Keywords: | --------------------+------------------------------------------------------- The attached patch makes the loop variable loop-private, making sure this works when using OpenMP. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/926> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 3

[Einstein Toolkit] #924: Improve sync performance
by Einstein Toolkit 24 May '12

24 May '12

#924: Improve sync performance -------------------------+-------------------------------------------------- Reporter: hinder | Owner: eschnett Type: enhancement | Status: new Priority: minor | Milestone: Component: SimFactory | Version: Keywords: | -------------------------+-------------------------------------------------- Running "sim sync" to a slow remote filesystem can take a long time due to having to check the time stamp and size of all the remote files. It would be good to speed this up. One option would be to assume that files are only edited on the local machine, which is a common situation. Each invocation of sim sync to a given machine would record the time at which it completed, and subsequent syncs would only transfer those files which had changed on the local system since then. A further optimisation would be to avoid statting all the local files by using a filesystem notification API such as fsevents or inotify to determine the required information. An advanced case would also use such a system on the remote side, so you wouldn't have to assume that the remote files were unchanged. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/924> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 1

[Einstein Toolkit] #925: Disable VECTORISE_ALIGNED_ARRAYS
by Einstein Toolkit 24 May '12

24 May '12

#925: Disable VECTORISE_ALIGNED_ARRAYS ------------------------+--------------------------------------------------- Reporter: eschnett | Owner: eschnett Type: defect | Status: new Priority: blocker | Milestone: ET_2012_05 Component: SimFactory | Version: Keywords: | ------------------------+--------------------------------------------------- VECTORISE_ALIGNED_ARRAYS is erroneously set in two option lists. This feature is untested and should be removed. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/925> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 2

[Einstein Toolkit] #922: GSL
by Einstein Toolkit 23 May '12

23 May '12

#922: GSL ----------------------+----------------------------------------------------- Reporter: knarf | Owner: Type: defect | Status: new Priority: critical | Milestone: ET_2012_05 Component: Other | Version: Keywords: | ----------------------+----------------------------------------------------- ExternalLibraries doesn't put -L directories in GSL_LIB_DIRS, but in GSL_LIBS, thus Cactus doesn't add an -rpath thus execution fails on some machines (trestles being one). -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/922> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 5

[Einstein Toolkit] #921: Automatic undersubscribing
by Einstein Toolkit 23 May '12

23 May '12

#921: Automatic undersubscribing -------------------------+-------------------------------------------------- Reporter: hinder | Owner: eschnett Type: enhancement | Status: new Priority: minor | Milestone: Component: SimFactory | Version: Keywords: | -------------------------+-------------------------------------------------- At the moment, http://simfactory.org/info/documentation/userguide/processterminology.html says that if you ask for 6 threads for a job (--procs 6), simfactory will assume that you want to use the whole node and will instead round this up to the number of cores per node, which on LoneStar is 12. If you want to use only 6 threads, you need to use --ppn-used 6. I find this confusing, and would prefer to be able to get 6 threads if I ask for 6 threads, even if underneath I have to claim 12 from the queuing system. This is the way it seems to work on Datura: if I ask for --procs 6, I get 6 threads (i.e. one MPI process). This seems to be in conflict with the documentation, but I prefer this behaviour. Proposal: if the number of threads requested (--procs) is less than the number of cores per node (PPN), then don't round up the number of threads to the nearest larger multiple of PPN. Thoughts? -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/921> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 4

[Einstein Toolkit] #776: GetCompoents/git stalls when cloneing a repository with only a single commit
by Einstein Toolkit 23 May '12

23 May '12

#776: GetCompoents/git stalls when cloneing a repository with only a single commit ---------------------------+------------------------------------------------ Reporter: rhaas | Owner: eric9 Type: defect | Status: new Priority: major | Milestone: Component: GetComponents | Version: Keywords: | ---------------------------+------------------------------------------------ this happens for an up-to-date GetComponent and git version 1.7.8 A simple fix is to change --depth from 1 to 0 in GetComponents. It still checks out one commit. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/776> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 4

[Einstein Toolkit] #923: Clarify what Simfactory replaces in templates
by Einstein Toolkit 23 May '12

23 May '12

#923: Clarify what Simfactory replaces in templates -------------------------+-------------------------------------------------- Reporter: eschnett | Owner: eschnett Type: enhancement | Status: new Priority: major | Milestone: Component: SimFactory | Version: Keywords: | -------------------------+-------------------------------------------------- There is extensive discussion in #919 that should not be forgotten. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/923> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 0

[Einstein Toolkit] #919: simfactory fails for standard thornlist copied using sync
by Einstein Toolkit 23 May '12

23 May '12

#919: simfactory fails for standard thornlist copied using sync --------------------+------------------------------------------------------- Reporter: knarf | Owner: Type: defect | Status: new Priority: major | Milestone: ET_2012_05 Component: Other | Version: Keywords: | --------------------+------------------------------------------------------- Here is my workflow: - checkout ET on my local machine - 'sim sync remotemachine' - 'sim login remotemachine' - 'sim build --thornlist=./thornlists/einsteintoolkit.th' This fails on lonestar because thorns are missing, specifically the OpenCL thorns. I can see why this is failing, but we should fix this before the release. Simfactory 'silentely' enabling thorns is harmful in this workflow of which I think it's not that unusual. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/919> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 13

← Newer
1
...
13
14
15
16
17
18
19
...
24
Older →

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

Trac May 2012