Trac

trac@lists.einsteintoolkit.org

8708 discussions

#2762: The flesh is not thread safe
by Steven R. Brandt 10 Nov '23

10 Nov '23

#2762: The flesh is not thread safe Reporter: Steven R. Brandt Status: open Milestone: ET_2023_11 Version: Type: bug Priority: major Component: Cactus Comment (by Steven R. Brandt): Add PR [https://bitbucket.org/cactuscode/cactus/pull-requests/158](https://bitbucke… -- Ticket URL: https://bitbucket.org/einsteintoolkit/tickets/issues/2762/the-flesh-is-not-…

1 0

#2172: Test "Binary black hole GW150914" example
by Roland Haas 10 Nov '23

10 Nov '23

#2172: Test "Binary black hole GW150914" example Reporter: Roland Haas Status: open Milestone: ET_2023_11 Version: development version Type: task Priority: major Component: EinsteinToolkit website Changes (by Roland Haas): responsible: [] (was ) assignee: Deborah Ferguson (was ) -- Ticket URL: https://bitbucket.org/einsteintoolkit/tickets/issues/2172/test-binary-black…

1 0

#2757: NSIMD tries to download sleef when compiling
by Gabriele Bozzola 09 Nov '23

09 Nov '23

#2757: NSIMD tries to download sleef when compiling Reporter: Roland Haas Status: new Milestone: Version: Type: bug Priority: major Component: EinsteinToolkit thorn Comment (by Gabriele Bozzola): This happens on anvil too -- Ticket URL: https://bitbucket.org/einsteintoolkit/tickets/issues/2757/nsimd-tries-to-do…

1 0

#2762: The flesh is not thread safe
by Roland Haas 08 Nov '23

08 Nov '23

#2762: The flesh is not thread safe Reporter: Steven R. Brandt Status: open Milestone: ET_2023_11 Version: Type: bug Priority: major Component: Cactus Changes (by Roland Haas): priority: major (was blocker) Comment (by Roland Haas): Dowgrading to “major”, according to [https://docs.einsteintoolkit.org/et-docs/Tickets#Priority](https://docs.ein… a “blocker” is > The ET does not build, or another problem which means development cannot continue. This requires immediate attention. which is not true here. At best one could argue for “critical” if indeed `CarpetX` is considered an important thorn $which I would argue against since it’s new$. -- Ticket URL: https://bitbucket.org/einsteintoolkit/tickets/issues/2762/the-flesh-is-not-…

1 0

#2762: The flesh is not thread safe
by Roland Haas 08 Nov '23

08 Nov '23

#2762: The flesh is not thread safe Reporter: Steven R. Brandt Status: open Milestone: ET_2023_11 Version: Type: bug Priority: blocker Component: Cactus Comment (by Roland Haas): related to #2326. Maybe use `#pragma omp threadlocal` for the global variable in question? At least somewhat standards conforming. -- Ticket URL: https://bitbucket.org/einsteintoolkit/tickets/issues/2762/the-flesh-is-not-…

1 0

#2762: The flesh is not thread safe
by Roland Haas 08 Nov '23

08 Nov '23

#2762: The flesh is not thread safe Reporter: Steven R. Brandt Status: open Milestone: ET_2023_11 Version: Type: bug Priority: blocker Component: Cactus Changes (by Roland Haas): status: open (was submitted) -- Ticket URL: https://bitbucket.org/einsteintoolkit/tickets/issues/2762/the-flesh-is-not-…

1 0

#2762: The flesh is not thread safe
by Steven R. Brandt 08 Nov '23

08 Nov '23

#2762: The flesh is not thread safe Reporter: Steven R. Brandt Status: submitted Milestone: ET_2023_11 Version: Type: bug Priority: blocker Component: Cactus The flesh is not thread safe, and therefore CarpetX’s calling of functions through the flesh via openmp is broken. In particular, the function below The variable :`current_scheduled_function` is a global variable. ``` const cFunctionData *CCTK_ScheduleQueryCurrentFunction(const cGH * CCTK_ATTRIBUTE_UNUSED GH) { return current_scheduled_function; } ``` If one makes the following hackish edit $which I do not recommend$ the problem goes away. ``` db1 flesh$ git diff src/main/ScheduleInterface.c|cat - diff --git a/src/main/ScheduleInterface.c b/src/main/ScheduleInterface.c index 93bdc20..c922904 100644 --- a/src/main/ScheduleInterface.c +++ b/src/main/ScheduleInterface.c @@ -12,6 +12,7 @@ #include <stdlib.h> #include <stdarg.h> #include <string.h> +#include <assert.h> #include "cctk_Flesh.h" #include "cctk_WarnLevel.h" @@ -35,6 +36,8 @@ #include "util_Table.h" +#include "omp.h" + static const char *rcsid = "$Header$"; CCTK_FILEVERSION(main_ScheduleInterface_c); @@ -238,7 +241,7 @@ static int *scheduled_storage_groups_timelevels = NULL; static cTimerData *timerinfo = NULL; static int total_timer = -1; -static const cFunctionData *current_scheduled_function = NULL; +static const cFunctionData *current_scheduled_function[100];// = NULL; /******************************************************************** @@ -286,21 +289,22 @@ int CCTK_CallFunction(void *function, int (*oneargfunc)(void *); + int tn = omp_get_thread_num(); #if ALLOW_RECURSIVE_SCHEDULE_CALLS - const cFunctionData *previous_scheduled_function = current_scheduled_function; + const cFunctionData *previous_scheduled_function = current_scheduled_function[tn]; #else - if(current_scheduled_function != NULL) + if(current_scheduled_function[tn] != NULL) { CCTK_VWarn(CCTK_WARN_PICKY, __LINE__, __FILE__, "Cactus", "CCTK_CallFunction: recursive call, calling " "'%s: %s::%s' while within '%s: %s::%s'", fdata->where, fdata->thorn, fdata->routine, - current_scheduled_function->where, - current_scheduled_function->thorn, - current_scheduled_function->routine); + current_scheduled_function[tn]->where, + current_scheduled_function[tn]->thorn, + current_scheduled_function[tn]->routine); } #endif - current_scheduled_function = fdata; + current_scheduled_function[tn] = fdata; switch(fdata->type) { @@ -317,6 +321,7 @@ int CCTK_CallFunction(void *function, { case LangC: standardfunc = (void (*)(void *))function; + //assert(data != 0); standardfunc(data); break; case LangFortran: @@ -336,9 +341,9 @@ int CCTK_CallFunction(void *function, } #if ALLOW_RECURSIVE_SCHEDULE_CALLS - current_scheduled_function = previous_scheduled_function; + current_scheduled_function[tn] = previous_scheduled_function; #else - current_scheduled_function = NULL; + current_scheduled_function[tn] = NULL; #endif /* Return 0, meaning didn't synchronise */ @@ -369,7 +374,8 @@ int CCTK_CallFunction(void *function, @@*/ const cFunctionData *CCTK_ScheduleQueryCurrentFunction(const cGH * CCTK_ATTRIBUTE_UNUSED GH) { - return current_scheduled_function; + int tn = omp_get_thread_num(); + return current_scheduled_function[tn]; } /*@@ ``` I think what needs to be done is cctkGH needs to hold the current\_scheduled\_function and CarpetX needs to set it appropriately in its various copies. -- Ticket URL: https://bitbucket.org/einsteintoolkit/tickets/issues/2762/the-flesh-is-not-…

1 0

#2747: Inclusion of sgrid importer in Einstein Toolkit
by Michal Pirog 07 Nov '23

07 Nov '23

#2747: Inclusion of sgrid importer in Einstein Toolkit Reporter: Samuel Cupp Status: open Milestone: ET_2023_11 Version: Type: enhancement Priority: major Component: EinsteinToolkit thorn Comment (by Michal Pirog): Done $other suggestions$. -- Ticket URL: https://bitbucket.org/einsteintoolkit/tickets/issues/2747/inclusion-of-sgri…

1 0

#2747: Inclusion of sgrid importer in Einstein Toolkit
by Michal Pirog 07 Nov '23

07 Nov '23

#2747: Inclusion of sgrid importer in Einstein Toolkit Reporter: Samuel Cupp Status: open Milestone: ET_2023_11 Version: Type: enhancement Priority: major Component: EinsteinToolkit thorn Comment (by Michal Pirog): > I’d remove the output file and thorn SystemStatistics from the ActiveThorns line That is what I did. I’m working on the other suggestions now. -- Ticket URL: https://bitbucket.org/einsteintoolkit/tickets/issues/2747/inclusion-of-sgri…

1 0

#2747: Inclusion of sgrid importer in Einstein Toolkit
by Samuel Cupp 07 Nov '23

07 Nov '23

#2747: Inclusion of sgrid importer in Einstein Toolkit Reporter: Samuel Cupp Status: open Milestone: ET_2023_11 Version: Type: enhancement Priority: major Component: EinsteinToolkit thorn Comment (by Samuel Cupp): He already removed the SystemStatistics output, if that’s what you mean. But yeah, removing the thorn completely is a reasonable request. -- Ticket URL: https://bitbucket.org/einsteintoolkit/tickets/issues/2747/inclusion-of-sgri…

1 0

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

Trac