| Commit message (Collapse) | Author | Age |
|
|
|
|
|
|
|
|
|
| |
Output "seconds" instead of the actual timer value, in accordance with
the column headers.
Do not indent output.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4933 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
| |
Using the data string as a format string can be a security vulnerability and hence triggers a compiler warning.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4916 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
| |
These functions return whether a Cactus timer is running or not (either by name or by handle).
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4890 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
|
| |
this adds a function CCTK_ScheduleQueryCurrentFunction which returns the
cFunctionData of the function currently executing via
CCTK_CallScheduledFunction
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4805 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
|
|
| |
This provides support for specifying READS and WRITES clauses for each
function scheduled in schedule.ccl. These list the variables which
the scheduled function reads from or writes to. This supports future
dependency-based scheduling. See
https://docs.einsteintoolkit.org/et-docs/Adding_requirements_to_the_Cactus_scheduler
for more information.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4788 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
| |
modifiers, and some of them apparently allow non-full variable names. My mistake, not corrected.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4639 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
| |
schedule tree, and give corresponding warning message
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4637 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
| |
Cactus does at startup a bit, fixing also some indentation problems.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4620 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
| |
global_late. These modes can then be used in Carpet, where they will
simplify traversing the schedule tree when local, level, and global
mode routines are mixed.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4589 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
|
|
| |
so its execution times in different bins can be distinguished.
For multiple calls within the same bin, the accumulated time is reported
only once.
This applies patch http://www.cactuscode.org/old/pipermail/patches/2009-April/000258.html.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4557 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4511 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
| |
only makes sense for while_check. Update all callers and callees.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4502 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4489 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Schedule items in Cactus can already have WHILE clauses, which means
that they are executed while a certain condition are true. This patch
adds IF clauses, which means that they are executed only if a certain
condition is true. The syntax is equivalent to WHILE clauses.
These if clauses is different from the existing C-syntax if
statements, which are only evaluated at startup and determine how the
schedule is constructed. These if clauses are evaluated every time
the schedule is traversed, and can skip certain schedule items.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4478 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
| |
postinitial is executed before the recursive initialisation of finer
grids, not afterwards.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4477 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4469 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
| |
when the grid hierarchy is changed
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4468 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
| |
The existing internal schedule printing functions now take an
additional FILE* argument, and the existing CCTK_SchedulePrintTimes
prints explicitly to stdout.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4428 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
groups.
Whether the synchronisation was done by CCTK_CallFunction or not was
stored in the "synchronised" flag of a t_sched_data object. This
object exists only once for the simulation, and not once for each
recursive call of the scheduler when it traverses groups. Thus the
information was correct only for the innermost schedule item, namely
functions, and incorrect for schedule groups.
Because PUGH does not overload CCTK_CallFunction, and thus this flag
always stays false, I assume that this error does not occur with PUGH
simulations. It does occur with Carpet simulations.
As a quick solution, I moved the "synchronised" flag from the
t_sched_data structure into the t_attribute structure. This does not
work for recursive calls.
It may be that the t_attribute structure is meant for unchanging
information. In that case, it is necessary to construct a stack of
t_sched_data objects.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@4060 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
| |
"loop-level", "loop-global", and "loop-meta". This makes CallFunction
loop over the corresponding modes.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3812 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3811 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3810 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3788 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3768 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
|
|
| |
This removes spurious timer warnings.
Check malloc return value.
Change message from "[...] at [group]" to "[...] in [group]".
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3646 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3643 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3575 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
| |
executes the scheduled item always.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3552 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3506 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
| |
scheduled at different schedule bins.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3467 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
| |
schedule tree.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3432 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3384 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
|
|
| |
a scheduled routine can have options associated with it. LEVEL mode
is where the routine should only be called once for any set of sub-grids
with the same cctk_levfac numbers.
Tom
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3209 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
enclosing group is triggered. The logic is now that if a group is
triggered at analysis, all member routines or groups of that group will be
automatically triggered unless they in turn have a trigger, in which case
that overrides the trigger.
E.g.
schedule TestSchedule_CalcOne AT Analysis before TestSchedule_Analysis
{
storage: testschedule::one
trigger: testschedule::one
lang: C
} "Calculate the value of one"
schedule group TestSchedule_Analysis at ANALYSIS
{
trigger: testschedule::two testschedule::three
} "TestSchedule top level analysis group"
schedule TestSchedule_CalcTwo IN TestSchedule_Analysis
{
trigger: testschedule::two
storage: testschedule::two
lang: C
} "Calculate the value of two"
schedule GROUP TestSchedule_Analysis2 in TestSchedule_Analysis after TestSchedule_CalcTwo
{
trigger: testschedule::three
} "TestSchedule second level analysis group"
schedule TestSchedule_CalcThree IN TestSchedule_Analysis2
{
trigger: testschedule::three
storage: testschedule::three
lang: C
} "Calculate the value of three"
will call the appropriate routines to calculate one, two or three if these are selected for
output.
As before, output is done on any trigger variable or variable group when a routine with
the variable as a trigger exits. So in the above example "three" is output when CalcThree
exits. If this is not desired, the trigger and storage for "three" could have been placed
on the enclosing schedule group, and then the routine would have been called even if output
was only requested for "two" and not for "three".
This fixes PR 694, and helps with PR 844.
Tom
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3188 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
| |
or group.
Tom
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3148 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
people to schedule in the real name and then schedule many aliases of the
group in the same schedule bin or parent group.
Note that you need to do a
make <config>-rebuild
on your configurations after updating with this change.
Tom
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3147 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
| |
Closes Cactus/1283
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3068 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
| |
Tom
git-svn-id: http://svn.cactuscode.org/flesh/trunk@3029 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2900 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2768 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
should now work.
Note that the COMM stuff is now completely obsoleted and the schedule stuff
no longer schedules variable groups for comm (this only affects driver writers as
the statement has been deprecated for ages).
Tom
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2725 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
| |
Tom
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2723 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
|
|
|
| |
Currently passes -1 as the timelevel for each group as we don't specify and
read that data from the schedule.ccl files yet.
This should make no visible change to anyone.
Tom
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2694 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
| |
beginning of a group now.
Tom
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2670 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
| |
Also put in Erik's patch to print group names in a schedule.
This closes PR Cactus/771.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2669 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
| |
This closes PR Cactus/943.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2664 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
| |
This closes PR Cactus/804.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2655 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2654 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
| |
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2526 17b73243-c579-4c4c-a9d2-2d5706c11dac
|
|
|
|
|
|
|
|
|
| |
Now POSTSTEP routines aren't run anymore twice on the same timestep after
recovery.
Closes PR Cactus-824 and Cactus-826.
git-svn-id: http://svn.cactuscode.org/flesh/trunk@2512 17b73243-c579-4c4c-a9d2-2d5706c11dac
|