aboutsummaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAge
...
| * Add .hgignoreErik Schnetter2012-09-11
| |
| * CarpetInterp2: Don't define dim, use Carpet's dim insteadErik Schnetter2012-09-11
| |
| * MergeErik Schnetter2012-09-11
| |\
| | * CarpetInterp2: Improve error messageErik Schnetter2012-09-11
| | | | | | | | | | | | | | | | | | Give more information in error message. Rename macro. Correct typo.
| * | CarpetWeb: fix typo in hg clone instructionsroland haas2012-09-11
| |/
| * CarpetInterp2: Check interpolation stencils for out-of-boundsRoland Haas2012-09-11
| | | | | | | | | | Check all interpolation stencils whether they are inside their respective arrays. Abort with an error message if not.
| * CarpetRegrid2: Warn user if level mask contains nansErik Schnetter2012-09-11
| |
| * CarpetRegrid2: Allocate storage for level_maskErik Schnetter2012-09-11
| |
| * CarpetLib: Ignore empty bboxes in bboxset::operator|=(bbox)Erik Schnetter2011-12-14
| |
| * Carpet: Recursive load balancing: Add dummy components if necessaryErik Schnetter2011-12-14
| | | | | | | | Ensure that all processes have the same number of components.
| * Restrict CarpetIOASCII tests to running on 2 processes onlyIan Hinder2011-12-14
| | | | | | | | The output format is processor-number dependent.
| * CarpetIOASCII: Remove nans from test caseErik Schnetter2011-12-14
| | | | | | | | | | Use InterpToArray instead of Carpet's timers and SphericalSurface as output variables.
| * CarpetIOASCII: Omit erroneous newlines in outputErik Schnetter2011-12-14
| | | | | | | | | | Don't output newline after describing a group's variables unless these are actually output.
| * CarpetIOASCII: Remove test timing output data from repositoryIan Hinder2011-12-14
| | | | | | | | This causes the tests to fail as it changes each time
| * Improve named barriersErik Schnetter2011-12-14
| | | | | | | | | | | | | | | | | | Introduce dist::barrier as low-level implementation of a named barrier. Use it in Carpet::NamedBarrier. Use the above in almost all barrier calls.
| * Carpet: Allow all unsigned int values in named barriersErik Schnetter2011-12-14
| | | | | | | | Don't restrict the range to non-negative signed integers.
| * Carpet: Add missing Adler-32 filesErik Schnetter2011-12-14
| |
| * Carpet: Use unique ids in schedule barriersErik Schnetter2011-12-14
| | | | | | | | | | | | Use an Adler-32 checksum to ensure that the ids in schedule barriers are unique, so that the code really tests that the same functions are called at the same time on all processes.
| * Carpet: Escape & characters in timer XML outputErik Schnetter2011-12-14
| |
| * Slight optimization of CC ENO operators.Christian Reisswig2011-12-14
| |
| * Carpet: Recursive load balancing: Renumber componentsErik Schnetter2011-12-14
| | | | | | | | | | Add more self-checks. Number components sequentially and per-patch.
| * MergeErik Schnetter2011-12-14
| |\
| | * LoopControl: Add some comments to field declarationsErik Schnetter2011-12-14
| | |
| * | CarpetIOHDF5: Introduce API to checkpoint only a subset of groupsErik Schnetter2011-12-14
| | | | | | | | | | | | | | | | | | | | | Introduce a new API to checkpoint only a subset of group, via an aliased function IO_SetCheckpointGroups. This can be used for simulation spawning, i.e. off-loading certain calculations (e.g. analysis) outside of the main simulation.
| * | Carpet: Recursive load balancing: Enable more debugging outputErik Schnetter2011-12-14
| | |
| * | CarpetInterp2: Remove superfluous empty linesErik Schnetter2011-12-14
| | |
| * | CarpetLib: Enable more detailed output for region_tErik Schnetter2011-12-14
| | |
| * | Carpet: Recursive load balancing: Initialise map numbersErik Schnetter2011-12-14
| |/
| * Carpet: Save and restore map information during recursive load balancingErik Schnetter2011-12-14
| |
| * Carpet: Correct errors and add self-checks in "recursive" load balancingErik Schnetter2011-12-14
| |
| * CarpetIOHDF5: plug memory leak introduced in one_file_per_group_optionRoland Haas2011-12-14
| | | | | | | | | | IOUtil_DefaultIORequest returns a fresh copy of the default IO request, rather than just a pointer to it. It has to be freeed afterwards.
| * CarpetIOHDF5: Add missing -D option to make utilities buildErik Schnetter2011-12-14
| |
| * Carpet: Correct error in previous commit regarding no_split_directionErik Schnetter2011-12-14
| |
| * Carpet: Correct implementation of no_split_directionErik Schnetter2011-12-14
| | | | | | | | | | Take no_split_direction into account when deciding into how many slices to cut the domain.
| * Remove intent attribute when declaring pointer arguments in order to allowPeter Diener2011-12-14
| | | | | | | | | | compilation with fortran 4.1.2 that doesn't support Fortran 2003. Also remove allocatable attributes when using intent(in).
| * CarpetIOASCII: Add new "compact" output formatErik Schnetter2011-12-14
| | | | | | | | | | Add support for a more compact output format with fewer columns and lines, enabled by IOASCII::compact_format=yes.
| * CarpetInterp2: Check some array indicesErik Schnetter2011-12-14
| |
| * Carpet: Initialise level_regridding_epochsErik Schnetter2011-12-14
| |
| * CarpetReduce: Use Carpet's MPI reduction operatorsErik Schnetter2011-12-14
| | | | | | | | | | | | Use Carpet's MPI reduction operators instead of the standard MPI operators, because the standard operators do not support complex numbers.
| * CarpetLib: Define MPI reduction operators for complex numbersErik Schnetter2011-12-14
| |
| * CarpetLib: Rewrite vectorisation of prolongate_3d_rf2Erik Schnetter2011-12-14
| |
| * LoopControl: Add more self-checkingErik Schnetter2011-12-14
| |
| * LoopControl: Add many asserts to check correctness at run timeErik Schnetter2011-12-14
| |
| * LoopControl: Remove explicit attribute(pure) declarationsErik Schnetter2011-12-14
| |
| * CarpetInterp2: Use level regridding epochErik Schnetter2011-12-14
| | | | | | | | | | Use level regridding epoch to determine whether the interpolation communication scheme has to be recreated.
| * Carpet: Finish implementing new "recursive" load balancing mechanismErik Schnetter2011-12-14
| |
| * Carpet: Output initial grid structureErik Schnetter2011-12-14
| | | | | | | | Output initial grid structure in the same way as after regridding.
| * Carpet: Introduce per-level regridding epochsErik Schnetter2011-12-14
| |
| * Carpet: Use CCTK_Barrier instead of MPI_BarrierErik Schnetter2011-12-14
| |
| * CarpetIOHDF5: additional check ensuring that a default request is used if theRoland Haas2011-12-14
| | | | | | | | | | | | | | | | | | | | | | | | | | current request does not exist for one_file_per_group output this is re #410: --8<-- by Erik Schnetter --8<-- The corresponding code in CarpetIOHDF5.cc, which outputs data that are not slices, uses the same algorithm. However, it contains an additional check ensuring that a default request is used if the corresponding request does not exist. Look for calls to IOUtil_DefaultIORequest to find this code. I believe that an equivalent logic would correct this problem in OutputSlice.cc. --8<-- by Erik Schnetter --8<--
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-17 10:24:39 +0000