aboutsummaryrefslogtreecommitdiff
path: root/Carpet
Commit message (Collapse)AuthorAge
* CarpetLib: Add function vect::reverseErik Schnetter2005-05-01
| | | | darcs-hash:20050501171344-891bb-d608668bef718cc9f4c6244b721b3d43d7c33ae0.gz
* CarpetReduce: handle the case of zero reductionsErik Schnetter2005-04-30
| | | | | | When there are zero reductions, allow the output pointers to be NULL. darcs-hash:20050430154439-891bb-95ea930518b19378040601526504ceb6be039a97.gz
* CapretReduce: Do not crash on grid functions with only one time levelErik Schnetter2005-04-28
| | | | | | | When a grid function has only one time level, emit a level 1 warning instead of aborting with an assertion failure. darcs-hash:20050428151159-891bb-53d3330b499a68f0304e99f86aa176af2ca00ecf.gz
* CarpetLib: Correct assert statementsErik Schnetter2005-04-16
| | | | | | | Use assert (dist::rank() == proc()) instead of assert (_owns_storage). The latter is wrong; it misinterprets the meaning of the field _owns_storage. darcs-hash:20050416184109-891bb-a07ba29e020dad420edebaa0c824b7c207d1ac2b.gz
* CarpetIOHDF5: bugfix for checkpoint/recoveryThomas Radke2005-04-12
| | | | | | | | | | | | | | | | | | | | | | | CarpetIOHDF5 used to output unchunked data only, ie. all ghostzones and boundary zones were cut off from the bboxes to be output. This caused problems after recovery: uninitialized ghostzones led to wrong results. The obvious solution, calling CCTK_SyncGroup() for all groups after recovery, was also problematic because that (1) synchronised only the current timelevel and (2) boundary prolongation was done in a scheduling order different to the regular order used during checkpointing. The solution implemented now by this patch is to write checkpoint files always in chunked mode (which includes all ghostzones and boundary zones). This also makes synchronisation of all groups after recovery unnecessary. Regular HDF5 output files can also be written in chunked mode but the default (still) is unchunked. A new boolean parameter IOHDF5::out_unchunked (with default value "yes") was introduced to toggle this option. Note that this parameter has the same meaning as IO::out_unchunked but an opposite default value. This is the only reason why IOHDF5::out_unchunked was introduced. darcs-hash:20050412161430-776a0-d5efd21ecdbe41ad9a804014b816acad0cd71b2c.gz
* CarpetLib: Forbid copying data<T> objectsErik Schnetter2005-04-11
| | | | darcs-hash:20050411183135-891bb-5d2ced682685fb55a00da1864560e54bd113f765.gz
* CarpetLib: Correct errors in handling mem<T> objectsErik Schnetter2005-04-11
| | | | | | | I think there were some errors in handling the mem<T> objects, but I'm not completely sure. darcs-hash:20050411183030-891bb-f1b5510bb4866c8d4bab48a7b320cb6de71b1121.gz
* CarpetLib: Remove unused function transfer_fromErik Schnetter2005-04-11
| | | | darcs-hash:20050411182954-891bb-6f141054635439136d978f98f528af1204919199.gz
* CarpetWeb: Mention new stable versionErik Schnetter2005-04-11
| | | | darcs-hash:20050411172219-891bb-2308d62a8e9de1310efb51d40e6f298310b8bd21.gz
* CarpetInterp: Correct error in allocating data objectsErik Schnetter2005-04-11
| | | | | | | | | data<> objects cannot be implicitly copied. The standard template library containers copy objects arbitrarily. That means that one has to store pointers to data<> objects instead of the objects themselves, and has to allocate and free them manually. darcs-hash:20050411170907-891bb-406b9b6bb6b97df2f47c349f32d91398338439ae.gz
* CarpetIOHDF5: Use CCTK_REAL instead of double for meta dataErik Schnetter2005-04-11
| | | | | | | | Use the type CCTK_REAL instead of double for storing meta data in the HDF5 files. This is necessary if CCTK_REAL has more precision than double. darcs-hash:20050411170627-891bb-374e4c2581155d825f9a1925b1d4319051bc36d6.gz
* CarpetLib: resolve conflict between collective communication and mem<T>Erik Schnetter2005-04-11
| | | | darcs-hash:20050411203309-891bb-5b74d6135f6cd6995f1eed6cc74dd2f29c42f8a8.gz
* CarpetLib: change the default for CarpetLib::use_waitall from "no" to "yes"Thomas Radke2005-04-11
| | | | | | | | Using CarpetLib::use_waitall = "yes" seems to improve Carpet performance both for the standard and for the collective buffers communication scheme. So I made it the default. darcs-hash:20050411173355-776a0-a1046bde7c4ccb4eebc00765b4264701b012c8d8.gz
* Carpet/CarpetLib: deactivate CarpetLib::minimise_outstanding_communicationsThomas Radke2005-04-11
| | | | | | | | | | | | | | The code to minimise the number of outstanding communication requests is superseded by the collective buffers communication code. Therefore the corresponding parameter has been deactivated (but not removed in order to keep backwards compatibility with older checkpoints). It is marked as deprecated in the param.ccl file and should not be used anymore (use CarpetLib::use_collective_communication_buffers instead). A level-2 warning of that meaning is printed at startup if the parameter is still set in a user's parfile. darcs-hash:20050411155524-776a0-ed9919869cc1f2821ab8b2fa23b4abea203b72ed.gz
* CarpetLib: remove erroneous assert statements in the collective buffers ↵Thomas Radke2005-04-11
| | | | | | communication code darcs-hash:20050411141439-776a0-98125bb76dcb733d3649cd50f9a27e4e7c9d2d6d.gz
* Carpet: Handle grid with zero interior cellsErik Schnetter2005-04-11
| | | | darcs-hash:20050411165653-891bb-42b5923d95fc75e8717c6fdcd7f3d180669711da.gz
* Carpet: Do not emit regridding warning for unigrid runsErik Schnetter2005-04-11
| | | | | | | Only complain about a missing regridding function when more than one refinement levels are possible. darcs-hash:20050411165426-891bb-1c4b6916615461eae57106750888ba9fec2e80e7.gz
* CarpetLib: some optimisations for the collective buffers communication schemeThomas Radke2005-04-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | * Receive operations are posted earlier now (don't wait until send buffers are filled). * A send operation is posted as soon as its send buffer is full (don't wait until all send buffers have been filled). * MPI_Irsend() is used instead of MPI_Isend() This probably doesn't make a difference with most MPI implementations. * Use MPI_Waitsome() to allow for overlapping of communication and computation to some extent: data from already finished receive operations can be copied back while active receive operations are still going on. MPI_Waitsome() is now called (instead of MPI_Waitall()) to wait for (one or more) posted receive operations to finish. The receive buffers for those operations are then flagged as ready for data copying. The drawback of this overlapping communication/computation scheme is that the comm_state loop may be iterated more often now. My benchmarks on up to 16 processors showed no performance win compared to using MPI_Waitall() (in fact, the performance decreased). Maybe it performs better on larger numbers of processors when there is more potential for network congestion. The feature can be turned on/off by setting CarpetLib::use_waitall to yes/no. For now I recommend using CarpetLib::use_waitall = "yes" (which is not the default setting). darcs-hash:20050411122235-776a0-e4f4179f46fce120572231b19cacb69c940f7b82.gz
* CarpetIOHDF5: use CCTK_ActiveTimeLevelsGI() instead of ↵Thomas Radke2005-04-11
| | | | | | CCTK_GroupStorageIncrease() to find out the number of timelevels to checkpoint darcs-hash:20050411121428-776a0-13b4d0626e749b2e20079d8101e7a5e9e57e18e1.gz
* CarpetLib: bugfix for collective buffers communicationThomas Radke2005-04-11
| | | | | | | | | | | | Collective buffers were accidentally used (eg. by CarpetIOHDF5 or CarpetIOASCII) even if CarpetLib::use_collective_communication_buffers was set to "no". Now this parameter is evaluated in the comm_state constructor (together with the variable type given) and the result stored in a flag comm_state::uses__collective_communication_buffers. This flag is then used later in comm_state::step() to decide about communication paths. darcs-hash:20050411100916-776a0-aef034c4a23dac96f515cf831d15c8b7e2ce2f9d.gz
* CarpetSlab: fix return value for CarpetSlab_GetList()Thomas Radke2005-04-10
| | | | | | | | | The return code of CarpetSlab_Get() must be checked against 0 for successful completion. The return code of CarpetSlab_GetList() should be the number of slabs returned, or negative in case of errors. darcs-hash:20050410140710-776a0-f293cb8176f10a3cc4fd20a2a0eae71fbda09d9e.gz
* CarpetLib: Resolve conflict after introducing mem<T> classErik Schnetter2005-04-10
| | | | | | | | Resolve the conflict that exists between the patches that introduce the mem<T> class conflicts and the option CarpetLib::use_collective_communication_buffers. darcs-hash:20050410175106-891bb-a66f3783fd8c897d65ed07f55b812e346b406baa.gz
* Carpet: Do not free timelevels in reverse order any moreErik Schnetter2005-03-05
| | | | darcs-hash:20050305175432-891bb-6e79165d8a094d6e54e981cada0c891dfca3d8dd.gz
* CarpetLib: Introduce new class mem<T> for memory managementErik Schnetter2005-03-05
| | | | | | | | | | | | | | | | | | | Introduce a new class mem<T> for memory management. Memory management has become sufficiently complicated to move into its own class. The class mem<T> features: 1. Allocating nelem items of type T 2. Managing contiguous regions of memory for several data<T> objects for vector groups 3. Allowing a pointer to a memory region to be passed in, which is used instead of allocating memory through new 4. Reference counting, so that the mem<T> object only goes away once the last using data<T> object does not need it any more. This makes it unnecessary to delete the first data<T> objects for a grid function group last. darcs-hash:20050305174647-891bb-e1f53adca34e5a668af96c662845cca0f259f8e6.gz
* Carpet: Update doxygen instructionsErik Schnetter2005-04-10
| | | | darcs-hash:20050410120954-891bb-c8ce14e43bfe5591204679e18e27da5721ff0468.gz
* Carpet: Output level times with higher precisionErik Schnetter2005-04-09
| | | | darcs-hash:20050409201450-891bb-24e5e0f2c92eeba86560d85754b40b8525434a3e.gz
* Carpet: Add debugging parameter to output the level timesErik Schnetter2005-04-09
| | | | darcs-hash:20050409195510-891bb-78231ea04482513e00b2a0a278b514ae95e1a8c8.gz
* Carpet: Forbid staggering about the origin only for multiple convergence levelsErik Schnetter2005-04-09
| | | | darcs-hash:20050409190317-891bb-e3601ddafcb9617a6780e43042cd008957a50d78.gz
* CarpetIOHDF5: optimisation of syncing all variables after recoveryThomas Radke2005-04-07
| | | | | | Synchronise all variables of the same vartype at once by calling Carpet::SyncProlongateGroups(). darcs-hash:20050407153843-776a0-e567718c6ba858f4c074c5ec65dd0fc5cb373526.gz
* Carpet: bugfix for high-level synchronisation routinesThomas Radke2005-04-07
| | | | | | | | | | | | | In one of my previous patches I accidentally added two bugs when optimising the high-level synchronisation routines in Carpet: * a SYNC statement did only synchronise the ghostzones but forgot to prolongate the boundaries for grid functions * SyncGroups() also tried to synchronise non-CCTK_GF variables at multigrid and refinement levels other than 0 darcs-hash:20050407150044-776a0-46b495efd5b68ab401ad00c5ac705f786069022c.gz
* CarpetLib: omit the name for the unused dummy function argument in ↵Thomas Radke2005-04-06
| | | | | | dist::datatype() to get rid of g++ compiler warnings darcs-hash:20050406145726-776a0-16ef8cd6d00ca41fcd3662b93bffe649476ff31f.gz
* CarpetLib: make fill_bbox_arrays() a static non-template function in data.cctradke2005-03-16
| | | | darcs-hash:20050316130144-3fd61-1f95c63b76c29de63f212546b5e4fa226afe7299.gz
* CarpetRegrid: remove invalid restrict qualifier in Automatic_Recursive()Thomas Radke2005-04-05
| | | | | | | Intel compilers seem to ignore the qualifier but g++ didn't compile automatic.cc anymore. darcs-hash:20050405095600-776a0-14eb3587897219c3d8fb95a23befc5c8fa2a8227.gz
* CarpetSlab: pass vartype in comm_state constructor tto make use of ↵Thomas Radke2005-03-31
| | | | | | | | | | collective communication buffers So far collective buffers can be used only for the collector object. For the case where all processors should receive the resulting hyperslab, the comm_state loop was left untouched because I didn't understand the code. darcs-hash:20050331082252-776a0-bae45b204fdf31f38969bee81c0ae97edae68f5c.gz
* CarpetIOHDF5: pass vartype in comm_state constructor tto make use of ↵Thomas Radke2005-03-31
| | | | | | collective communication buffers darcs-hash:20050331080034-776a0-629822f876800af1b76d5d43ca131f5373e991a4.gz
* CarpetIOASCII: pass vartype in comm_state constructor tto make use of ↵Thomas Radke2005-03-31
| | | | | | collective communication buffers darcs-hash:20050331074851-776a0-fe39223cec4a68197e224c9b92f4fbef7b6258d8.gz
* CarpetLib, Carpet: implement and use collective communication buffersThomas Radke2005-03-30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Collective buffers are used to gather all components' data on a processor before it gets send off to other processors in one go. This minimizes the number of outstanding MPI communications down to O(N-1) and thus improves overall efficiency as benchmarks show. Each processor allocates a pair of single send/recv buffers to communicate with all other processors. For this the class (actually, the struct) comm_state was extended by 3 more states: state_get_buffer_sizes: accumulates the sizes for the send/recv buffers state_fill_send_buffers: gathers all the data into the send buffers state_empty_recv_buffers: copies the data from the recv buffer back into the processor's components Send/recv buffers are exchanged during state_fill_send_buffers and state_empty_recv_buffers. The constructor for a comm_state struct now takes an argument <datatype> which denotes the CCTK datatype to use for the attached collective buffers. If a negative value is passed here then it falls back to using the old send/recv/wait communication scheme. The datatype argument has a default value of -1 to maintain backwards compatibility to existing code (which therefore will keep using the old scheme). The new communication scheme is chosen by setting the parameter CarpetLib::use_collective_communication_buffers to "yes". It defaults to "no" meaning that the old send/recv/wait scheme is still used. So far all the comm_state objects in the higher-level routines in thorn Carpet (restriction/prolongation, regridding, synchronization) have been enabled to use collective communication buffers. Other thorns (CarpetInterp, CarpetIO*, CarpetSlab) will follow in separate commits. darcs-hash:20050330152811-776a0-51f426887fea099d1a67b42bd79e4f786979ba91.gz
* Carpet: short cut in Restrict(): don't call SyncGVGroup() on empty (vector) ↵Thomas Radke2005-03-25
| | | | | | groups darcs-hash:20050325093919-776a0-2cf1c8734de6187a8622ad69f4d6ac3b1f86e14f.gz
* CarpetLib: remove unused send_listvect argument in copycat() and intercat()Thomas Radke2005-03-23
| | | | darcs-hash:20050323191002-776a0-4a40d844dee2a66e8802669d960709e3488216c4.gz
* CarpetRegrid: Correct some errors in the automatic regridding routineErik Schnetter2005-03-23
| | | | | | | Correct some errors in the automatic regridding routine. Add a parameter for verbose screen output. darcs-hash:20050323211540-891bb-8591fe329d8878afb826f7336d00daf6bb1345cb.gz
* CarpetIOHDF5: fix for IOHDF5::use_reflevels_from_checkpoint = "yes" for the ↵Thomas Radke2005-03-21
| | | | | | case when CarpetRegrid::refinement_levels was also set in the recovery parfile darcs-hash:20050321110931-776a0-6fd09edfbd764f2b4d3f296a3f8c429f1000e407.gz
* CarpetLib: Do not check invariant of bboxset classErik Schnetter2005-03-21
| | | | | | | | | Checking the invariant of the bboxset class is probably O(N^3) in the number of bboxes, possibly worse. It is a very slow operation when there are many components in a simulation, especially with AMR, and possibly also when running on many processors. darcs-hash:20050321020814-891bb-c5eb1cde6f3ac064e39a362b19bd20e15d03bc24.gz
* CarpetLib: Correct misleading commentErik Schnetter2005-03-21
| | | | darcs-hash:20050321020511-891bb-2775aab7e620a3c8da997c10cefcf5ac53124509.gz
* Carpet: fix for my latest patch which still had some (incomplete) debug ↵Thomas Radke2005-03-17
| | | | | | statements left that broke compiling Comm.cc darcs-hash:20050317150756-776a0-d9e6719f3c75b27fe4aaa01a773e9db489a84a5c.gz
* Carpet: simplify SyncGroup(); merge SyncGFArrayGroup() and SyncGFGroup() ↵tradke2005-03-16
| | | | | | into SyncGVGroup() darcs-hash:20050316140925-3fd61-fd64d2290d26975fa5521f57f0d83442d5af7feb.gz
* Carpet: call SyncGFGroup() from within Restrict() to remove code duplicationtradke2005-03-16
| | | | darcs-hash:20050316123248-3fd61-b9695858d99c5d6dc769c0b4e1db3c50c9e5032a.gz
* move block of duplicated assert() statements in ↵Thomas Radke2005-03-16
| | | | | | {copy,interpolate}_from_{recv,send,wait}() further up into {copy,interpolate}_from() so that the code is shared darcs-hash:20050316132044-776a0-525aa7485c2718a9717b6f253553982524872727.gz
* Carpet/CarpetLib: minimise the number of outstanding communication requeststradke2005-03-11
| | | | | | | | | | | | | | | | | | | | | | | This patch greatly reduces the number of outstanding MPI_Isend/MPI_Irecv communication requests by moving the loop over comm_states (recv,send,wait) from the outermost to the innermost. This resolves problems with certain MPI implementations (specifically LAM, MPICH-NCSA, and Mvapich over Infiniband) which potentially resulted in some communication buffer overflow and caused the Cactus application to abort or hang forever. Preliminary benchmarks with BSSN_MoL show that the patch does not have a negative impact on myrinet clusters (measured to 64 processors). It even improves the Carpet performance on GigE clusters (measured up to 16 processors). The order of the communication loops is controlled by the boolean parameter CarpetRegrid::minimise_outstanding_communications which defaults to "no" (preserving the old behaviour). darcs-hash:20050311160040-3fd61-04d40ac79ef218252f9364a8d18796e9b270d295.gz
* CarpetInterp: Correct check whether a processor owns a componentErik Schnetter2005-03-07
| | | | darcs-hash:20050307170026-891bb-03754477692ad245563fda22ecdd4510da4549ab.gz
* Carpet: Add new flag Carpet::constant_load_per_processorErik Schnetter2005-03-07
| | | | | | | | Add a new flag Carpet::constant_load_per_processor which takes the specified grid size and multiplies it by the number of processors. When running benchmarks, this keeps the local load constant. darcs-hash:20050307165844-891bb-7b4c36a5e3bb152086d2eb240a898cb2ac5a3122.gz
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-08 11:32:36 +0000