Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | CarpetAdaptiveRegrid: Improve CCTK_Warn replacement | Erik Schnetter | 2012-09-11 |
| | |||
* | CarpetLib: add preliminary support for higher order restriction | Roland Haas | 2012-09-11 |
| | |||
* | CarpetInterp: "m" -> "mglevel" when accessing ↵ | Christian Reisswig | 2012-09-11 |
| | | | | groupdata.AT(gi).activetimelevels.AT(mglevel).AT(rl) to find out how many active timelevels are available. When using "m", I get a std::vector out of range. | ||
* | CarpetInterp: Don't use CCTK_ActiveTimeLevels to get number of active ↵ | Christian Reisswig | 2012-09-11 |
| | | | | | | timelevels. Use groupdata.AT(gi).activetimelevels.AT(m).AT(rl) instead. This rempoves a problem in CarpetInterp's error check. | ||
* | CarpetReduce: increase warning level about possible deadlock to | Roland Haas | 2012-09-11 |
| | | | | | WARN_DEBUG from WARN_PICKY since there might still be thorns around that do so | ||
* | CarpetEvolutionMask: add relative error tolerance of 1e-12 | Roland Haas | 2012-09-11 |
| | |||
* | CarpetIOScalar: add test cases for all combinations of | Roland Haas | 2012-09-11 |
| | | | | one_file_per_group and all_reductions_in_one_file | ||
* | CarpetIOScalar: correct column labels | Roland Haas | 2012-09-11 |
| | | | | when both one_file_per_group and all_reductions_in_one_file are active | ||
* | CarpetReduce: output calling routine when warning about reductions | Roland Haas | 2012-09-11 |
| | | | | in local mode | ||
* | CarpetLib: Fill overlap zones via prolongation during regrid. | Christian Reisswig | 2012-09-11 |
| | |||
* | CarpetLib: disable debug output | Roland Haas | 2012-09-11 |
| | |||
* | Remove all #warning statements | Erik Schnetter | 2012-09-11 |
| | |||
* | CarpetLib: Correct determining overlap zones | Erik Schnetter | 2012-09-11 |
| | |||
* | CarpetLib: Correct determining buffer and overlap zones | Erik Schnetter | 2012-09-11 |
| | |||
* | LoopControl: Explain why downcast is safe | Erik Schnetter | 2012-09-11 |
| | |||
* | CarpetLib: Disable OpenMP collapse statements | Erik Schnetter | 2012-09-11 |
| | | | | These do not work on all systems, and we don't autoconf them yet. | ||
* | CarpetEvolutionMask: use ML_BSSN instead of BSSN_MoL in testsuites | Roland Haas | 2012-09-11 |
| | |||
* | CarpetEvolutionMask: use dd.buffer_widths instead of buffer_width parameter | Roland Haas | 2012-09-11 |
| | |||
* | CarpetLib: Remove superfluous memoryof() definitions | Erik Schnetter | 2012-09-11 |
| | | | | | Remove definitions for memoryof(T*) sinfc there is already memoryof(T const*). xlC does not like having both. | ||
* | Carpet: Run overlap zone tests on 2 processes | Erik Schnetter | 2012-09-11 |
| | |||
* | Carpet: Add test cases for overlap zones | Erik Schnetter | 2012-09-11 |
| | |||
* | Carpet…: Rename buffer2 to overlap zones; correct implementation in dh | Erik Schnetter | 2012-09-11 |
| | | | | | | Rename buffer2 zones to overlap zones. Complete implementing overlap zones in the dh class. | ||
* | CarpetLib: Remove warnings for non-aligned grid variables | Erik Schnetter | 2012-09-11 |
| | |||
* | Carpet: Correct setting core affinity | Erik Schnetter | 2012-09-11 |
| | | | | Correct upper loop bound | ||
* | CarpetRegrid2: Take buffer2 zones into account | Erik Schnetter | 2012-09-11 |
| | |||
* | Carpet: Correct condition for using buffer2 zones | Erik Schnetter | 2012-09-11 |
| | |||
* | CarpetLib: Use vectors instead of lists to store bboxset bboxes | Erik Schnetter | 2012-09-11 |
| | |||
* | Carpet, CarpetLib: Complete patch to support buffer2 zones | Erik Schnetter | 2012-09-11 |
| | |||
* | Carpet: Correct error in thread id handling | Erik Schnetter | 2012-09-11 |
| | |||
* | CarpetLib: Check whether grid functions are aligned | Erik Schnetter | 2012-09-11 |
| | | | | Check whether grid functions are aligned to multiples of a cache line. | ||
* | Add a timer around the scheduled functions barrier | Ian Hinder | 2012-09-11 |
| | |||
* | Add parameter sync_barriers to insert an MPI barrier before every sync | Ian Hinder | 2012-09-11 |
| | | | | This causes each process to wait for all the others to reach this point in the execution. This will happen anyway (for most of the processes) during the sync, and adding this barrier means that this time is not included in the sync timer. Also add a new timer to time this barrier. | ||
* | CarpetIOF5: Add example for outputting grid arrays | Erik Schnetter | 2012-09-11 |
| | |||
* | CarpetIOF5: Add time step information to grid arrays | Erik Schnetter | 2012-09-11 |
| | |||
* | Carpet: Remove debug output | Erik Schnetter | 2012-09-11 |
| | |||
* | Carpet: Set CPU affinity correctly for multiple MPI processes per host | Erik Schnetter | 2012-09-11 |
| | |||
* | CarpetIOHDF5: use version 1.6 of the HDF5 API within hdf5_recombiner | knarf | 2012-09-11 |
| | | | | | | | There are still systems with only version 1.6 installed, or broken installs of version 1.8 (Debian system packages at least up to squeeze). These systems benefit from a compiling hdf5_recombiner, while version 1.8 is not really required to be used here. | ||
* | Output XML timer tree at end of run | Ian Hinder | 2012-09-11 |
| | |||
* | Carpet: get thread number from CarpetLib's dist object | Roland Haas | 2012-09-11 |
| | |||
* | CarpetLib: store OpenMP thread number in dist object | Roland Haas | 2012-09-11 |
| | |||
* | CarpetRegrid2: Ensure that the refinement hierarchy is symmetry about the ↵ | Erik Schnetter | 2012-09-11 |
| | | | | | | origin, if desired Introduce a new parameter that tests whether the refinement hierarchy is symmetric about the origin. | ||
* | CarpetLib: Improve comment of dh data structures | Erik Schnetter | 2012-09-11 |
| | |||
* | Carpet: Time OutputGH operations | Erik Schnetter | 2012-09-11 |
| | |||
* | Carpet: Do not count ghost zones when calculating speed | Erik Schnetter | 2012-09-11 |
| | | | | When calculating the speed of a simulation, ignore ghost zones. Use two counters, one including the outer boundaries, the other excluding it. | ||
* | CarpetIOASCII: Declare function prototype | Erik Schnetter | 2012-09-11 |
| | |||
* | Make timer tree output precision and threshold configurable with parameters | Ian Hinder | 2012-09-11 |
| | |||
* | CarpetLib: output regions when not-contained error is detected in | Roland Haas | 2012-09-11 |
| | | | | restrict_3d_cc_rf2 and restrict_3d_vc_rf2 | ||
* | Carpet: make OutputGridCoordinates fully multipatch aware | Roland Haas | 2012-09-11 |
| | | | | | | | This is achieved by using domain information in domainspecs the way OutputGrids does. The key functional change was to use Multipatch_ConvertFromPhysicalBoundary (used to fill domainspecs) rather than CoordBase::ConvertFromPhysicalBoundary. | ||
* | Backed out changeset 74ddd545dbb1 | Roland Haas | 2012-09-11 |
| | | | | | I give up. I cannot get this right today. The previous patch would have allowed a thread to switch sockets which is undesirable. | ||
* | Carpet: let thread run on any core [n0,n0+num_threads) instead of binding to | Roland Haas | 2012-09-11 |
| | | | | | | | single core This is the behaviour of eg. Kraken's aprun --cc numa_node. Avoids using omp_get_thread_num(). |