Историја ревизија

Аутор SHA1 Порука Датум
  Samuel Thibault e71124580f shut up warning пре 8 година
  Samuel Thibault 91f985c664 Do not bother telling _starpu_post_data_request which node is handler for the request, it can determine it by itself from the request, and it is actually more right when the request is an invalidation, for which the handler is undetermined (-1) пре 8 година
  Corentin Salingue cc4eb6b654 fix indent пре 8 година
  Samuel Thibault 0ae8f154db fix warning пре 8 година
  Corentin Salingue 087b676559 add MPI slave to MPI slave sync transfers пре 8 година
  Corentin Salingue 0dbf966aef Merge from trunk пре 8 година
  Corentin Salingue f7acc7fe76 * fix bug in async mode when using MPI Master-Slave пре 8 година
  Corentin Salingue 3bbc1443c4 Each worker can manage the good set of memories пре 8 година
  Nathalie Furmento ea326f4d15 src: add character in front of macros STARPU_MALLOC, STARPU_CALLOC and STARPU_REALLOC пре 8 година
  Nathalie Furmento d4761fddf6 src: introduce macros STARPU_MALLOC, STARPU_CALLOC and STARPU_REALLOC to make sure we always check the return value of stdlib malloc functions пре 8 година
  Samuel Thibault b643914328 fix warnings пре 8 година
  Samuel Thibault c0b04e4d0d Fix and test the case where we try to invalidate a data which has some transfers pending. Also make sure that eviction doesn't evict a data being invalidated пре 8 година
  Samuel Thibault 0b5135e60e re-apply r18403 again, we'll be using maxmin/precision simgrid parameter to coarsen the time пре 8 година
  Samuel Thibault 514f24d352 revert r18403 for now, it seems to increase starpu-mpi-simgrid execution time a lot пре 9 година
  Samuel Thibault 4fb4ce92aa Reduce the granularity of simulation of CUDA and MPI probes, it is not that expensive. пре 9 година
  Samuel Thibault 6bd3bb1b96 revert spurious change пре 9 година
  Samuel Thibault 8bb9a66912 Fix data migration: we need to flush the cache too. Add starpu_mpi_data_migrate which does things properly пре 9 година
  Samuel Thibault 1f841a3f0d Add origin of data requests for debugging пре 9 година
  Samuel Thibault 38097a0048 fix spurious trace event пре 9 година
  Samuel Thibault b75b95b108 fix printing data requests in gdb пре 9 година
  Samuel Thibault a5f7d96fea Add rbtree and rbtree+list implementation. Use it to introduce priorities in data requests, which default to the task priority or workerorder пре 9 година
  Samuel Thibault e56836b055 Keep fetches and prefetches in the submission order even when upgrading пре 9 година
  Samuel Thibault 0e92653f70 Add _list_member and _list_ismember helpers, and use them пре 9 година
  Samuel Thibault ecc274e4c0 Distinguish between fetches, prefetches and idle fetches in the paje trace пре 9 година
  Samuel Thibault 90bf39960e Vastly improve simgrid simulation time by using wake queues пре 9 година
  Samuel Thibault 23b5457f92 port r16114 from 1.2: Make non-cpu drivers also process main_ram requests so write_invalidation requests can work in non-cpu case. Those drivers can run them anyway, and this is actually required for the disk+gpu case. пре 9 година
  Samuel Thibault cef92ef39b Catch bogus handling_node early пре 9 година
  Samuel Thibault 91fd2cfc15 Fix mem_reclaim: on write request, if some requests are pending (notably reclaiming), create an additional write request which will wait for them before invalidating all copies пре 9 година
  Samuel Thibault d06eb3bbd4 Make reclaiming prevent more fetches on the node being cleaned up, to avoid permanent battle between them пре 10 година
  Samuel Thibault 93e54d53ad Fix safety of _starpu_wait_data_request_completion: starpu_data_request_destroy was supposed to be called with the handle lock held. Move that part of starpu_data_request_destroy to _starpu_data_request_unlink, which can then be called directly from _starpu_wait_data_request_completion, avoiding races between unregistering the handle and _starpu_wait_data_request_completion пре 10 година