История коммитов

Автор SHA1 Сообщение Дата
  Nathalie Furmento e2675531f5 mpi: fix for receiving early several datas (and not only one) лет назад: 12
  Nathalie Furmento 31753c0497 mpi/src/starpu_mpi.c: use the tag which is defined for the communication, and not the tag of the data (as they may be different) лет назад: 12
  Samuel Thibault 5c113f4053 While unpartitioning, do not acquire the child data when they are not in redux mode. Otherwise we would not be able to unpartition a data in a callback лет назад: 12
  Samuel Thibault ce1dc108c3 make sure the buffer we are dropping does not contain data лет назад: 12
  Samuel Thibault 2c4d2a6c7e Fix releasing buffers of partitioned data used with reduction лет назад: 12
  Nathalie Furmento b78f57263a mpi/src/starpu_mpi.c: improve debug and error messages лет назад: 12
  Nathalie Furmento d889f9df2d mpi/tests/gather.c: use same tag for all the nodes, and skip test if лет назад: 12
  Nathalie Furmento f3288d4dda Changelog: mention MPI fixes лет назад: 12
  Nathalie Furmento 4e5b001319 mpi: fix for being able to receive a data with the same tag from лет назад: 12
  Nathalie Furmento 90f8e97cde mpi/tests/gather.c: skip test when less than 3 nodes лет назад: 12
  Samuel Thibault 77b58f8dd8 Fix memory leak лет назад: 12
  Nathalie Furmento 1071eb99e2 mpi/tests/mpi_reduction.c: initialize memory лет назад: 12
  Nathalie Furmento 59353eccf8 src/core/perfmodel/perfmodel_bus.c: free hwloc bitmap лет назад: 12
  Nathalie Furmento 133ee36825 src/datawizard/interfaces/data_interface.c: improve error message лет назад: 12
  Samuel Thibault e2b16b3138 Avoid getting build failures just because of automake warnings лет назад: 12
  Samuel Thibault e3625c944d make starpu_data_unpartition acquire the child pieces, otherwise we may not have collapsed the reduction лет назад: 12
  Samuel Thibault b5e6986273 fix protecting access to worker_exp_end with the sched mutex лет назад: 12
  Samuel Thibault 41dee18d0c fix protecting post_sync_tasks_cnt with sequential_consistency_mutex. But no need to take the mutex when it is known to be 0, just tell hellgrind to be fine with it лет назад: 12
  Samuel Thibault 242066fe76 Tell hellgrind about header spinlock vs busy_mutex in the same order as in _starpu_data_check_not_busy лет назад: 12
  Nathalie Furmento 2c71c896d0 mpi: test functionality provided in previous commit лет назад: 12
  Nathalie Furmento 29bb94205b mpi/src: fix when receiving too early data which have not yet been registered, the data is received as as a raw memory, and will be given it to the application when it post a equivalent receive лет назад: 12
  Nathalie Furmento c8be1347be mpi/src: properly set the size of the data in the envelope лет назад: 12
  Nathalie Furmento 73d80820ab mpi/src: rename variables to have a more appropriate name лет назад: 12
  Andra Hugo 9502f53f25 introduce min max as a constraint for the linear program лет назад: 12
  Nathalie Furmento 2d5990eadd tests/disk/disk_copy.c: decrease vector size on 32 bits machine лет назад: 12
  Pierre-André Wacrenier 9c421fc50e unlock worker's sched_mutex before busy waiting лет назад: 12
  Nathalie Furmento 8b523baf9c examples/Makefile.am: only check sched_ctx/parallel_code when long-check is enabled лет назад: 12
  Nathalie Furmento de463ed920 doc/doxygen/Makefile.am: use different files for latex and html version to avoid problems лет назад: 12
  Nathalie Furmento c6044cd5fe ChangeLog: mention fix for nan on windows лет назад: 12
  Andra Hugo 3e4395d0ba configurable time sample лет назад: 12