提交历史

作者 SHA1 备注 提交日期
  Nathalie Furmento 4ce96baf81 src/datawizard/data_request.c: add parenthesis to enhance clarity 11 年之前
  Samuel Thibault 840af37490 push pending requests at the back of the list of pending requests, not the front 11 年之前
  Samuel Thibault 7ce4ced85d Let the CUDA driver progress while the GPU is computing 11 年之前
  Samuel Thibault 5ccb4bf6fc Silent warning 11 年之前
  Samuel Thibault 0423864961 port r11516 from 1.1: considerably reduce the amount of requests submitted at the same time. Pushing more does not seem to really improve performance, and on the contrary increases the latency of possibly urging requests 11 年之前
  Samuel Thibault f4c7eb0c8e port r11378 from 1.1: Do not allocate data on the critical path 11 年之前
  Samuel Thibault e9c70aac17 port r11376 from 1.1: Introduce rwlock_tryrdlock and trywrlock variants. Use them in the progression hooks to avoid getting stuck due to idling workers. 11 年之前
  Samuel Thibault 5f1af2ec79 port r11140 from 1.1: When prefetching, do not try too hard to lock a data handle, better do something else instead 11 年之前
  Samuel Thibault b217a5399a data_requests[i] may change, it is still fine for _starpu_handle_node_data_requests to read it unprotected 11 年之前
  Samuel Thibault e5bea6f293 port r11205 from trunk: Do not push too many data requests at the same time, CUDA would actually enter synchronous mode... 12 年之前
  Samuel Thibault edce30c7f0 port r11194 from 1.1: Also disable checking _head of renewed request lists 12 年之前
  Samuel Thibault aea35461df Document each racy spot normally reported by helgrind 12 年之前
  Samuel Thibault 0d1b0375b3 backport r11155 from 1.1: Disabling access to a variable locally does not actually seem to prevent helgrind from raising the race issues, on the contrary it prevents it from recording where the race comes from... Simply just disable checking these variables completely. 12 年之前
  Samuel Thibault 54460ab919 port r11138 from 1.1: Do not lie to helgrind about having taken a mutex, it produces erroneous races inside mutexes. Rather make helgrind ignore the precise memory accesses we know we do not need to care about 12 年之前
  Thibaud Lambert 3b7abcc2cf mic: Fix bugs 12 年之前
  Samuel Thibault 423529392d Do not let StarPU queue a request on a node which doesn't have any worker 12 年之前
  Samuel Thibault fa47d65684 Make sure we don't post disk-related requests to a disk node. This would have happened for a gpu-disk transfer. 12 年之前
  Samuel Thibault a3f27f08ad Make some warnings clearer. Avoid a very odd warning when the codelet has more parameters than allowed 12 年之前
  Nathalie Furmento 30860cac02 Renaming of diverse functions and datatypes. 12 年之前
  Nathalie Furmento 786b8fb4b7 move _STARPU_PTHREAD_XXX macros to public API starpu_thread_util and rename them to STARPU_PTHREAD_XXX 12 年之前
  Nathalie Furmento 7f792e3082 Define new public API starpu_pthread which is similar to the pthread API. 12 年之前
  Samuel Thibault d95e1c8398 explain helgrind about some races we are fine with 12 年之前
  Samuel Thibault add756f1af Note about racyness. We can't really add a suppression for this case, it would hide potential other races 12 年之前
  Samuel Thibault 55a6fa0d9e complete lock comment 12 年之前
  Samuel Thibault 38d8bb35e3 Add missing support for mpi_insert_task cases 12 年之前
  Nathalie Furmento c7321a76ff fix type for node to always be unsigned (instead of uint32_t) 12 年之前
  Nathalie Furmento b770541f52 src: memory_nodes function renaming 12 年之前
  Nathalie Furmento eb32a9b3d4 src: fix coding style 12 年之前
  Nathalie Furmento edc236df55 memory stats: group all functions in new file src/datawizard/memstats.c and rename them to follow pattern starpu_memory_... 12 年之前
  Samuel Thibault 242b6116cf pass pthread types through typedefs 12 年之前