154 Commits (b2cff2842ded2e1df5669052d7edbb9ea505068e)

Author SHA1 Message Date
  mindspore-ci-bot 8c7444ab47 !5140 add cuda path checker 5 years ago
  lizhenyu 551879240c add cuda path checker 5 years ago
  lizhenyu 5d6f7204d3 [bugfix]LSTM SyncDeviceToHost failed 5 years ago
  mindspore-ci-bot 0f69259abf !5035 clean static check 5 years ago
  zhoufeng 99a94bfd01 clean static check 5 years ago
  mindspore-ci-bot 80e9606a19 !5020 revert parameter set 5 years ago
  gukecai 6c22c8a09d parallel ctrl 5 years ago
  WilliamLian d4536eef14 revert paremter device dtype set 5 years ago
  mindspore-ci-bot 73c4022ef4 !3775 remove the dtype convert when update output 5 years ago
  lizhenyu 1becddf3a4 [bugfix]SyncDeviceToHost failed when device address size is zero 5 years ago
  mindspore-ci-bot a245ee665e !4934 fix nccl kernel memory align bug 5 years ago
  lizhenyu fcaf86f5d9 fix nccl kernel memory align bug 5 years ago
  qianlong 113619f1ca Revert "Add Size() and Capacity() in gpu queue." 5 years ago
  WilliamLian 601b0b6e4d remove convert datatype when updateoutputs && 5 years ago
  mindspore-ci-bot b69b1ca8a8 !4830 [gpu] fix continuous allreduces bug 5 years ago
  mindspore-ci-bot d04d58fd21 !4472 Add API to query GPU queue size and capacity 5 years ago
  anthonyaje e2b346d5af Add Size() and Capacity() in gpu queue. 5 years ago
  mindspore-ci-bot bfa3cd900e !4843 remove ccsrc/common.h by explicit dependent header file 5 years ago
  lizhenyu 839ec02542 Add FusedBatchEx support 5 years ago
  zhousiyi d0e58dd765 remove ccsrc/common.h 5 years ago
  limingqi107 5b76e8f3d7 gpu add format transform pass 5 years ago
  yuchaojie 61bf4b18a2 fix_consecutive_allreduce_bug 5 years ago
  mindspore-ci-bot 5686315199 !4557 change profiling log level 5 years ago
  mindspore-ci-bot e2a63790bd !4731 genmask parallel and fix iter num 5 years ago
  mindspore-ci-bot 55bd09c689 !4684 add log for gpu profiler 5 years ago
  gukecai 66e7b02b4b independent stream parallel 5 years ago
  askmiao 5a817d7444 add log and modify log level for gpu profiler 5 years ago
  caifubi 6eba89b1bc fix profiling log bug 5 years ago
  mindspore-ci-bot 58523a41fe !4392 use builtin float16 for arm 5 years ago
  mindspore-ci-bot 8f6ed032e5 !4428 Operation Overflow Watchpoint for D-Chip debugger 5 years ago
  mindspore-ci-bot 1ca715c7e7 !4656 fix redundancy print 5 years ago
  jjfeing 16e67ff143 fix redundancy print 5 years ago
  zhoufeng 663278112f optimize code compile performance 5 years ago
  mindspore-ci-bot 5f3e7aa6b1 !4652 block transdata to change format for now 5 years ago
  lvchangquan 0b63a1ffe4 block transdata to change format for now. 5 years ago
  mindspore-ci-bot 3fb58fcbe4 !4585 add gpu nccl broadcast 5 years ago
  mindspore-ci-bot 19192e75e3 !4609 change unsupport to unsupported 5 years ago
  Adel Shafiei 4834a3378b Op Overflow Watchpoint support for D-chip debugger 5 years ago
  chenzomi bb125cb309 change unsupport to unsupported 5 years ago
  gukecai 6362e954df Revert "independent stream parallel" 5 years ago
  baihuawei b9ebd9c280 add gpu nccl broadcast 5 years ago
  zhousiyi e1aa49a4b7 use built-in float16 in arm_neon.h for lite arm 5 years ago
  mindspore-ci-bot 9f635e52c7 !4463 change some wrong log about static memory 5 years ago
  liangzelang 1608c4d096 change-static-memory-size-log 5 years ago
  mindspore-ci-bot b48c1f45f0 !4236 fix gpu heterogeneous bug 5 years ago
  baihuawei 517fcc16ee fix gpu heterogeneous 5 years ago
  mindspore-ci-bot 21014fd624 !4235 add gpu profiler feature 5 years ago
  mindspore-ci-bot 15c533d481 !4277 Profiling Support Multi Graph 5 years ago
  askmiao 25cae1a2e7 add profiler featrue 5 years ago
  gukecai adb6ff6c78 independent stream parallel 5 years ago