21 Commits (269b514b0590e89652ab768fc8df8c5594a1c19a)

Author SHA1 Message Date
  limingqi107 0f4397cece fix all nop node graph execute 5 years ago
  mindspore-ci-bot 4642df207a !2210 gpu optimize the max device memory config 5 years ago
  limingqi107 55b3557c0d gpu optimize the max device memory config 5 years ago
  limingqi107 20083679a0 gpu memreuse supports summary node 5 years ago
  limingqi107 da2b93916e gpu device code review 5 years ago
  lizhenyu 0a55ebf6e9 fix code review defects 5 years ago
  lizhenyu fa4d9b2846 fix resource release bug of memory swap 5 years ago
  lizhenyu 23a57476da change gpu kernel runtime to support memory swap 5 years ago
  caifubi 5b963aef2b Change uintptr_t to void ptr 5 years ago
  limingqi107 d9197b591a gpu optimize the use of reference count 5 years ago
  limingqi107 63f3a2caac gpu optimize some return values of dynamic memory pool 5 years ago
  lizhenyu 3a4c28fa33 change directory of akg cuda kernel 5 years ago
  limingqi107 664f2628e5 optimize gpu allReduce alloc memory performance 5 years ago
  limingqi107 0f0e8fe874 gpu dynamic memory pool can not reuse allReduce in multi-stream 5 years ago
  limingqi107 2891f0d20d gpu dynamic memory pool supports multi-allReduce 5 years ago
  limingqi107 5e01b94ccd gpu dynamic memory pool suppoerts multi-graph 5 years ago
  limingqi107 99f12f9105 gpu uses dynamic memory pool by default 5 years ago
  kswang b8a7e73f7d fix reshape output and clearres error 5 years ago
  kswang bef62db128 add ascend mem pool 6 years ago
  kswang fb343bd607 add mem manager 6 years ago
  zhunaipan 930a1fb0a8 initial version 6 years ago