97 Commits (062dcaaaa17664f4be6fb191d97f85c19eec8840)

Author SHA1 Message Date
  Zichun Ye a7d89f6686 add graph kernel userdefine op support 4 years ago
  tronzhang 134ffa9efe support tot ops 4 years ago
  ms_yan 36a8886ca2 Revert "[feat] [assistant] [I3T96T] add new Dataset operator CMUARCTICDataset" 4 years ago
  djc 4e6f7dc97d [feat] [assistant] [I3T96X] add new Dataset operator LibriSpeechDataset 4 years ago
  dayschan fff39e7451 fix static check problems 4 years ago
  i-robot a5388a5227 !21621 fix recompute_fuse 4 years ago
  zengzitao b8095efcab gk fix warnings in master 4 years ago
  lingyunli63 5ea00fbabc fix find_cheap_ops 4 years ago
  chenlei_autodiff 0271535429 [GraphKernel] fix bert and add graph kernel ops. 4 years ago
  Zichun Ye 22172f18bc update graph kernel support for argmax/argmin 4 years ago
  tronzhang 94dda0c7c7 speed up bert profermance in ascend for graph kernel 4 years ago
  i-robot ab78bcf16f !19081 add ops IsNan 4 years ago
  Yang Jiao 582669e41c add expander checkings 4 years ago
  lingyunli63 50a66ae476 isnan isfinite isinf squaresumall identity oneslik 4 years ago
  i-robot e7b8cf2961 !20508 consider case that graph has no tensor input 4 years ago
  yanglf1121 c30b1e6d06 add graph kernel div, floordiv, mod, floormod, floor 4 years ago
  lingyunli63 32571f5a0c consider no tensor input in graph 4 years ago
  wangrao124 7cddde47b0 !215 add ops: LogicalNot, LogicalAnd, LogicalOr, NotEqual, EqualCount, Asinh, Acosh 4 years ago
  huangmengxi 1bd448ef2a add atan, atan2, expm1 4 years ago
  chenlei_autodiff 7d55cef106 [GraphKernel] add sponge ops. 4 years ago
  zengzitao aa019a639f support complex in gpu about graph_kernel 4 years ago
  lingyunli63 3679e99fe8 fix recompute_fuse with reshape user 4 years ago
  lingyunli63 a995bea507 recompute_fuse 4 years ago
  zengzitao 8064de7931 fix maximum_grad and minimum_grad input_shape not equal to output_shape bug 4 years ago
  i-robot 07f58b0b46 !17626 matmul to mul 4 years ago
  lingyunli63 4f34e537a0 replace matmul/batchmatmul by mul when k is 1 4 years ago
  Yang Jiao d9a60e0d28 fix static warnings 4 years ago
  Gaoxiong 1d3da1789e Acyclic checking bugfix of split model 4 years ago
  looop5 68f55e1e93 expand conv2d when input format is DefaultFormat but attr format is NHWC 4 years ago
  looop5 dd81f47271 add conv2d expander 4 years ago
  mindspore-ci-bot f91a365564 !16322 [GraphKernel] Enable matmul for gpu 4 years ago
  lingyunli63 afc69b16f7 enable gpu gk MatMul and insert pad/unpad 5 years ago
  chenlei_autodiff e0f882b5ce [GraphKernel] fix op infer for elementwise. 4 years ago
  dayschan 54a0edb837 Limit the cluster size in costmodel 4 years ago
  mindspore-ci-bot f247cc2db7 !16047 [GraphKernel]adapt batchmatmul for GraphKernel in ascend 4 years ago
  mindspore-ci-bot c492d784bf !16104 [GraphKernel] add stitch fusion test case in CI 4 years ago
  wenfangpei 2e2e850b4a adapt batchmatmul for GraphKernel in ascend 4 years ago
  r1chardf1d0 b1be842d2b add stitch fusion case in ci 4 years ago
  hanhuifeng2020 bc46d644fe [GraphKernel]Support reshape/elewise/broadcast+transdata fusion 4 years ago
  mindspore-ci-bot 0887d35b1c !15951 [GraphKernel]add the attribute reduce_output_fuse to enable fuse for the reduce_output on Ascend 4 years ago
  mindspore-ci-bot 1827697642 !15961 Eliminate recursion call in split model 4 years ago
  wenfangpei c41875b318 adapt expanders of some ops from gpu to ascend 4 years ago
  Gaoxiong 4bc67f38de eliminate recursion call 4 years ago
  hanhuifeng2020 425d401e85 [GraphKernel]add the attr reduce_output_fuse to enable fuse for reduce_output on Ascend 4 years ago
  mindspore-ci-bot d6f58cb765 !15658 Reduce recursion overhead of split model 4 years ago
  Gaoxiong 71002ed19d reduce recursion overhead of split model 4 years ago
  zengzitao 8dcff8d83c refactor tile op and in expander open on gpu 4 years ago
  r1chardf1d0 5c5d125b1d optimize stitch fusion strategy 5 years ago
  hanhuifeng2020 25505642ce enable GraphKernel for TransData 5 years ago
  lingyunli63 c48c2430f0 fuse matmul and elementwise in graphkernel 5 years ago