MCPcopy Create free account

hub / github.com/InfiniTensor/InfiniTensor / functions

Functions2,429 in github.com/InfiniTensor/InfiniTensor

↓ 1,163 callersMethodsize
include/core/tensor.h:33
↓ 889 callersMethodgetOutput
include/core/operator.h:80
↓ 770 callersMethodgetDims
include/nnet/expr.h:175
↓ 749 callersMethodgetInputs
src/core/graph_match.cc:20
↓ 556 callersMethodaddTensor
src/core/graph.cc:291
↓ 473 callersMethoddataMalloc
src/core/graph.cc:158
↓ 437 callersMethodcloneTensor
* @brief Clone a tensor and add it to the graph. */
include/core/graph.h:30
↓ 414 callersMethodsetData
src/core/tensor.cc:174
↓ 411 callersMethodgetDType
src/operators/recv.cc:19
↓ 297 callersMethodrun
src/core/runtime.cc:9
↓ 274 callersMethodcopyin
include/core/tensor.h:82
↓ 201 callersMethodequalData
src/core/tensor.cc:128
↓ 201 callersFunctionmakeSubscript
Wrappers for type deduction
src/nnet/expr.cc:370
↓ 155 callersMethodget
src/nnet/permutation.cc:25
↓ 141 callersMethodgetGuid
include/core/object.h:55
↓ 135 callersMethodtensor
src/core/graph_handler.cc:51
↓ 133 callersFunctioncnnlDataTypeConvert
include/bang/bang_common.h:34
↓ 131 callersMethodclone
src/core/graph_match.cc:4
↓ 131 callersFunctionmakeRangeOperator
src/nnet/expr.cc:374
↓ 122 callersMethodprintData
src/core/tensor.cc:99
↓ 121 callersMethodunderlying
include/core/op_type.h:246
↓ 116 callersFunctioncastTo64
transform vector<int> to vector<int64_t>
src/core/common.cc:25
↓ 106 callersMethodgetRank
include/core/tensor.h:38
↓ 105 callersMethodKUNLUNHandle
include/kunlun/kunlun_runtime.h:50
↓ 105 callersMethodgetWorkspace
include/core/workspace.h:24
↓ 102 callersMethodcnnlHandle
include/bang/bang_runtime.h:51
↓ 88 callersMethodprint
src/nnet/derivator.cc:306
↓ 73 callersMethodgetStride
src/core/tensor.cc:52
↓ 69 callersMethodgetOpType
src/kernels/bang/trigon.cc:47
↓ 66 callersFunctionvecToString
include/core/common.h:65
↓ 64 callersMethodgetOutputs
src/core/graph_match.cc:29
↓ 62 callersMethodgetBytes
include/core/tensor.h:34
↓ 60 callersMethodgetEngine
include/intelcpu/mkl_runtime.h:30
↓ 52 callersMethodgetIndex
include/core/data_type.h:70
↓ 52 callersMethodreshape
src/core/graph_handler.cc:300
↓ 50 callersMethodgetSize
src/nnet/expr.cc:390
↓ 46 callersFunctionmakeTensor
Wrappers for type deduction
src/nnet/expr.cc:381
↓ 44 callersFunctionmake_and_import_model
(graph: onnx.GraphProto)
pyinfinitensor/tests/test_onnx.py:16
↓ 40 callersMethodgetShape
src/nnet/routine.cc:62
↓ 40 callersMethodgetType
include/operators/unary.h:277
↓ 35 callersMethodcount
src/nnet/Visitor/CountRoutineVisitor.cc:12
↓ 35 callersMethodgetObject
include/nnet/expr.h:353
↓ 34 callersMethodload
src/core/tensor.cc:192
↓ 33 callersMethodASCENDHandle
include/ascend/ascend_runtime.h:50
↓ 33 callersMethodgetSource
include/core/tensor_base.h:55
↓ 29 callersMethodsave
src/core/tensor.cc:194
↓ 27 callersMethodalloc
src/core/lazy_allocator.cc:61
↓ 27 callersMethodtoReadable
src/nnet/expr.cc:47
↓ 26 callersFunctiongatheredOffset2Offset
test/kernels/cuda/test_cuda_gather.cc:68
↓ 26 callersFunctionhash
src/nnet/Visitor/hashVisitor.cc:15
↓ 25 callersMethodgetNumCandidates
include/nnet/derivator.h:81
↓ 25 callersMethodgetPadStrideDilation
include/operators/conv.h:178
↓ 24 callersFunctionenum_to_underlying
include/core/common.h:61
↓ 23 callersMethodgetPerfTime
src/core/runtime.cc:62
↓ 23 callersMethodpush_node
(self, node: NodeProto)
pyinfinitensor/src/pyinfinitensor/onnx.py:1205
↓ 23 callersFunctiontimeit
src/core/common.cc:7
↓ 22 callersFunctioncompute
()
python/cpp_plugin/gen_ansor_op.py:47
↓ 22 callersMethodruleBasedDFS
src/nnet/derivator.cc:288
↓ 21 callersMethodequal
include/nnet/expr.h:137
↓ 21 callersMethodgetOpType
include/nnet/expr.h:198
↓ 21 callersMethodsearch
src/nnet/derivator.cc:300
↓ 20 callersFunction_parse_data
(tensor: TensorProto)
pyinfinitensor/src/pyinfinitensor/onnx.py:1539
↓ 20 callersMethodcudnnHandle
include/cuda/cuda_runtime.h:63
↓ 20 callersMethodgetDim
include/operators/split.h:45
↓ 20 callersMethodgetStream
include/intelcpu/mkl_runtime.h:31
↓ 20 callersMethodgetSuccessors
include/core/operator.h:89
↓ 20 callersMethodgetTargets
include/core/tensor_base.h:54
↓ 19 callersMethodgetPaddings
src/nnet/expr.cc:397
↓ 19 callersMethodgetRuntime
include/core/graph.h:22
↓ 18 callersMethodgetFuid
include/core/tensor.h:42
↓ 18 callersMethodgetValue
include/nnet/expr.h:322
↓ 18 callersMethodgetVarRange
src/nnet/expr.cc:150
↓ 18 callersMethodmatmul
src/core/graph_handler.cc:87
↓ 17 callersMethodgetAxis
include/operators/unary.h:93
↓ 17 callersMethodgetPredecessors
include/core/operator.h:88
↓ 16 callersMethoddispatch
include/nnet/visitor.h:29
↓ 16 callersMethodgetExpr
src/nnet/iterator_table.cc:530
↓ 16 callersMethodgetPadding
include/nnet/expr.h:169
↓ 15 callersMethodinitComm
src/bang/bang_runtime.cc:67
↓ 15 callersMethodrun
(self)
pyinfinitensor/src/pyinfinitensor/onnx.py:1507
↓ 15 callersMethodtranspose
src/core/graph_handler.cc:290
↓ 14 callersMethodgetChannelPerGroup
include/operators/conv.h:113
↓ 14 callersMethodgetHash
src/nnet/Visitor/hashVisitor.cc:28
↓ 14 callersMethodgetNCHWFRS
include/operators/conv.h:111
↓ 14 callersMethodprintStatistics
src/nnet/derivator.cc:464
↓ 14 callersMethodsimplify
src/nnet/Visitor/SimplifyExprVisitor.cc:51
↓ 13 callersMethodaddSubGraph
"inputs" must be tensors in original graph
src/core/graph_match.cc:378
↓ 13 callersMethodgetOutputShape
src/nnet/expr.cc:442
↓ 13 callersMethodnumInputs
include/operators/lrn.h:15
↓ 13 callersMethodresize
src/core/graph_handler.cc:311
↓ 13 callersMethodrun
src/nnet/nmutator.cc:27
↓ 12 callersMethodgetOpPerfKey
src/core/operator.cc:41
↓ 12 callersFunctionget_real_axis
src/utils/operator_utils.cc:34
↓ 12 callersFunctionmatchExprResult
src/nnet/test.cc:27
↓ 12 callersFunctionsize
include/nnet/dbg.h:284
↓ 11 callersFunction_parse_attribute
(node: NodeProto, attrs: Dict[str, Any] = dict())
pyinfinitensor/src/pyinfinitensor/onnx.py:1522
↓ 11 callersMethodfindMatch
src/core/graph_match.cc:75
↓ 11 callersFunctionfrom_onnx
(model: ModelProto, runtime)
pyinfinitensor/src/pyinfinitensor/onnx.py:1517
↓ 11 callersMethodgetAct
include/operators/GBMM.h:43
↓ 11 callersMethodgetEps
include/operators/batch_norm.h:44
next →1–100 of 2,429, ranked by callers