AOE工具当前版本仅支持使用DSL接口实现计算逻辑的AI Core算子的自动调优，本章节介绍支持的算子列表。
- Abs
- AccumulateNV2
- Add
- AddN
- Adds
- BatchNorm3D
- BiasAdd
- BiasAddGrad
- BNInfer
- BNTrainingReduce
- BNTrainingReduceGrad
- BNTrainingUpdate
- BNTrainingUpdateGrad
- BNTrainingUpdateV2
- BNTrainingUpdateV3（仅Atlas 200/300/500 推理产品支持）
- ClipByNormNoDivSum
- ClipByValue
- DiagPartD
- Div
- DivNoNan
- DynamicRNN
- Elu
- EluGrad
- Exp
- ExpandD
- Floor
- FloorDiv
- Gelu
- InstanceNorm
- L2Loss
- LambUpdateWithLrV2
- LayerNormBetaGammaBackpropV2（仅Atlas 200/300/500 推理产品支持）
- LeakyRelu
- Log
- Log1p
- LpNorm（仅Atlas 200/300/500 推理产品支持）
- Maximum
- MaxPool
- MaxPool3D
- MaxPoolV3
- Minimum
- Mul
- Muls
- Neg
- Pow
- PRelu
- RealDiv
- ReduceAllD
- ReduceMaxD
- ReduceMeanD
- ReduceMinD
- ReduceSumD
- Relu
- ReluV2
- Round
- Rsqrt
- RsqrtGrad
- Sigmoid
- Sign
- SoftmaxCrossEntropyWithLogits
- Softplus
- SplitVD（仅Atlas 200/300/500 推理产品支持）
- SqrtGrad
- Square
- SquaredDifference
- SquareSumV1
- SquareSumV2
- StridedSliceD
- Sub
- Tanh
- TileD
- Unpack
- ReluGradV2
- AvgPool
- AvgPoolV2
- AvgPool3D
- BatchMatMulV3
- Deconvolution
- Conv1D
- Conv2D
- Conv2DCompress
- Conv2DBackpropInput
- Conv2DBackpropFilter
- DeformableConv2D
- GEMM
- MatMul
- MatMulV2
- MatMulV3
- MatMulV2Compress
- BatchMatMul
- BatchMatMulV2
- FullyConnection
- FullyConnectionCompress
- DepthwiseConv2D
- DepthwiseConv2DBackpropInput
- DepthwiseConv2DBackpropFilter
- Conv3D
- Conv3DBackpropInput
- Conv3DBackpropFilter
- AvgPool3DGrad
- Pooling
- Conv2DTranspose
- Conv3DTranspose
- GatherV2（仅支持Atlas 推理系列产品（Ascend 310P处理器）和Atlas 训练系列产品）
