- Generated by
1.9.3
|
Poplar and PopLibs
|
| ▼ include | |
| ► gcl | |
| CollectiveBalancedReorder.hpp | |
| Collectives.hpp | |
| TileAllocation.hpp | |
| ► intrinsics | |
| ipu_intrinsics | Functions that target single IPU instructions |
| ipu_memory_intrinsics | Functions that target IPU memory instructions |
| ipu_vector_math | IPU vector math functions |
| ► popfloat | |
| ► experimental | |
| CastToGfloat.hpp | |
| CastToHalf.hpp | |
| codelets.hpp | |
| GfloatExpr.hpp | |
| GfloatExprUtil.hpp | |
| ► poplar | |
| ArrayRef.hpp | References to arrays |
| CallbackTraits.hpp | |
| CodeletFileType.hpp | |
| CSRFunctions.hpp | |
| CycleCount.hpp | |
| DataStream.hpp | |
| DataStreamType.hpp | |
| DebugContext.hpp | |
| Device.hpp | |
| DeviceManager.hpp | |
| Engine.hpp | |
| EngineOptions.hpp | |
| Error.hpp | |
| exceptions.hpp | |
| Executable.hpp | |
| FunctionBufferMappingType.hpp | |
| GlobalExchangeConstraints.hpp | |
| Graph.hpp | |
| GraphElements.hpp | |
| HostFunctionCallback.hpp | |
| Interval.hpp | |
| IpuLinkConfiguration.hpp | |
| IpuLinkTopology.hpp | |
| IPUModel.hpp | |
| LateInitCallback.hpp | |
| Module.hpp | |
| OptionFlags.hpp | |
| PerfEstimateFunc.hpp | |
| Preallocations.hpp | |
| ProfileValue.hpp | |
| Program.hpp | |
| Quarter.hpp | |
| RandomSeed.hpp | |
| ReplicatedStreamMode.hpp | |
| replication_factor.hpp | |
| RuntimeOptions.hpp | |
| SerializationFormat.hpp | |
| SSOPointer.hpp | |
| StreamCallback.hpp | |
| StringRef.hpp | |
| SyncType.hpp | |
| Target.hpp | |
| TargetType.hpp | |
| Tensor.hpp | |
| TensorCloneMethod.hpp | |
| TensorRearranger.hpp | |
| Type.hpp | |
| TypeConversion.hpp | |
| TypeTraits.hpp | |
| VariableMappingMethod.hpp | |
| VariableRef.hpp | |
| VectorLayout.hpp | |
| VertexIntrospector.hpp | |
| ► poplin | |
| Cholesky.hpp | Factorise a positive definite matrix using Cholesky decomposition |
| codelets.hpp | |
| Convolution.hpp | Functions and data types to support performing convolutions |
| ConvParams.hpp | Data types for convolution parameters |
| ConvPreplan.hpp | Functions and data types to support performing convolution preplanning |
| ConvUtil.hpp | A collection of utility functions to assist calculation of input/output ranges when moving a 2-dimensional kernel over a larger 2-dimensional space (for example in convolution or pooling layers) |
| FullyConnected.hpp | Functions and data types to for performing operations on fully-connected layers |
| MatMul.hpp | Functions and data types for performing matrix multiplies on the IPU |
| MeshGrid.hpp | Functions to populate arrays with linear sequences of values |
| MultiConvolution.hpp | Support performing convolutions in parallel |
| Norms.hpp | Functions to support normalising values in a tensor |
| TriangularSolve.hpp | Solving linear equations using triangular matrices |
| ► popnn | |
| ► experimental | |
| ROIAlign.hpp | |
| BatchNorm.hpp | Batch normalization operations |
| codelets.hpp | |
| CTCInference.hpp | Support for Connectionist Temporal Classification (CTC) Beam search decoder |
| CTCLoss.hpp | Support for Connectionist Temporal Classification (CTC) Loss |
| CTCPlan.hpp | Support for planning Connectionist Temporal Classification (CTC) Operations |
| GroupNorm.hpp | Group normalization operations |
| Gru.hpp | Support for gated recurrent units |
| GruDef.hpp | Definitions for GRU cell operations |
| InstanceNorm.hpp | Instance normalization operations |
| LayerNorm.hpp | Layer normalisation operations |
| LogSoftmax.hpp | Log of softmax functions |
| Loss.hpp | Loss and gradient calculations |
| Lstm.hpp | Support for Long short-term memory cells |
| LstmDef.hpp | Definitions for LSTM cell operations |
| NonLinearity.hpp | Non-linearity operations |
| NonLinearityDef.hpp | Definitions for non-linearity operations |
| NonLinearityDefUtil.hpp | Definitions for non-linearity operations |
| Norms.hpp | Normalisation operations |
| Pooling.hpp | Support for pooling operations |
| PoolingDef.hpp | Definitions for pooling operations |
| Recurrent.hpp | Functions for recurrent neural networks (RNN) |
| Rnn.hpp | Functions for recurrent neural networks (RNN) |
| SpatialSoftMax.hpp | Functions for spatial softmax |
| ► popops | |
| AllTrue.hpp | Perform logical AND of tensor elements |
| Cast.hpp | Casts between tensor types |
| CircBuf.hpp | Circular buffer support |
| codelets.hpp | |
| DynamicSlice.hpp | Support for dynamic slices |
| ElementWise.hpp | These functions perform the same operation on each element of one or more tensors |
| ElementWiseUtil.hpp | Supporting functions for element-wise operations |
| Encoding.hpp | Encoding and generating ranges of integers |
| EncodingConstants.hpp | Constants used by encoding functions |
| Expr.hpp | Expressions with elements of tensors |
| ExprOp.hpp | Operators used in expressions with elements of tensors |
| ExprOpUtils.hpp | |
| Fill.hpp | Functions to fill tensors with values |
| Gather.hpp | Support for gather operations |
| GatherStatistics.hpp | Functions to generate histograms of data |
| HostSliceTensor.hpp | Create tensor layouts that are optimised for host transfers |
| Loop.hpp | Functions to provide counted loops of programs |
| NaN.hpp | Test for NaN values in a tensor |
| NormaliseImage.hpp | Functions for padding and normalising image tensors |
| Operation.hpp | Read/write types of operations used in a reduce |
| OperationDef.hpp | Define types of operations used in Reduce/MultiUpdate |
| OperationDefUtil.hpp | Utilities for Operation types |
| Pad.hpp | Functions for padding a tensor |
| PerformanceEstimation.hpp | This file is for internal use only and should not be used |
| Rearrange.hpp | Operations to rearrange tensors on tiles |
| Reduce.hpp | Define types of operations used in a reduce |
| ScaledAdd.hpp | Functions for scaling and adding tensors |
| Scatter.hpp | Scatter operations |
| SelectScalarFromRows.hpp | Select values from rows of a tensor |
| SequenceSlice.hpp | Support for dynamic slices |
| Sort.hpp | Functions for sorting tensors |
| SortOrder.hpp | Defintions of sort ordering |
| TopK.hpp | Functions for finding the top k elements |
| UpdateScalarInRows.hpp | Functions for updating values in tensors |
| Zero.hpp | Set elements of tensor to zero |
| ► poprand | |
| codelets.hpp | |
| RandomGen.hpp | Functions for random number generation and applying random functions to tensors |
| ► popsparse | |
| ► experimental | |
| BlockSparse.hpp | Block sparse operations |
| BlockSparseMatMul.hpp | Block sparse matrix multiply |
| codelets.hpp | |
| Embedding.hpp | Functions for slicing and mapping sparse tensors |
| FullyConnected.hpp | Fully-connected layers using sparse tensors |
| FullyConnectedParams.hpp | Parameters used for fully-connected layers using sparse tensors |
| MatMul.hpp | Sparse matrix multiply operations |
| MatMulParams.hpp | Definitions for sparse matrix multiply operations |
| PlanningCache.hpp | Caching of plans for dynamically sparse operations |
| SparsePartitioner.hpp | Translation and encoding of sparsity information for a fully connected layer |
| SparseStorageFormats.hpp | Storage formats for a block sparse matrix |
| SparseTensor.hpp | Basic representation of a sparse tensor |
| SparsityParams.hpp | Parameters used for sparse tensors |
| ► poputil | |
| Broadcast.hpp | Functions to provide numpy-like tensor matching and broadcasting |
| cyclesTables.hpp | This file is for internal use only and should not be used |
| DebugInfo.hpp | Poplibs generic debug info structure |
| exceptions.hpp | Define a PopLibs exception |
| GraphFunction.hpp | Definitions for reusing graph structures |
| OptionParsing.hpp | OptionSpec and OptionHandler used to build up a specification of what options and their values should be, and to translate the value strings to real values |
| TensorMetaData.hpp | Class to allow extra data to be associated with a tensor |
| TileMapping.hpp | Functions for handling the mapping of tensors to tiles |
| Util.hpp | General operations on tensors |
| VarStructure.hpp | Manage partitioning and grouping in tensors |
| VertexTemplates.hpp | Generate a string describing a vertex type |
| ► pva | |
| analysis.h | |
| ► runtime | |
| Alignment.hpp | |
| AvailableVTypes.h | |
| Checking.hpp | |
| FieldTypes.hpp | |
| FieldTypeTraits.hpp | |
| HalfFloat.hpp | |
| IeeeHalf.hpp | |
| InOutTypes.hpp | |
| Iterators.hpp | |
| Loops.hpp | |
| QuarterFloat.hpp | |
| StackSizeDefs.hpp | |
| TileConstants.hpp | |
| VectorListTypes.hpp | |
| VectorTypes.hpp | |
| Vertex.hpp |
1.9.3