IVGCVSW-3890 Add NEON INSTANCE_NORMALIZATION Workload

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ia3e55da6e6a7b9d46544466897e3b1635c90c297

1 files changed, 93 insertions, 90 deletions

diff --git a/src/backends/neon/NeonWorkloadFactory.hpp b/src/backends/neon/NeonWorkloadFactory.hpp
index aad9cf949d..9546164d36 100644
--- a/src/backends/neon/NeonWorkloadFactory.hpp
+++ b/src/backends/neon/NeonWorkloadFactory.hpp
@@ -39,43 +39,42 @@ public:
                                                       DataLayout dataLayout,
                                                       const bool IsMemoryManaged = true) const override;
 
-    std::unique_ptr<IWorkload> CreateInput(const InputQueueDescriptor& descriptor,
-                                           const WorkloadInfo& info) const override;
-
-    std::unique_ptr<IWorkload> CreateOutput(const OutputQueueDescriptor& descriptor,
-                                            const WorkloadInfo& info) const override;
-
     std::unique_ptr<IWorkload> CreateAbs(const AbsQueueDescriptor& descriptor,
                                          const WorkloadInfo& info) const override;
 
     std::unique_ptr<IWorkload> CreateActivation(const ActivationQueueDescriptor& descriptor,
                                                 const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateSoftmax(const SoftmaxQueueDescriptor& descriptor,
-                                             const WorkloadInfo& info) const override;
-
-    std::unique_ptr<IWorkload> CreateSplitter(const SplitterQueueDescriptor& descriptor,
+    std::unique_ptr<IWorkload> CreateAddition(const AdditionQueueDescriptor& descriptor,
                                               const WorkloadInfo& info) const override;
 
-    ARMNN_DEPRECATED_MSG("Use CreateConcat instead")
-    std::unique_ptr<IWorkload> CreateMerger(const MergerQueueDescriptor& descriptor,
-                                            const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateArgMinMax(const ArgMinMaxQueueDescriptor& descriptor,
+                                               const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateFullyConnected(const FullyConnectedQueueDescriptor& descriptor,
-                                                    const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateBatchNormalization(const BatchNormalizationQueueDescriptor& descriptor,
+                                                        const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreatePermute(const PermuteQueueDescriptor& descriptor,
-                                             const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateBatchToSpaceNd(const BatchToSpaceNdQueueDescriptor& descriptor,
+                                                    const WorkloadInfo& Info) const override;
 
-    std::unique_ptr<IWorkload> CreatePooling2d(const Pooling2dQueueDescriptor& descriptor,
-                                               const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateConcat(const ConcatQueueDescriptor& descriptor,
+                                            const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreatePrelu(const PreluQueueDescriptor& descriptor,
-                                           const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateConstant(const ConstantQueueDescriptor& descriptor,
+                                              const WorkloadInfo& info) const override;
+
+    std::unique_ptr<IWorkload> CreateConvertFp16ToFp32(const ConvertFp16ToFp32QueueDescriptor& descriptor,
+                                                       const WorkloadInfo& info) const override;
+
+    std::unique_ptr<IWorkload> CreateConvertFp32ToFp16(const ConvertFp32ToFp16QueueDescriptor& descriptor,
+                                                       const WorkloadInfo& info) const override;
 
     std::unique_ptr<IWorkload> CreateConvolution2d(const Convolution2dQueueDescriptor& descriptor,
                                                    const WorkloadInfo& info) const override;
 
+    std::unique_ptr<IWorkload> CreateDebug(const DebugQueueDescriptor& descriptor,
+                                           const WorkloadInfo& info) const override;
+
     std::unique_ptr<IWorkload> CreateDepthToSpace(const DepthToSpaceQueueDescriptor& descriptor,
                                                   const WorkloadInfo& info) const override;
 
@@ -88,120 +87,124 @@ public:
     std::unique_ptr<IWorkload> CreateDetectionPostProcess(const DetectionPostProcessQueueDescriptor& descriptor,
                                                           const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateNormalization(const NormalizationQueueDescriptor& descriptor,
-                                                   const WorkloadInfo& info) const override;
-
-    std::unique_ptr<IWorkload> CreateMultiplication(const MultiplicationQueueDescriptor& descriptor,
-                                                    const WorkloadInfo& info) const override;
-
-    std::unique_ptr<IWorkload> CreateAddition(const AdditionQueueDescriptor& descriptor,
+    std::unique_ptr<IWorkload> CreateDivision(const DivisionQueueDescriptor& descriptor,
                                               const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateBatchNormalization(const BatchNormalizationQueueDescriptor& descriptor,
-                                                        const WorkloadInfo& info) const override;
-
-    std::unique_ptr<IWorkload> CreateMemCopy(const MemCopyQueueDescriptor& descriptor,
-                                             const WorkloadInfo& info) const override;
-
-    std::unique_ptr<IWorkload> CreateMemImport(const MemImportQueueDescriptor& descriptor,
-                                               const WorkloadInfo& info) const override;
-
-    std::unique_ptr<IWorkload> CreateResize(const ResizeQueueDescriptor& descriptor,
-                                            const WorkloadInfo& info) const override;
-
-    ARMNN_DEPRECATED_MSG("Use CreateResize instead")
-    std::unique_ptr<IWorkload> CreateResizeBilinear(const ResizeBilinearQueueDescriptor& descriptor,
-                                                    const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateEqual(const EqualQueueDescriptor& descriptor,
+                                           const WorkloadInfo& info) const override;
 
     std::unique_ptr<IWorkload> CreateFakeQuantization(const FakeQuantizationQueueDescriptor& descriptor,
                                                       const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateQuantize(const QuantizeQueueDescriptor& descriptor,
-                                              const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateFloor(const FloorQueueDescriptor& descriptor,
+                                           const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateL2Normalization(const L2NormalizationQueueDescriptor& descriptor,
-                                                     const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateFullyConnected(const FullyConnectedQueueDescriptor& descriptor,
+                                                    const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateConcat(const ConcatQueueDescriptor& descriptor,
+    std::unique_ptr<IWorkload> CreateGather(const GatherQueueDescriptor& descriptor,
                                             const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateConstant(const ConstantQueueDescriptor& descriptor,
-                                              const WorkloadInfo& info) const override;
-
-    std::unique_ptr<IWorkload> CreateReshape(const ReshapeQueueDescriptor& descriptor,
+    std::unique_ptr<IWorkload> CreateGreater(const GreaterQueueDescriptor& descriptor,
                                              const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateSpaceToBatchNd(const SpaceToBatchNdQueueDescriptor& descriptor,
-                                                    const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateInput(const InputQueueDescriptor& descriptor,
+                                           const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateSpaceToDepth(const SpaceToDepthQueueDescriptor& descriptor,
-                                                  const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateInstanceNormalization(const InstanceNormalizationQueueDescriptor& descriptor,
+                                                           const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateFloor(const FloorQueueDescriptor& descriptor,
-                                           const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateL2Normalization(const L2NormalizationQueueDescriptor& descriptor,
+                                                     const WorkloadInfo& info) const override;
 
     std::unique_ptr<IWorkload> CreateLstm(const LstmQueueDescriptor& descriptor,
                                           const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateQuantizedLstm(const QuantizedLstmQueueDescriptor& descriptor,
-                                                   const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateMaximum(const MaximumQueueDescriptor& descriptor,
+                                             const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateConvertFp16ToFp32(const ConvertFp16ToFp32QueueDescriptor& descriptor,
-                                                       const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateMean(const MeanQueueDescriptor& descriptor,
+                                          const WorkloadInfo& Info) const override;
 
-    std::unique_ptr<IWorkload> CreateConvertFp32ToFp16(const ConvertFp32ToFp16QueueDescriptor& descriptor,
-                                                       const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateMemCopy(const MemCopyQueueDescriptor& descriptor,
+                                             const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateDivision(const DivisionQueueDescriptor& descriptor,
-                                              const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateMemImport(const MemImportQueueDescriptor& descriptor,
+                                               const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateSubtraction(const SubtractionQueueDescriptor& descriptor,
-                                                 const WorkloadInfo& info) const override;
+    ARMNN_DEPRECATED_MSG("Use CreateConcat instead")
+    std::unique_ptr<IWorkload> CreateMerger(const MergerQueueDescriptor& descriptor,
+                                            const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateMaximum(const MaximumQueueDescriptor& descriptor,
+    std::unique_ptr<IWorkload> CreateMinimum(const MinimumQueueDescriptor& descriptor,
                                              const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateMean(const MeanQueueDescriptor& descriptor,
-                                          const WorkloadInfo& Info) const override;
+    std::unique_ptr<IWorkload> CreateMultiplication(const MultiplicationQueueDescriptor& descriptor,
+                                                    const WorkloadInfo& info) const override;
+
+    std::unique_ptr<IWorkload> CreateNormalization(const NormalizationQueueDescriptor& descriptor,
+                                                   const WorkloadInfo& info) const override;
+
+    std::unique_ptr<IWorkload> CreateOutput(const OutputQueueDescriptor& descriptor,
+                                            const WorkloadInfo& info) const override;
 
     std::unique_ptr<IWorkload> CreatePad(const PadQueueDescriptor& descriptor,
                                          const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateEqual(const EqualQueueDescriptor& descriptor,
-                                           const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreatePermute(const PermuteQueueDescriptor& descriptor,
+                                             const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateBatchToSpaceNd(const BatchToSpaceNdQueueDescriptor& descriptor,
-                                                    const WorkloadInfo& Info) const override;
+    std::unique_ptr<IWorkload> CreatePooling2d(const Pooling2dQueueDescriptor& descriptor,
+                                               const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateStridedSlice(const StridedSliceQueueDescriptor& descriptor,
-                                                  const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreatePreCompiled(const PreCompiledQueueDescriptor& descriptor,
+                                                 const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateMinimum(const MinimumQueueDescriptor& descriptor,
-                                             const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreatePrelu(const PreluQueueDescriptor& descriptor,
+                                           const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateGreater(const GreaterQueueDescriptor& descriptor,
+    std::unique_ptr<IWorkload> CreateQuantize(const QuantizeQueueDescriptor& descriptor,
+                                              const WorkloadInfo& info) const override;
+
+    std::unique_ptr<IWorkload> CreateQuantizedLstm(const QuantizedLstmQueueDescriptor& descriptor,
+                                                   const WorkloadInfo& info) const override;
+
+    std::unique_ptr<IWorkload> CreateReshape(const ReshapeQueueDescriptor& descriptor,
                                              const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateDebug(const DebugQueueDescriptor& descriptor,
-                                           const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateResize(const ResizeQueueDescriptor& descriptor,
+                                            const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateTransposeConvolution2d(const TransposeConvolution2dQueueDescriptor& descriptor,
-                                                            const WorkloadInfo& info) const override;
+    ARMNN_DEPRECATED_MSG("Use CreateResize instead")
+    std::unique_ptr<IWorkload> CreateResizeBilinear(const ResizeBilinearQueueDescriptor& descriptor,
+                                                    const WorkloadInfo& info) const override;
 
     std::unique_ptr<IWorkload> CreateRsqrt(const RsqrtQueueDescriptor& descriptor,
                                            const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreatePreCompiled(const PreCompiledQueueDescriptor& descriptor,
-                                                 const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateSoftmax(const SoftmaxQueueDescriptor& descriptor,
+                                             const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateGather(const GatherQueueDescriptor& descriptor,
-                                            const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateSpaceToBatchNd(const SpaceToBatchNdQueueDescriptor& descriptor,
+                                                    const WorkloadInfo& info) const override;
+
+    std::unique_ptr<IWorkload> CreateSpaceToDepth(const SpaceToDepthQueueDescriptor& descriptor,
+                                                  const WorkloadInfo& info) const override;
+
+    std::unique_ptr<IWorkload> CreateSplitter(const SplitterQueueDescriptor& descriptor,
+                                              const WorkloadInfo& info) const override;
 
     std::unique_ptr<IWorkload> CreateStack(const StackQueueDescriptor& descriptor,
                                            const WorkloadInfo& info) const override;
 
-    std::unique_ptr<IWorkload> CreateArgMinMax(const ArgMinMaxQueueDescriptor& descriptor,
-                                               const WorkloadInfo& info) const override;
+    std::unique_ptr<IWorkload> CreateStridedSlice(const StridedSliceQueueDescriptor& descriptor,
+                                                  const WorkloadInfo& info) const override;
+
+    std::unique_ptr<IWorkload> CreateSubtraction(const SubtractionQueueDescriptor& descriptor,
+                                                 const WorkloadInfo& info) const override;
+
+    std::unique_ptr<IWorkload> CreateTransposeConvolution2d(const TransposeConvolution2dQueueDescriptor& descriptor,
+                                                            const WorkloadInfo& info) const override;
 
 private:
     mutable std::shared_ptr<NeonMemoryManager> m_MemoryManager;