diff options
author | telsoa01 <telmo.soares@arm.com> | 2018-03-09 14:13:49 +0000 |
---|---|---|
committer | telsoa01 <telmo.soares@arm.com> | 2018-03-09 14:13:49 +0000 |
commit | 4fcda0101ec3d110c1d6d7bee5c83416b645528a (patch) | |
tree | c9a70aeb2887006160c1b3d265c27efadb7bdbae /src/armnn/backends/ClWorkloadFactory.hpp | |
download | armnn-4fcda0101ec3d110c1d6d7bee5c83416b645528a.tar.gz |
Release 18.02
Change-Id: Id3c11dc5ee94ef664374a988fcc6901e9a232fa6
Diffstat (limited to 'src/armnn/backends/ClWorkloadFactory.hpp')
-rw-r--r-- | src/armnn/backends/ClWorkloadFactory.hpp | 129 |
1 files changed, 129 insertions, 0 deletions
diff --git a/src/armnn/backends/ClWorkloadFactory.hpp b/src/armnn/backends/ClWorkloadFactory.hpp new file mode 100644 index 0000000000..2477e23eeb --- /dev/null +++ b/src/armnn/backends/ClWorkloadFactory.hpp @@ -0,0 +1,129 @@ +// +// Copyright © 2017 Arm Ltd. All rights reserved. +// See LICENSE file in the project root for full license information. +// +#pragma once + +#include "WorkloadFactory.hpp" +#include "OutputHandler.hpp" +#include "armnn/IRuntime.hpp" + +#ifdef ARMCOMPUTECL_ENABLED +#include <arm_compute/runtime/CL/CLTuner.h> +#endif + +namespace cl +{ +class Context; +class CommandQueue; +class Device; +} + +namespace armnn +{ + +class IClTunedParameters; + +// ARM Compute OpenCL workload factory +class ClWorkloadFactory : public IWorkloadFactory +{ +public: + virtual ~ClWorkloadFactory(){}; + + virtual Compute GetCompute() const override { return Compute::GpuAcc; } + + static bool IsLayerSupported(const Layer& layer, DataType dataType, std::string& outReasonIfUnsupported); + + void LoadOpenClRuntime(IClTunedParameters* clTunedParameters = nullptr); + + virtual bool SupportsSubTensors() const override { return true; } + + virtual std::unique_ptr<ITensorHandle> CreateSubTensorHandle(ITensorHandle& parent, + TensorShape const& subTensorShape, + unsigned int const* subTensorOrigin) const override; + + virtual std::unique_ptr<ITensorHandle> CreateTensorHandle(const TensorInfo& tensorInfo) const override; + + virtual std::unique_ptr<IWorkload> CreateInput(const InputQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateOutput(const OutputQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateActivation(const ActivationQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateSoftmax(const SoftmaxQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateSplitter(const SplitterQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateMerger(const MergerQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateFullyConnected(const FullyConnectedQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreatePermute(const PermuteQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreatePooling2d(const Pooling2dQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateConvolution2d(const Convolution2dQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateDepthwiseConvolution2d( + const DepthwiseConvolution2dQueueDescriptor& descriptor, const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateNormalization(const NormalizationQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateAddition(const AdditionQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateMultiplication(const MultiplicationQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateBatchNormalization(const BatchNormalizationQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateMemCopy(const MemCopyQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateResizeBilinear(const ResizeBilinearQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateFakeQuantization(const FakeQuantizationQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateL2Normalization(const L2NormalizationQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateConstant(const ConstantQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateReshape(const ReshapeQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; + + virtual std::unique_ptr<IWorkload> CreateFloor(const FloorQueueDescriptor& descriptor, + const WorkloadInfo& info) const override; +}; + +class ClTunedParameters : public IClTunedParameters +{ +public: + ClTunedParameters(armnn::IClTunedParameters::Mode mode); + + virtual void Load(const char* filename); + virtual void Save(const char* filename) const; + + Mode m_Mode; + +#ifdef ARMCOMPUTECL_ENABLED + arm_compute::CLTuner m_Tuner; +#endif +}; + +} // namespace armnn |