diff options
author | David Beck <david.beck@arm.com> | 2018-09-26 17:41:13 +0100 |
---|---|---|
committer | Matthew Bentham <matthew.bentham@arm.com> | 2018-10-10 16:16:57 +0100 |
commit | ac42efd972b7d03da17f057b2ceaaac5d6e96b1a (patch) | |
tree | 1ebc1320fa3ea7f494d3716ea79a2bda0f4ffd1e /src/backends/cl/workloads/ClFullyConnectedWorkload.cpp | |
parent | bcd3c85b5a7657b38f503676b88a80ae74165acd (diff) | |
download | armnn-ac42efd972b7d03da17f057b2ceaaac5d6e96b1a.tar.gz |
IVGCVSW-1900 : CL backend folder structure
* moving backends/ClWorkloads to backends/cl
* and moving pure Cl workload related code to
backends/cl/workloads
Change-Id: I019a3c6b4da5e7a23074bf03fb057e63199ad129
Diffstat (limited to 'src/backends/cl/workloads/ClFullyConnectedWorkload.cpp')
-rw-r--r-- | src/backends/cl/workloads/ClFullyConnectedWorkload.cpp | 96 |
1 files changed, 96 insertions, 0 deletions
diff --git a/src/backends/cl/workloads/ClFullyConnectedWorkload.cpp b/src/backends/cl/workloads/ClFullyConnectedWorkload.cpp new file mode 100644 index 0000000000..b3a97f35f8 --- /dev/null +++ b/src/backends/cl/workloads/ClFullyConnectedWorkload.cpp @@ -0,0 +1,96 @@ +// +// Copyright © 2017 Arm Ltd. All rights reserved. +// SPDX-License-Identifier: MIT +// + +#include "ClFullyConnectedWorkload.hpp" +#include <backends/cl/ClTensorHandle.hpp> +#include <backends/CpuTensorHandle.hpp> +#include <backends/aclCommon/ArmComputeTensorUtils.hpp> +#include <backends/aclCommon/ArmComputeUtils.hpp> +#include <backends/cl/ClLayerSupport.hpp> + +#include "ClWorkloadUtils.hpp" + +namespace armnn +{ +using namespace armcomputetensorutils; + +arm_compute::Status ClFullyConnectedWorkloadValidate(const TensorInfo& input, + const TensorInfo& output, + const TensorInfo& weights, + const TensorInfo& biases, + const FullyConnectedDescriptor& descriptor) +{ + const arm_compute::TensorInfo aclInput = BuildArmComputeTensorInfo(input); + const arm_compute::TensorInfo aclOutput = BuildArmComputeTensorInfo(output); + const arm_compute::TensorInfo aclWeights = BuildArmComputeTensorInfo(weights); + + arm_compute::TensorInfo aclBiases; + arm_compute::TensorInfo *optionalAclBiases = nullptr; + if (descriptor.m_BiasEnabled) + { + aclBiases = BuildArmComputeTensorInfo(biases); + optionalAclBiases = &aclBiases; + } + + const arm_compute::FullyConnectedLayerInfo fullyConnectedLayerInfo = + ConvertFullyConnectedDescriptorToAclFullyConnectedLayerInfo(descriptor); + + return arm_compute::CLFullyConnectedLayer::validate(&aclInput, + &aclWeights, + optionalAclBiases, + &aclOutput, + fullyConnectedLayerInfo); +} + +ClFullyConnectedWorkload::ClFullyConnectedWorkload(const FullyConnectedQueueDescriptor& descriptor, + const WorkloadInfo& info, std::shared_ptr<arm_compute::MemoryManagerOnDemand>& memoryManager) + : BaseWorkload<FullyConnectedQueueDescriptor>(descriptor, info) + , m_FullyConnectedLayer(memoryManager) +{ + m_WeightsTensor = std::make_unique<arm_compute::CLTensor>(); + BuildArmComputeTensor(*m_WeightsTensor, m_Data.m_Weight->GetTensorInfo()); + + if (m_Data.m_Parameters.m_BiasEnabled) + { + m_BiasesTensor = std::make_unique<arm_compute::CLTensor>(); + BuildArmComputeTensor(*m_BiasesTensor, m_Data.m_Bias->GetTensorInfo()); + } + + m_Data.ValidateInputsOutputs("ClFullyConnectedWorkload", 1, 1); + + arm_compute::ICLTensor& input = static_cast<IClTensorHandle*>(m_Data.m_Inputs[0])->GetTensor(); + arm_compute::ICLTensor& output = static_cast<IClTensorHandle*>(m_Data.m_Outputs[0])->GetTensor(); + + // Construct + arm_compute::FullyConnectedLayerInfo fc_info; + fc_info.transpose_weights = m_Data.m_Parameters.m_TransposeWeightMatrix; + m_FullyConnectedLayer.configure(&input, m_WeightsTensor.get(), m_BiasesTensor.get(), &output, fc_info); + + InitializeArmComputeClTensorData(*m_WeightsTensor, m_Data.m_Weight); + + if (m_BiasesTensor) + { + InitializeArmComputeClTensorData(*m_BiasesTensor, m_Data.m_Bias); + } + + // Force Compute Library to perform the necessary copying and reshaping, after which + // delete all the input tensors that will no longer be needed + m_FullyConnectedLayer.prepare(); + FreeUnusedTensors(); +} + +void ClFullyConnectedWorkload::Execute() const +{ + ARMNN_SCOPED_PROFILING_EVENT_CL("ClFullyConnectedWorkload_Execute"); + m_FullyConnectedLayer.run(); +} + +void ClFullyConnectedWorkload::FreeUnusedTensors() +{ + FreeTensorIfUnused(m_WeightsTensor); + FreeTensorIfUnused(m_BiasesTensor); +} + +} //namespace armnn |