diff options
author | arovir01 <Aron.Virginas-Tar@arm.com> | 2018-08-31 15:26:35 +0100 |
---|---|---|
committer | Matthew Bentham <matthew.bentham@arm.com> | 2018-09-17 17:21:25 +0100 |
commit | 9e53a35b66b1ec7ceee7c712380a13596175b83b (patch) | |
tree | d40bf9f27c799184324b6ab91cbb1a546fc4012e /src/armnn/backends/NeonWorkloads/NeonDepthwiseConvolutionFloatWorkload.cpp | |
parent | 5540d2f379b15503269d1b9b5fbe8fbafd160d2e (diff) | |
download | armnn-9e53a35b66b1ec7ceee7c712380a13596175b83b.tar.gz |
IVGCVSW-1784: Rename float32 workloads for ACL
Change-Id: I98bdfe9cb12c663d1d5cfa456e2cc967d70ab22b
Diffstat (limited to 'src/armnn/backends/NeonWorkloads/NeonDepthwiseConvolutionFloatWorkload.cpp')
-rw-r--r-- | src/armnn/backends/NeonWorkloads/NeonDepthwiseConvolutionFloatWorkload.cpp | 94 |
1 files changed, 94 insertions, 0 deletions
diff --git a/src/armnn/backends/NeonWorkloads/NeonDepthwiseConvolutionFloatWorkload.cpp b/src/armnn/backends/NeonWorkloads/NeonDepthwiseConvolutionFloatWorkload.cpp new file mode 100644 index 0000000000..96ca938242 --- /dev/null +++ b/src/armnn/backends/NeonWorkloads/NeonDepthwiseConvolutionFloatWorkload.cpp @@ -0,0 +1,94 @@ +// +// Copyright © 2017 Arm Ltd. All rights reserved. +// See LICENSE file in the project root for full license information. +// + +#include "NeonDepthwiseConvolutionFloatWorkload.hpp" +#include "backends/NeonLayerSupport.hpp" +#include "backends/CpuTensorHandle.hpp" +#include "backends/ArmComputeTensorUtils.hpp" + + +namespace armnn +{ +using namespace armcomputetensorutils; + +NeonDepthwiseConvolutionFloatWorkload::NeonDepthwiseConvolutionFloatWorkload( + const DepthwiseConvolution2dQueueDescriptor& descriptor, + const WorkloadInfo& info) + : FloatWorkload<DepthwiseConvolution2dQueueDescriptor>(descriptor, info) +{ + const TensorInfo& weightInfo = m_Data.m_Weight->GetTensorInfo(); + + m_KernelTensor = std::make_unique<arm_compute::Tensor>(); + BuildArmComputeTensor(*m_KernelTensor, weightInfo); + + if (m_Data.m_Parameters.m_BiasEnabled) + { + m_BiasTensor = std::make_unique<arm_compute::Tensor>(); + BuildArmComputeTensor(*m_BiasTensor, m_Data.m_Bias->GetTensorInfo()); + } + + arm_compute::PadStrideInfo padStrideInfo(m_Data.m_Parameters.m_StrideX, + m_Data.m_Parameters.m_StrideY, + m_Data.m_Parameters.m_PadLeft, + m_Data.m_Parameters.m_PadRight, + m_Data.m_Parameters.m_PadTop, + m_Data.m_Parameters.m_PadBottom, + arm_compute::DimensionRoundingType::FLOOR); + + m_Data.ValidateInputsOutputs("NeonDepthwiseConvolutionFloatWorkload", 1, 1); + + arm_compute::ITensor& input = static_cast<INeonTensorHandle*>(m_Data.m_Inputs[0])->GetTensor(); + arm_compute::ITensor& output = static_cast<INeonTensorHandle*>(m_Data.m_Outputs[0])->GetTensor(); + + bool use3x3Optimisation = weightInfo.GetShape()[3] == 3 && weightInfo.GetShape()[2] == 3; + if (use3x3Optimisation) + { + m_pDepthwiseConvolutionLayer = std::make_unique<arm_compute::NEDepthwiseConvolutionLayer3x3>(); + static_cast<arm_compute::NEDepthwiseConvolutionLayer3x3*>( + m_pDepthwiseConvolutionLayer.get())->configure(&input, + m_KernelTensor.get(), + m_BiasTensor.get(), + &output, + padStrideInfo); + } + else + { + m_pDepthwiseConvolutionLayer = std::make_unique<arm_compute::NEDepthwiseConvolutionLayer>(); + static_cast<arm_compute::NEDepthwiseConvolutionLayer*>( + m_pDepthwiseConvolutionLayer.get())->configure(&input, + m_KernelTensor.get(), + m_BiasTensor.get(), + &output, + padStrideInfo); + } + + BOOST_ASSERT(m_pDepthwiseConvolutionLayer); + + InitializeArmComputeTensorDataForFloatTypes(*m_KernelTensor, m_Data.m_Weight); + + if (m_BiasTensor) + { + InitializeArmComputeTensorDataForFloatTypes(*m_BiasTensor, m_Data.m_Bias); + } + + m_pDepthwiseConvolutionLayer->prepare(); + FreeUnusedTensors(); +} + +void NeonDepthwiseConvolutionFloatWorkload::Execute() const +{ + ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonDepthwiseConvolutionFloatWorkload_Execute"); + BOOST_ASSERT(m_pDepthwiseConvolutionLayer); + + m_pDepthwiseConvolutionLayer->run(); +} + +void NeonDepthwiseConvolutionFloatWorkload::FreeUnusedTensors() +{ + FreeTensorIfUnused(m_KernelTensor); + FreeTensorIfUnused(m_BiasTensor); +} + +} //namespace armnn |