diff options
author | David Beck <david.beck@arm.com> | 2018-09-24 15:59:27 +0100 |
---|---|---|
committer | Matthew Bentham <matthew.bentham@arm.com> | 2018-10-10 16:16:57 +0100 |
commit | 0dbe0ee25312b728d77383d11c465156e64ae757 (patch) | |
tree | af37a9802e3ad551e1bf63f7636508cde7a41643 /src/backends/neon/workloads/NeonBaseConstantWorkload.hpp | |
parent | b4540bef0b0327683fe8e63f727c1212800dc2a9 (diff) | |
download | armnn-0dbe0ee25312b728d77383d11c465156e64ae757.tar.gz |
IVGCVSW-1899 : Neon backend folder structure
armnn:149855
Change-Id: I26e8cf83422a65049386a5ebdb6d0001627aefaa
Diffstat (limited to 'src/backends/neon/workloads/NeonBaseConstantWorkload.hpp')
-rw-r--r-- | src/backends/neon/workloads/NeonBaseConstantWorkload.hpp | 82 |
1 files changed, 82 insertions, 0 deletions
diff --git a/src/backends/neon/workloads/NeonBaseConstantWorkload.hpp b/src/backends/neon/workloads/NeonBaseConstantWorkload.hpp new file mode 100644 index 0000000000..6bb275ac13 --- /dev/null +++ b/src/backends/neon/workloads/NeonBaseConstantWorkload.hpp @@ -0,0 +1,82 @@ +// +// Copyright © 2017 Arm Ltd. All rights reserved. +// SPDX-License-Identifier: MIT +// + +#pragma once + +#include <arm_compute/core/Types.h> +#include <backends/aclCommon/ArmComputeTensorUtils.hpp> +#include <backends/neon/NeonTensorHandle.hpp> +#include <backends/neon/workloads/NeonWorkloadUtils.hpp> +#include <backends/CpuTensorHandle.hpp> +#include <backends/Workload.hpp> +#include <Half.hpp> + +#include <boost/cast.hpp> + +namespace armnn +{ + +// Base class template providing an implementation of the Constant layer common to all data types. +template <armnn::DataType... DataFormats> +class NeonBaseConstantWorkload : public TypedWorkload<ConstantQueueDescriptor, DataFormats...> +{ +public: + NeonBaseConstantWorkload(const ConstantQueueDescriptor& descriptor, const WorkloadInfo& info) + : TypedWorkload<ConstantQueueDescriptor, DataFormats...>(descriptor, info) + , m_RanOnce(false) + { + } + + virtual void Execute() const override + { + using namespace armcomputetensorutils; + + // The intermediate tensor held by the corresponding layer output handler can be initialised with the + // given data on the first inference, then reused for subsequent inferences. + // The initialisation cannot happen at workload construction time since the ACL kernel for the next layer + // may not have been configured at the time. + if (!m_RanOnce) + { + const ConstantQueueDescriptor& data = this->m_Data; + + BOOST_ASSERT(data.m_LayerOutput != nullptr); + arm_compute::ITensor& output = + boost::polymorphic_downcast<NeonTensorHandle*>(data.m_Outputs[0])->GetTensor(); + arm_compute::DataType computeDataType = + boost::polymorphic_downcast<NeonTensorHandle*>(data.m_Outputs[0])->GetDataType(); + + switch (computeDataType) + { + case arm_compute::DataType::F16: + { + CopyArmComputeITensorData(data.m_LayerOutput->GetConstTensor<Half>(), output); + break; + } + case arm_compute::DataType::F32: + { + CopyArmComputeITensorData(data.m_LayerOutput->GetConstTensor<float>(), output); + break; + } + case arm_compute::DataType::QASYMM8: + { + CopyArmComputeITensorData(data.m_LayerOutput->GetConstTensor<uint8_t>(), output); + break; + } + default: + { + BOOST_ASSERT_MSG(false, "Unknown data type"); + break; + } + } + + m_RanOnce = true; + } + } + +private: + mutable bool m_RanOnce; +}; + +} //namespace armnn |