diff options
Diffstat (limited to 'src/backends/neon/workloads')
9 files changed, 102 insertions, 164 deletions
diff --git a/src/backends/neon/workloads/CMakeLists.txt b/src/backends/neon/workloads/CMakeLists.txt index a96c27c75a..0b0b9ed5a0 100644 --- a/src/backends/neon/workloads/CMakeLists.txt +++ b/src/backends/neon/workloads/CMakeLists.txt @@ -8,13 +8,10 @@ list(APPEND armnnNeonBackendWorkloads_sources NeonActivationWorkload.hpp NeonAdditionFloatWorkload.cpp NeonAdditionFloatWorkload.hpp - NeonBaseConstantWorkload.hpp NeonBatchNormalizationFloatWorkload.cpp NeonBatchNormalizationFloatWorkload.hpp - NeonConstantFloatWorkload.cpp - NeonConstantFloatWorkload.hpp - NeonConstantUint8Workload.cpp - NeonConstantUint8Workload.hpp + NeonConstantWorkload.cpp + NeonConstantWorkload.hpp NeonConvertFp16ToFp32Workload.cpp NeonConvertFp16ToFp32Workload.hpp NeonConvertFp32ToFp16Workload.cpp diff --git a/src/backends/neon/workloads/NeonBaseConstantWorkload.hpp b/src/backends/neon/workloads/NeonBaseConstantWorkload.hpp deleted file mode 100644 index 828e476d29..0000000000 --- a/src/backends/neon/workloads/NeonBaseConstantWorkload.hpp +++ /dev/null @@ -1,82 +0,0 @@ -// -// Copyright © 2017 Arm Ltd. All rights reserved. -// SPDX-License-Identifier: MIT -// - -#pragma once - -#include <arm_compute/core/Types.h> -#include <armnnUtils/Half.hpp> -#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 <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 diff --git a/src/backends/neon/workloads/NeonConstantFloatWorkload.cpp b/src/backends/neon/workloads/NeonConstantFloatWorkload.cpp deleted file mode 100644 index dbdd057101..0000000000 --- a/src/backends/neon/workloads/NeonConstantFloatWorkload.cpp +++ /dev/null @@ -1,17 +0,0 @@ -// -// Copyright © 2017 Arm Ltd. All rights reserved. -// SPDX-License-Identifier: MIT -// - -#include "NeonConstantFloatWorkload.hpp" - -namespace armnn -{ - -void NeonConstantFloatWorkload::Execute() const -{ - ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonConstantFloatWorkload_Execute"); - NeonBaseConstantWorkload::Execute(); -} - -} //namespace armnn diff --git a/src/backends/neon/workloads/NeonConstantFloatWorkload.hpp b/src/backends/neon/workloads/NeonConstantFloatWorkload.hpp deleted file mode 100644 index c35b5fda3e..0000000000 --- a/src/backends/neon/workloads/NeonConstantFloatWorkload.hpp +++ /dev/null @@ -1,20 +0,0 @@ -// -// Copyright © 2017 Arm Ltd. All rights reserved. -// SPDX-License-Identifier: MIT -// - -#pragma once - -#include "NeonBaseConstantWorkload.hpp" - -namespace armnn -{ - -class NeonConstantFloatWorkload : public NeonBaseConstantWorkload<DataType::Float16, DataType::Float32> -{ -public: - using NeonBaseConstantWorkload<DataType::Float16, DataType::Float32>::NeonBaseConstantWorkload; - virtual void Execute() const override; -}; - -} //namespace armnn diff --git a/src/backends/neon/workloads/NeonConstantUint8Workload.cpp b/src/backends/neon/workloads/NeonConstantUint8Workload.cpp deleted file mode 100644 index c607d86844..0000000000 --- a/src/backends/neon/workloads/NeonConstantUint8Workload.cpp +++ /dev/null @@ -1,17 +0,0 @@ -// -// Copyright © 2017 Arm Ltd. All rights reserved. -// SPDX-License-Identifier: MIT -// - -#include "NeonConstantUint8Workload.hpp" - -namespace armnn -{ - -void NeonConstantUint8Workload::Execute() const -{ - ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonConstantUint8Workload_Execute"); - NeonBaseConstantWorkload::Execute(); -} - -} //namespace armnn diff --git a/src/backends/neon/workloads/NeonConstantUint8Workload.hpp b/src/backends/neon/workloads/NeonConstantUint8Workload.hpp deleted file mode 100644 index 2cb9516afe..0000000000 --- a/src/backends/neon/workloads/NeonConstantUint8Workload.hpp +++ /dev/null @@ -1,20 +0,0 @@ -// -// Copyright © 2017 Arm Ltd. All rights reserved. -// SPDX-License-Identifier: MIT -// - -#pragma once - -#include "NeonBaseConstantWorkload.hpp" - -namespace armnn -{ - -class NeonConstantUint8Workload : public NeonBaseConstantWorkload<DataType::QuantisedAsymm8> -{ -public: - using NeonBaseConstantWorkload<DataType::QuantisedAsymm8>::NeonBaseConstantWorkload; - virtual void Execute() const override; -}; - -} //namespace armnn diff --git a/src/backends/neon/workloads/NeonConstantWorkload.cpp b/src/backends/neon/workloads/NeonConstantWorkload.cpp new file mode 100644 index 0000000000..a3485471c8 --- /dev/null +++ b/src/backends/neon/workloads/NeonConstantWorkload.cpp @@ -0,0 +1,75 @@ +// +// Copyright © 2017 Arm Ltd. All rights reserved. +// SPDX-License-Identifier: MIT +// + +#include "NeonConstantWorkload.hpp" + +#include <arm_compute/core/Types.h> +#include <armnnUtils/Half.hpp> +#include <backends/aclCommon/ArmComputeTensorUtils.hpp> +#include <backends/neon/NeonTensorHandle.hpp> +#include <backends/CpuTensorHandle.hpp> +#include <backends/Workload.hpp> + +#include <boost/cast.hpp> + +namespace armnn +{ + +NeonConstantWorkload::NeonConstantWorkload(const ConstantQueueDescriptor& descriptor, + const WorkloadInfo& info) + : BaseWorkload<ConstantQueueDescriptor>(descriptor, info) + , m_RanOnce(false) +{ +} + +void NeonConstantWorkload::Execute() const +{ + ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonConstantWorkload_Execute"); + + 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; + } +} + +} //namespace armnn diff --git a/src/backends/neon/workloads/NeonConstantWorkload.hpp b/src/backends/neon/workloads/NeonConstantWorkload.hpp new file mode 100644 index 0000000000..72069633f8 --- /dev/null +++ b/src/backends/neon/workloads/NeonConstantWorkload.hpp @@ -0,0 +1,24 @@ +// +// Copyright © 2017 Arm Ltd. All rights reserved. +// SPDX-License-Identifier: MIT +// + +#pragma once + +#include <backends/neon/workloads/NeonWorkloadUtils.hpp> + +namespace armnn +{ + +class NeonConstantWorkload : public BaseWorkload<ConstantQueueDescriptor> +{ +public: + NeonConstantWorkload(const ConstantQueueDescriptor& descriptor, const WorkloadInfo& info); + + virtual void Execute() const override; + +private: + mutable bool m_RanOnce; +}; + +} //namespace armnn diff --git a/src/backends/neon/workloads/NeonWorkloads.hpp b/src/backends/neon/workloads/NeonWorkloads.hpp index 93711b6fc1..702ddb5c82 100644 --- a/src/backends/neon/workloads/NeonWorkloads.hpp +++ b/src/backends/neon/workloads/NeonWorkloads.hpp @@ -6,10 +6,8 @@ #pragma once #include "NeonActivationWorkload.hpp" #include "NeonAdditionFloatWorkload.hpp" -#include "NeonBaseConstantWorkload.hpp" #include "NeonBatchNormalizationFloatWorkload.hpp" -#include "NeonConstantFloatWorkload.hpp" -#include "NeonConstantUint8Workload.hpp" +#include "NeonConstantWorkload.hpp" #include "NeonConvertFp16ToFp32Workload.hpp" #include "NeonConvertFp32ToFp16Workload.hpp" #include "NeonConvolution2dBaseWorkload.hpp" |