From 250d3927b16abe4d6932cd5dce1184bd7026a2b7 Mon Sep 17 00:00:00 2001 From: Narumol Prangnawarat Date: Mon, 30 Mar 2020 16:11:04 +0100 Subject: IVGCVSW-4633 Add conversion of BF16 support to Neon * Add NeonConvertBf16ToFp32Workload * Add NeonConvertFp32ToBf16Workload * Add BFloat16 type support to NeonConstantWorkload and NeonTensorHandle * Add ConvertBf16ToFp32Weight when ConvertBf16ToFp32Layer is added * Unit tests Signed-off-by: Narumol Prangnawarat Change-Id: Id5b44a203add5e0c98c1ca4e2162115741b56644 --- src/backends/neon/workloads/CMakeLists.txt | 4 ++ .../neon/workloads/NeonConstantWorkload.cpp | 6 +++ .../workloads/NeonConvertBf16ToFp32Workload.cpp | 43 +++++++++++++++++++++ .../workloads/NeonConvertBf16ToFp32Workload.hpp | 26 +++++++++++++ .../workloads/NeonConvertFp32ToBf16Workload.cpp | 44 ++++++++++++++++++++++ .../workloads/NeonConvertFp32ToBf16Workload.hpp | 26 +++++++++++++ src/backends/neon/workloads/NeonWorkloads.hpp | 2 + 7 files changed, 151 insertions(+) create mode 100644 src/backends/neon/workloads/NeonConvertBf16ToFp32Workload.cpp create mode 100644 src/backends/neon/workloads/NeonConvertBf16ToFp32Workload.hpp create mode 100644 src/backends/neon/workloads/NeonConvertFp32ToBf16Workload.cpp create mode 100644 src/backends/neon/workloads/NeonConvertFp32ToBf16Workload.hpp (limited to 'src/backends/neon/workloads') diff --git a/src/backends/neon/workloads/CMakeLists.txt b/src/backends/neon/workloads/CMakeLists.txt index cbe1e3b945..7db315f116 100644 --- a/src/backends/neon/workloads/CMakeLists.txt +++ b/src/backends/neon/workloads/CMakeLists.txt @@ -22,8 +22,12 @@ list(APPEND armnnNeonBackendWorkloads_sources NeonConcatWorkload.hpp NeonConstantWorkload.cpp NeonConstantWorkload.hpp + NeonConvertBf16ToFp32Workload.cpp + NeonConvertBf16ToFp32Workload.hpp NeonConvertFp16ToFp32Workload.cpp NeonConvertFp16ToFp32Workload.hpp + NeonConvertFp32ToBf16Workload.cpp + NeonConvertFp32ToBf16Workload.hpp NeonConvertFp32ToFp16Workload.cpp NeonConvertFp32ToFp16Workload.hpp NeonConvolution2dWorkload.cpp diff --git a/src/backends/neon/workloads/NeonConstantWorkload.cpp b/src/backends/neon/workloads/NeonConstantWorkload.cpp index 08f0390e34..83a2692b6e 100644 --- a/src/backends/neon/workloads/NeonConstantWorkload.cpp +++ b/src/backends/neon/workloads/NeonConstantWorkload.cpp @@ -6,6 +6,7 @@ #include "NeonConstantWorkload.hpp" #include +#include #include #include #include @@ -46,6 +47,11 @@ void NeonConstantWorkload::Execute() const switch (computeDataType) { + case arm_compute::DataType::BFLOAT16: + { + CopyArmComputeITensorData(data.m_LayerOutput->GetConstTensor(), output); + break; + } case arm_compute::DataType::F16: { CopyArmComputeITensorData(data.m_LayerOutput->GetConstTensor(), output); diff --git a/src/backends/neon/workloads/NeonConvertBf16ToFp32Workload.cpp b/src/backends/neon/workloads/NeonConvertBf16ToFp32Workload.cpp new file mode 100644 index 0000000000..79d1f22313 --- /dev/null +++ b/src/backends/neon/workloads/NeonConvertBf16ToFp32Workload.cpp @@ -0,0 +1,43 @@ +// +// Copyright © 2020 Arm Ltd. All rights reserved. +// SPDX-License-Identifier: MIT +// + +#include "NeonConvertBf16ToFp32Workload.hpp" + +#include + +#include + +#include + +namespace armnn +{ + +NeonConvertBf16ToFp32Workload::NeonConvertBf16ToFp32Workload(const ConvertBf16ToFp32QueueDescriptor& descriptor, + const WorkloadInfo& info) + : BFloat16ToFloat32Workload(descriptor, info) +{ + this->m_Data.ValidateInputsOutputs("NeonConvertBf16ToFp32Workload", 1, 1); + GatherTensorHandlePairs(descriptor, m_TensorHandlePairs); +} + +void NeonConvertBf16ToFp32Workload::Execute() const +{ + ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonConvertBf16ToFp32Workload_Execute"); + + auto convertFunc = [](uint8_t* dst, const uint8_t* src, size_t size) + { + auto input = reinterpret_cast(src); + auto output = reinterpret_cast(dst); + size_t numElements = size/2; // 2 bytes per Bf16 + armnnUtils::FloatingPointConverter::ConvertBFloat16ToFloat32(input, numElements, output); + }; + + for (const auto& pair : m_TensorHandlePairs) + { + CopyTensorContentsGeneric(pair.first, pair.second, convertFunc); + } +} + +} //namespace armnn diff --git a/src/backends/neon/workloads/NeonConvertBf16ToFp32Workload.hpp b/src/backends/neon/workloads/NeonConvertBf16ToFp32Workload.hpp new file mode 100644 index 0000000000..0969088b92 --- /dev/null +++ b/src/backends/neon/workloads/NeonConvertBf16ToFp32Workload.hpp @@ -0,0 +1,26 @@ +// +// Copyright © 2020 Arm Ltd. All rights reserved. +// SPDX-License-Identifier: MIT +// + +#pragma once + +#include +#include +#include + +namespace armnn +{ + +class NeonConvertBf16ToFp32Workload : public BFloat16ToFloat32Workload +{ +public: + NeonConvertBf16ToFp32Workload(const ConvertBf16ToFp32QueueDescriptor& descriptor, const WorkloadInfo& info); + virtual void Execute() const override; + +private: + using TensorHandlePair = std::pair; + std::vector m_TensorHandlePairs; +}; + +} //namespace armnn diff --git a/src/backends/neon/workloads/NeonConvertFp32ToBf16Workload.cpp b/src/backends/neon/workloads/NeonConvertFp32ToBf16Workload.cpp new file mode 100644 index 0000000000..e1aceec197 --- /dev/null +++ b/src/backends/neon/workloads/NeonConvertFp32ToBf16Workload.cpp @@ -0,0 +1,44 @@ +// +// Copyright © 2020 Arm Ltd. All rights reserved. +// SPDX-License-Identifier: MIT +// + +#include "NeonConvertFp32ToBf16Workload.hpp" + +#include +#include + +#include + +#include + +namespace armnn +{ + +NeonConvertFp32ToBf16Workload::NeonConvertFp32ToBf16Workload(const ConvertFp32ToBf16QueueDescriptor& descriptor, + const WorkloadInfo& info) + : Float32ToBFloat16Workload(descriptor, info) +{ + this->m_Data.ValidateInputsOutputs("NeonConvertFp32ToBf16Workload", 1, 1); + GatherTensorHandlePairs(descriptor, m_TensorHandlePairs); +} + +void NeonConvertFp32ToBf16Workload::Execute() const +{ + ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonConvertFp32ToBf16Workload_Execute"); + + auto convertFunc = [](uint8_t* dst, const uint8_t* src, size_t size) + { + auto input = reinterpret_cast(src); + auto output = reinterpret_cast(dst); + size_t numElements = size/2; // 2 bytes per bf16 + armnnUtils::FloatingPointConverter::ConvertFloat32ToBFloat16(input, numElements, output); + }; + + for (const auto& pair : m_TensorHandlePairs) + { + CopyTensorContentsGeneric(pair.first, pair.second, convertFunc); + } +} + +} //namespace armnn diff --git a/src/backends/neon/workloads/NeonConvertFp32ToBf16Workload.hpp b/src/backends/neon/workloads/NeonConvertFp32ToBf16Workload.hpp new file mode 100644 index 0000000000..bc96c16287 --- /dev/null +++ b/src/backends/neon/workloads/NeonConvertFp32ToBf16Workload.hpp @@ -0,0 +1,26 @@ +// +// Copyright © 2020 Arm Ltd. All rights reserved. +// SPDX-License-Identifier: MIT +// + +#pragma once + +#include +#include +#include + +namespace armnn +{ + +class NeonConvertFp32ToBf16Workload : public Float32ToBFloat16Workload +{ +public: + NeonConvertFp32ToBf16Workload(const ConvertFp32ToBf16QueueDescriptor& descriptor, const WorkloadInfo& info); + virtual void Execute() const override; + +private: + using TensorHandlePair = std::pair; + std::vector m_TensorHandlePairs; +}; + +} //namespace armnn diff --git a/src/backends/neon/workloads/NeonWorkloads.hpp b/src/backends/neon/workloads/NeonWorkloads.hpp index 2b7eabeb0d..f25554722d 100644 --- a/src/backends/neon/workloads/NeonWorkloads.hpp +++ b/src/backends/neon/workloads/NeonWorkloads.hpp @@ -13,7 +13,9 @@ #include "NeonBatchToSpaceNdWorkload.hpp" #include "NeonComparisonWorkload.hpp" #include "NeonConstantWorkload.hpp" +#include "NeonConvertBf16ToFp32Workload.hpp" #include "NeonConvertFp16ToFp32Workload.hpp" +#include "NeonConvertFp32ToBf16Workload.hpp" #include "NeonConvertFp32ToFp16Workload.hpp" #include "NeonConvolution2dWorkload.hpp" #include "NeonDepthToSpaceWorkload.hpp" -- cgit v1.2.1