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/NeonMultiplicationFloatWorkload.cpp | |
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/NeonMultiplicationFloatWorkload.cpp')
-rw-r--r-- | src/backends/neon/workloads/NeonMultiplicationFloatWorkload.cpp | 60 |
1 files changed, 60 insertions, 0 deletions
diff --git a/src/backends/neon/workloads/NeonMultiplicationFloatWorkload.cpp b/src/backends/neon/workloads/NeonMultiplicationFloatWorkload.cpp new file mode 100644 index 0000000000..c4241ece19 --- /dev/null +++ b/src/backends/neon/workloads/NeonMultiplicationFloatWorkload.cpp @@ -0,0 +1,60 @@ +// +// Copyright © 2017 Arm Ltd. All rights reserved. +// SPDX-License-Identifier: MIT +// + +#include "NeonMultiplicationFloatWorkload.hpp" + + +namespace armnn +{ + +arm_compute::Status NeonMultiplicationWorkloadValidate(const TensorInfo& input0, + const TensorInfo& input1, + const TensorInfo& output) +{ + const arm_compute::TensorInfo aclInput1 = armcomputetensorutils::BuildArmComputeTensorInfo(input0); + const arm_compute::TensorInfo aclInput2 = armcomputetensorutils::BuildArmComputeTensorInfo(input1); + const arm_compute::TensorInfo aclOutput = armcomputetensorutils::BuildArmComputeTensorInfo(output); + + // At the time of writing, configure() will fail if a rounding policy other than TO_ZERO is supplied to it, + // when providing a scale of 1.0 for F32 tensors, even though the provided rounding policy appears to be + // ignored for F32 tensors. + return arm_compute::NEPixelWiseMultiplication::validate(&aclInput1, + &aclInput2, + &aclOutput, + 1.0f, + arm_compute::ConvertPolicy::SATURATE, + arm_compute::RoundingPolicy::TO_ZERO); +} + +NeonMultiplicationFloatWorkload::NeonMultiplicationFloatWorkload(const MultiplicationQueueDescriptor& descriptor, + const WorkloadInfo& info) + : FloatWorkload<MultiplicationQueueDescriptor>(descriptor, info) +{ + m_Data.ValidateInputsOutputs("NeonMultiplicationFloatWorkload", 2, 1); + + arm_compute::ITensor& input1 = boost::polymorphic_downcast<INeonTensorHandle*>(m_Data.m_Inputs[0])->GetTensor(); + arm_compute::ITensor& input2 = boost::polymorphic_downcast<INeonTensorHandle*>(m_Data.m_Inputs[1])->GetTensor(); + arm_compute::ITensor& output = boost::polymorphic_downcast<INeonTensorHandle*>(m_Data.m_Outputs[0])->GetTensor(); + + // At the time of writing, configure() will fail if a rounding policy other than TO_ZERO is supplied to it, + // when providing a scale of 1.0 for F32 tensors, even though the provided rounding policy appears to be + // ignored for F32 tensors. + m_PixelWiseMultiplication.configure(&input1, + &input2, + &output, + 1.0f, + arm_compute::ConvertPolicy::SATURATE, + arm_compute::RoundingPolicy::TO_ZERO); +} + +void NeonMultiplicationFloatWorkload::Execute() const +{ + ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonMultiplicationFloatWorkload_Execute"); + m_PixelWiseMultiplication.run(); +} + +} //namespace armnn + + |