blob: 445e32ea445bb62dd86af0a3d00717f1fcf49e10 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
|
//
// Copyright © 2017 Arm Ltd. All rights reserved.
// SPDX-License-Identifier: MIT
//
#include "NeonAdditionFloatWorkload.hpp"
#include <backends/aclCommon/ArmComputeTensorUtils.hpp>
#include <backends/CpuTensorHandle.hpp>
namespace armnn
{
arm_compute::Status NeonAdditionWorkloadValidate(const TensorInfo& input0,
const TensorInfo& input1,
const TensorInfo& output)
{
const arm_compute::TensorInfo aclInput0 = armcomputetensorutils::BuildArmComputeTensorInfo(input0);
const arm_compute::TensorInfo aclInput1 = armcomputetensorutils::BuildArmComputeTensorInfo(input1);
const arm_compute::TensorInfo aclOutput = armcomputetensorutils::BuildArmComputeTensorInfo(output);
return arm_compute::NEArithmeticAddition::validate(&aclInput0,
&aclInput1,
&aclOutput,
arm_compute::ConvertPolicy::SATURATE);
}
NeonAdditionFloatWorkload::NeonAdditionFloatWorkload(const AdditionQueueDescriptor& descriptor,
const WorkloadInfo& info)
: FloatWorkload<AdditionQueueDescriptor>(descriptor, info)
{
m_Data.ValidateInputsOutputs("NeonAdditionFloatWorkload", 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();
m_AddLayer.configure(&input1, &input2, &output, arm_compute::ConvertPolicy::SATURATE);
}
void NeonAdditionFloatWorkload::Execute() const
{
ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonAdditionFloatWorkload_Execute");
m_AddLayer.run();
}
} //namespace armnn
|
