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
49
50
51
52
53
54
55
56
57
58
59
60
|
//
// Copyright © 2017 Arm Ltd. All rights reserved.
// See LICENSE file in the project root for full license information.
//
#include "NeonMultiplicationFloat32Workload.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);
}
NeonMultiplicationFloat32Workload::NeonMultiplicationFloat32Workload(const MultiplicationQueueDescriptor& descriptor,
const WorkloadInfo& info)
: FloatWorkload<MultiplicationQueueDescriptor>(descriptor, info)
{
m_Data.ValidateInputsOutputs("NeonMultiplicationFloat32Workload", 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 NeonMultiplicationFloat32Workload::Execute() const
{
ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonMultiplicationFloat32Workload_Execute");
m_PixelWiseMultiplication.run();
}
} //namespace armnn
|
