blob: 027b508ad5b09750d7dfa01c659197890ea5ec44 (
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
|
//
// Copyright © 2017 Arm Ltd. All rights reserved.
// See LICENSE file in the project root for full license information.
//
#include "NeonSoftmaxFloat32Workload.hpp"
namespace armnn
{
NeonSoftmaxFloat32Workload::NeonSoftmaxFloat32Workload(const SoftmaxQueueDescriptor& descriptor,
const WorkloadInfo& info, std::shared_ptr<arm_compute::MemoryManagerOnDemand>& memoryManager)
: FloatWorkload<SoftmaxQueueDescriptor>(descriptor, info)
, m_SoftmaxLayer(memoryManager)
{
m_Data.ValidateInputsOutputs("NeonSoftmaxFloat32Workload", 1, 1);
// The ArmCompute softmax layer uses 2D input/output tensors, so flatten the first three dimensions.
arm_compute::ITensor& input = boost::polymorphic_downcast<INeonTensorHandle*>(m_Data.m_Inputs[0])->GetTensor();
arm_compute::ITensor& output = boost::polymorphic_downcast<INeonTensorHandle*>(m_Data.m_Outputs[0])->GetTensor();
m_SoftmaxLayer.configure(&input, &output, m_Data.m_Parameters.m_Beta);
}
void NeonSoftmaxFloat32Workload::Execute() const
{
ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonSoftmaxFloat32Workload_Execute");
m_SoftmaxLayer.run();
}
} //namespace armnn
|
