IVGCVSW-1899 : Neon backend folder structure

armnn:149855

Change-Id: I26e8cf83422a65049386a5ebdb6d0001627aefaa

1 files changed, 41 insertions, 0 deletions

diff --git a/src/backends/neon/workloads/NeonConvertFp16ToFp32Workload.cpp b/src/backends/neon/workloads/NeonConvertFp16ToFp32Workload.cpp
new file mode 100644
index 0000000000..86ec31c71d
--- /dev/null
+++ b/src/backends/neon/workloads/NeonConvertFp16ToFp32Workload.cpp
@@ -0,0 +1,41 @@
+//
+// Copyright © 2017 Arm Ltd. All rights reserved.
+// SPDX-License-Identifier: MIT
+//
+
+#include "NeonConvertFp16ToFp32Workload.hpp"
+#include "Half.hpp"
+#include "FloatingPointConverter.hpp"
+
+#include "backends/WorkloadUtils.hpp"
+
+namespace armnn
+{
+
+NeonConvertFp16ToFp32Workload::NeonConvertFp16ToFp32Workload(const ConvertFp16ToFp32QueueDescriptor& descriptor,
+                                                             const WorkloadInfo& info)
+     : Float16ToFloat32Workload<ConvertFp16ToFp32QueueDescriptor>(descriptor, info)
+{
+    this->m_Data.ValidateInputsOutputs("NeonConvertFp16ToFp32Workload", 1, 1);
+    GatherTensorHandlePairs(descriptor, m_TensorHandlePairs);
+}
+
+void NeonConvertFp16ToFp32Workload::Execute() const
+{
+    ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonConvertFp16ToFp32Workload_Execute");
+
+    auto convertFunc = [](uint8_t* dst, const uint8_t* src, size_t size)
+        {
+            auto input = reinterpret_cast<const Half*>(src);
+            auto output = reinterpret_cast<float*>(dst);
+            size_t numElements = size/2; // 2 bytes per fp16
+            armnnUtils::FloatingPointConverter::ConvertFloat16To32(input, numElements, output);
+        };
+
+    for (const auto& pair : m_TensorHandlePairs)
+    {
+        CopyTensorContentsGeneric(pair.first, pair.second, convertFunc);
+    }
+}
+
+} //namespace armnn