1 files changed, 43 insertions, 0 deletions
diff --git a/src/armnn/backends/NeonWorkloads/NeonConvertFp32ToFp16Workload.cpp b/src/armnn/backends/NeonWorkloads/NeonConvertFp32ToFp16Workload.cpp
new file mode 100644
index 0000000000..61f30522a8
--- /dev/null
+++ b/src/armnn/backends/NeonWorkloads/NeonConvertFp32ToFp16Workload.cpp
@@ -0,0 +1,43 @@
+//
+// Copyright © 2017 Arm Ltd. All rights reserved.
+// See LICENSE file in the project root for full license information.
+//
+
+#include "NeonConvertFp32ToFp16Workload.hpp"
+
+#include "Half.hpp"
+#include "FloatingPointConverter.hpp"
+
+#include "Profiling.hpp"
+#include "backends/WorkloadUtils.hpp"
+
+namespace armnn
+{
+
+NeonConvertFp32ToFp16Workload::NeonConvertFp32ToFp16Workload(const ConvertFp32ToFp16QueueDescriptor& descriptor,
+                                                             const WorkloadInfo& info)
+    : Float32ToFloat16Workload<ConvertFp32ToFp16QueueDescriptor>(descriptor, info)
+{
+    this->m_Data.ValidateInputsOutputs("NeonConvertFp32ToFp16Workload", 1, 1);
+    GatherTensorHandlePairs(descriptor, m_TensorHandlePairs);
+}
+
+void NeonConvertFp32ToFp16Workload::Execute() const
+{
+    ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonConvertFp32ToFp16Workload_Execute");
+
+    auto convertFunc = [](uint8_t* dst, const uint8_t* src, size_t size)
+        {
+            auto input = reinterpret_cast<const float*>(src);
+            auto output = reinterpret_cast<Half*>(dst);
+            size_t numElements = size/2; // 2 bytes per fp16
+            armnnUtils::FloatingPointConverter::ConvertFloat32To16(input, numElements, output);
+        };
+
+    for (const auto& pair : m_TensorHandlePairs)
+    {
+        CopyTensorContentsGeneric(pair.first, pair.second, convertFunc);
+    }
+}
+
+} //namespace armnn