diff --git a/src/backends/cl/workloads/ClConvertFp16ToFp32Workload.hpp b/src/backends/cl/workloads/ClConvertFp16ToFp32Workload.hpp
new file mode 100644
index 0000000..b644748
--- /dev/null
+++ b/src/backends/cl/workloads/ClConvertFp16ToFp32Workload.hpp
@@ -0,0 +1,30 @@
+//
+// Copyright © 2017 Arm Ltd. All rights reserved.
+// SPDX-License-Identifier: MIT
+//
+
+#pragma once
+
+#include <backends/Workload.hpp>
+
+#include <arm_compute/runtime/CL/CLFunctions.h>
+
+namespace armnn
+{
+
+class ClConvertFp16ToFp32Workload : public Float16ToFloat32Workload<ConvertFp16ToFp32QueueDescriptor>
+{
+public:
+
+    ClConvertFp16ToFp32Workload(const ConvertFp16ToFp32QueueDescriptor& descriptor, const WorkloadInfo& info);
+    virtual void Execute() const override;
+
+private:
+    mutable arm_compute::CLDepthConvertLayer m_Layer;
+};
+
+arm_compute::Status ClConvertFp16ToFp32WorkloadValidate(const TensorInfo& input,
+                                                        const TensorInfo& output,
+                                                        std::string* reasonIfUnsupported);
+
+} //namespace armnn