Add fp16 support for dequantize

* Changed RefDequantizeWorkload to use Encoder/Decoder
* Added related unit tests for Cl, Neon and Ref

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ic2fd4103090dd2127c6859b49305736f7b2dfb05
diff --git a/src/backends/reference/RefLayerSupport.cpp b/src/backends/reference/RefLayerSupport.cpp
index 5972158..716e8d9 100644
--- a/src/backends/reference/RefLayerSupport.cpp
+++ b/src/backends/reference/RefLayerSupport.cpp
@@ -587,8 +587,9 @@
     supported &= CheckSupportRule(TypeAnyOf(input, supportedInputTypes), reasonIfUnsupported,
                                   "Reference dequantize: input type not supported.");
 
-    std::array<DataType,1> supportedOutputTypes = {
-        DataType::Float32
+    std::array<DataType,2> supportedOutputTypes = {
+        DataType::Float32,
+        DataType::Float16
     };
 
     supported &= CheckSupportRule(TypeAnyOf(output, supportedOutputTypes), reasonIfUnsupported,