IVGCVSW-3845 Add Reference FP16 support for required layers

* Working on layers required by FSRCNN, FCRN and DeepSpeaker
* Updates RefLayerSupport and RefWorkloadFactory methods
* Adds RefPadFloat16Workload
* Tested by successful execution of these networks on Reference FP16 backend

Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: I4817dca0a89bba6902f0feffc494b27a26a0ab2d

1 files changed, 6 insertions, 0 deletions

diff --git a/src/backends/reference/workloads/Pad.cpp b/src/backends/reference/workloads/Pad.cpp
index 5773cac6a8..42291b8661 100644
--- a/src/backends/reference/workloads/Pad.cpp
+++ b/src/backends/reference/workloads/Pad.cpp
@@ -158,6 +158,12 @@ template void Pad<float>(const TensorInfo& inputInfo,
                          const float* inputData,
                          float* outData,
                          const float padValue);
+template void Pad<Half>(const TensorInfo& inputInfo,
+                        const TensorInfo& outputInfo,
+                        std::vector<std::pair<unsigned int, unsigned int>> m_PadList,
+                        const Half* inputData,
+                        Half* outData,
+                        const float padValue);
 template void Pad<uint8_t>(const TensorInfo& inputInfo,
                            const TensorInfo& outputInfo,
                            std::vector<std::pair<unsigned int, unsigned int>> m_PadList,