IVGCVSW-2957 MergerLayer subtensor optimization now backend agnostic

+ Update clframework pin
+ Cl and Neon Merger workloads updated to use MemoryLayout agnostic API
+ Workloads only use sub-tensor optimization if ALL input tensors are sub-tensors
+ Refactor LayerSupportCommon code to be a bit more succinct

Change-Id: Ib61ad4ccbd767e924dff07e61022e0cda4069828
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>

1 files changed, 14 insertions, 0 deletions

diff --git a/src/armnn/Tensor.cpp b/src/armnn/Tensor.cpp
index da19e5b97a..614abc77f5 100644
--- a/src/armnn/Tensor.cpp
+++ b/src/armnn/Tensor.cpp
@@ -188,6 +188,20 @@ unsigned int TensorInfo::GetNumBytes() const
     return GetDataTypeSize(m_DataType) * GetNumElements();
 }
 
+bool TensorInfo::IsTypeSpaceMatch(const TensorInfo& other) const
+{
+    bool match = true;
+
+    match &= m_DataType == other.m_DataType;
+
+    if (IsQuantized())
+    {
+        match &= GetQuantizationScale() == other.GetQuantizationScale() &&
+                 GetQuantizationOffset() == other.GetQuantizationOffset();
+    }
+    return match;
+}
+
 // ---
 // --- BaseTensor
 // ---