IVGCVSW-5843 Separate memory managers for WorkingMemHandles

 * Add inter layer memory management to WorkingMemHandle
 * Change Const layers to be executed once in loadedNetworkConstruction
   and share tensorHandle between all WorkingMemHandles
 * Fix various reference workloads pointing to memory in the queueDescriptor

Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I69d4b3c5c84d2f5abe4540c3e624ab4f00d88226

1 files changed, 5 insertions, 0 deletions

diff --git a/src/backends/backendsCommon/TensorHandleFactoryRegistry.hpp b/src/backends/backendsCommon/TensorHandleFactoryRegistry.hpp
index f926478432..e9e76e73a6 100644
--- a/src/backends/backendsCommon/TensorHandleFactoryRegistry.hpp
+++ b/src/backends/backendsCommon/TensorHandleFactoryRegistry.hpp
@@ -41,6 +41,11 @@ public:
     /// Release memory required for inference
     void ReleaseMemory();
 
+    std::vector<std::shared_ptr<IMemoryManager>>& GetMemoryManagers()
+    {
+        return m_MemoryManagers;
+    }
+
 private:
     std::vector<std::unique_ptr<ITensorHandleFactory>> m_Factories;
     std::vector<std::shared_ptr<IMemoryManager>> m_MemoryManagers;