commit b7e5f53607829c865a11adf8763969399f04515c
author Cathal Corbett <cathal.corbett@arm.com> Fri Jul 22 16:03:36 2022 +0100
committer Cathal Corbett <cathal.corbett@arm.com> Fri Jul 29 09:50:20 2022 +0000
tree 6842e15904037d73426d814d5751945b3d9c2376
parent 4d3298e21e5bc07bb71cf421d514034b23851bab

GitHub #667: Neon fold padding into average pool 2D quantization bug fix.

  * Originated from a GitHub issue: https://github.com/ARM-software/armnn/issues/667
  * Initially, Arm NN supports the pool 2D operation because there is no padding
    on the pool2d. Neon failure occurs when padding is followed by average pool 2D
    due to folding optimization.
  * Here we prevent the folding optimization from happening for the above special case
    and add it in as a backend specific optimization.

Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ia0fd90c3a6b4b9d29c81106f154617d2e893e26b

src/backends/reference/RefBackend.hpp

diff --git a/src/backends/reference/RefBackend.hpp b/src/backends/reference/RefBackend.hpp
index 9828d09..ecbe4d5 100644
--- a/src/backends/reference/RefBackend.hpp
+++ b/src/backends/reference/RefBackend.hpp
@@ -50,7 +50,8 @@
 
     IBackendInternal::ILayerSupportSharedPtr GetLayerSupport() const override;
 
-    OptimizationViews OptimizeSubgraphView(const SubgraphView& subgraph) const override;
+    OptimizationViews OptimizeSubgraphView(const SubgraphView& subgraph,
+                                           const ModelOptions& modelOptions) const override;
 
     std::vector<ITensorHandleFactory::FactoryId> GetHandleFactoryPreferences() const override;