Update Neon™ pooling kernel

- Reduce duplication and simplify overall structure.
- Improve multi-threaded performance by sharing more data
  in lower-level caches.

Partially Resolves: COMPMID-5054
Signed-off-by: Ramy Elgammal<ramy.elgammal@arm.com>
Change-Id: I5f4dc50913401d5c1cbfc10b866fae9490cbc4d7
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7404
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Andrew Mundy
Reviewed-by: Sheri Zhang <sheri.zhang@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 10 insertions, 12 deletions

diff --git a/src/core/NEON/kernels/assembly/pool_common.hpp b/src/core/NEON/kernels/assembly/pool_common.hpp
index b6a0a0abed..599e18ac59 100644
--- a/src/core/NEON/kernels/assembly/pool_common.hpp
+++ b/src/core/NEON/kernels/assembly/pool_common.hpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021 Arm Limited.
+ * Copyright (c) 2021-2022 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -23,8 +23,9 @@
  */
 
 #pragma once
-
-#include "common.hpp"
+#ifdef CYCLE_PROFILING
+#include "profiler.hpp"
+#endif
 
 namespace arm_conv
 {
@@ -53,6 +54,11 @@ struct PoolingStride
     unsigned int rows, cols;
 };
 
+struct PaddingValues
+{
+    unsigned int left, top, right, bottom;
+};
+
 class IPoolingCommon
 {
 public:
@@ -60,6 +66,7 @@ public:
 
     // Determine the amount of working space required.
     virtual size_t get_working_size(unsigned int num_threads) const = 0;
+    virtual size_t get_working_size(unsigned int num_threads, unsigned int n_channels) const = 0;
 
     // Execute pooling over the specified area of memory.
     virtual void execute(
@@ -103,14 +110,5 @@ public:
         unsigned int num_threads) const = 0;
 };
 
-struct Nothing
-{
-};
-
-template <typename TInput, typename TOutput, class OutputStage = Nothing>
-class PoolingCommon : public IPoolingCommon
-{
-};
-
 } // namespace pooling
 } // namespace arm_conv