Add support for 2d and 3d indices for axis 0

* Partially resolves COMPMID-5055

Change-Id: Id05374b8c69e6b9ab4c2790a4de93d7172063b71

Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Change-Id: Ic6e2c2d1d34abbf6222c8d56859514e267447266
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7488
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/core/NEON/kernels/NEGatherKernel.h b/src/core/NEON/kernels/NEGatherKernel.h
index 0711f81..fc0e678 100644
--- a/src/core/NEON/kernels/NEGatherKernel.h
+++ b/src/core/NEON/kernels/NEGatherKernel.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2021 Arm Limited.
+ * Copyright (c) 2019-2022 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -85,18 +85,23 @@
      *
      * For gather on the 0 axis an element by element copy is performed.
      *
-     * @param[in] window Region on which to execute the kernel. (Must be a region of the window returned by window())
-     * @param[in] info   Info about executing thread and CPU.
+     * @param[in] window Region on which to run the kernel. (Must be a region of the window returned by window())
+     * @param[in] info   Info about running thread and CPU.
      */
     template <typename U>
     void gather_0_axis(const Window &window, const ThreadInfo &info);
 
+    template <typename U>
+    void gather_dims_0_axis(const Window &window, const ThreadInfo &info);
+
+    template <typename U>
+    void gather_dims_n_axis(const Window &window, const ThreadInfo &info);
     /** Implementation of the gather operation.
      *
      * For 1<=axis a row-wise copy is taking place.
      *
-     * @param[in] window Region on which to execute the kernel. (Must be a region of the window returned by window())
-     * @param[in] info   Info about executing thread and CPU.
+     * @param[in] window Region on which to run the kernel. (Must be a region of the window returned by window())
+     * @param[in] info   Info about running thread and CPU.
      */
     template <typename U>
     void gather_n_axis(const Window &window, const ThreadInfo &info);