Add support for 2d and 3d indices for axis 1

* Resolves COMPMID-5055

Change-Id: I2d14de29d3ec913d20c971bc8bbc9ad71e2d998f
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7547
Reviewed-by: SiCong Li <sicong.li@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>

2 files changed, 49 insertions, 12 deletions

diff --git a/arm_compute/core/utils/misc/ShapeCalculator.h b/arm_compute/core/utils/misc/ShapeCalculator.h
index df907c106e..9f9f53ed8b 100644
--- a/arm_compute/core/utils/misc/ShapeCalculator.h
+++ b/arm_compute/core/utils/misc/ShapeCalculator.h
@@ -1494,15 +1494,53 @@ inline TensorShape compute_pool3d_shape(const TensorShape &src, Pooling3dLayerIn
     return output_shape;
 }
 
+/** Calculate the gather output shape of a tensor
+ *
+ * @param[in] input_shape   Input tensor shape
+ * @param[in] indices_shape Indices tensor shape. Only supports for 2d and 3d indices
+ * @param[in] actual_axis   Axis to be used in the computation
+ *
+ * @note Let input_shape be (X,Y,Z) and indices shape (W,O,P) and axis 1
+ *       the new shape is computed by replacing the axis in the input shape with
+ *       the indice shape so the output shape will be (X,W,O,P,Z)
+ *
+ * @return the calculated shape
+ */
 inline TensorShape compute_gather_shape(const TensorShape &input_shape, const TensorShape &indices_shape, uint32_t actual_axis)
 {
-    ARM_COMPUTE_ERROR_ON(indices_shape.num_dimensions() > 1);
     ARM_COMPUTE_ERROR_ON(input_shape.num_dimensions() > 4);
     ARM_COMPUTE_ERROR_ON(actual_axis >= input_shape.num_dimensions());
-
-    TensorShape output_shape  = input_shape;
-    output_shape[actual_axis] = indices_shape[0];
-
+    ARM_COMPUTE_ERROR_ON(indices_shape.num_dimensions() > 3);
+    TensorShape output_shape = input_shape;
+    if(indices_shape.num_dimensions() == 1u)
+    {
+        output_shape[actual_axis] = indices_shape[0];
+    }
+    else
+    {
+        const auto ind_num_dims
+        {
+            indices_shape.num_dimensions()
+        };
+        output_shape.shift_right(ind_num_dims - 1);
+        switch(actual_axis)
+        {
+            case 1:
+            {
+                output_shape[0] = input_shape[0];
+                for(size_t idx = 0; idx < ind_num_dims; ++idx)
+                {
+                    output_shape.set(actual_axis + idx, indices_shape[idx], false);
+                }
+                break;
+            }
+            default:
+            {
+                // 2d and 3d indices are only supported for axis == 1
+                ARM_COMPUTE_ERROR_ON(actual_axis != 1 && indices_shape.num_dimensions() > 1);
+            }
+        }
+    }
     return output_shape;
 }
 } // namespace shape_calculator
diff --git a/arm_compute/runtime/NEON/functions/NEGather.h b/arm_compute/runtime/NEON/functions/NEGather.h
index 393a38ee4d..8253e986df 100644
--- a/arm_compute/runtime/NEON/functions/NEGather.h
+++ b/arm_compute/runtime/NEON/functions/NEGather.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2021 Arm Limited.
+ * Copyright (c) 2019-2022 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -49,18 +49,17 @@ public:
      * |All            |All            |
      *
      * @param[in]  input   Source tensor. Supported tensor rank: up to 4. Data type supported: All
-     * @param[in]  indices Indices tensor. Supported tensor rank: up to 1. Must be one of the following type: U32/S32. Each value Must be in range [0, input.shape[@p axis])
+     * @param[in]  indices Indices tensor. Supported tensor rank: up to 3. Must be one of the following type: U32/S32. Each value Must be in range [0, input.shape[@p axis])
+     *                     @note The "axis" must be in the range [0, input.rank -1] when indices is a vector, and must be 1 when indices is a 2D or 3D tensor.
      * @param[out] output  Destination tensor. Data type supported: Same as @p input
      * @param[in]  axis    (Optional) The axis in @p input to gather @p indices from. Defaults to 0
+     *
      */
     void configure(const ITensor *input, const ITensor *indices, ITensor *output, int axis = 0);
 
-    /** Static function to check if given info will lead to a valid configuration of @ref NEGatherKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] input   Source tensor info. Supported tensor rank: up to 4. Data type supported: All
-     * @param[in] indices Indices tensor info. Supported tensor rank: up to 1. Must be one of the following types: U32/S32. Each value Must be in range [0, input.shape[@p axis])
-     * @param[in] output  Destination tensor info. Data type supported: Same as @p input
-     * @param[in] axis    (Optional) The axis in @p input to gather @p indices from. Defaults to 0
+     * Similar to @ref NEGather::configure()
      *
      * @return a status
      */