COMPMID-617: Add validate support for NEON FullyConnectedLayer

Change-Id: I08987022c8d4cc335c00b8af27bd3edb8fe64d3b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/111596
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Alexander Gilday <alexander.gilday@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>

3 files changed, 46 insertions, 26 deletions

diff --git a/arm_compute/core/NEON/kernels/NEGEMMMatrixAccumulateBiasesKernel.h b/arm_compute/core/NEON/kernels/NEGEMMMatrixAccumulateBiasesKernel.h
index 051b8b7d4f..e48a9a77e4 100644
--- a/arm_compute/core/NEON/kernels/NEGEMMMatrixAccumulateBiasesKernel.h
+++ b/arm_compute/core/NEON/kernels/NEGEMMMatrixAccumulateBiasesKernel.h
@@ -55,6 +55,14 @@ public:
      * @param[in]      biases The shared biases tensor to append. It must be 1D Tensor. Data type supported: Same as @p input
      */
     void configure(ITensor *accum, const ITensor *biases);
+    /** Static function to check if given info will lead to a valid configuration of @ref NEGEMMMatrixAccumulateBiasesKernel
+     *
+     * @param[in] accum  The accumulate tensor to convert. Data type supported: QS8/QS16/F32
+     * @param[in] biases The shared biases tensor to append. It must be 1D Tensor. Data type supported: Same as @p input
+     *
+     * @return a status
+     */
+    static Status validate(const ITensorInfo *accum, const ITensorInfo *biases);
 
     // Inherited methods overridden:
     void run(const Window &window, const ThreadInfo &info) override;
diff --git a/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h b/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h
index 4598e15b8e..d54522c678 100644
--- a/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h
+++ b/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h
@@ -58,22 +58,28 @@ public:
      * @note If the output tensor is a matrix, the input matrices @p input0 and @p input1 should be the output of the kernels: @ref NEGEMMInterleave4x4Kernel and @ref NEGEMMTranspose1xWKernel
      *       These two kernels change the layout of the original matrices to be more cache-friendly.
      *
-     * @param[in]  input0 Input tensor containing the interleaved Matrix A or the vector A. Data types supported: QS8/QS16/F16/F32
-     * @param[in]  input1 Input tensor containing the transposed Matrix B if the first input tensor A is not a vector.
-     *                    If the output tensor is a vector, input1 must contain the matrix B not reshaped. Data type supported: same as @p input0
-     * @param[out] output Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0.
-     * @param[in]  alpha  Weight of the matrix product
+     * @param[in]  input0         Input tensor containing the interleaved Matrix A or the vector A. Data types supported: QS8/QS16/F16/F32
+     * @param[in]  input1         Input tensor containing the transposed Matrix B if the first input tensor A is not a vector.
+     *                            If the output tensor is a vector, input1 must contain the matrix B not reshaped. Data type supported: same as @p input0
+     * @param[out] output         Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0.
+     * @param[in]  alpha          Weight of the matrix product
+     * @param[in]  is_interleaved (Optional) True if input0 and input1 have been reshaped respectively using @ref NEGEMMInterleave4x4Kernel and @ref NEGEMMTranspose1xWKernel
+     * @param[in]  reshape_info   (Optional) GEMM reshape info. If is_interleaved_transposed = true, this object must contain the information to understand how the matrix A and matrix B have been reshaped
      */
-    void configure(const ITensor *input0, const ITensor *input1, ITensor *output, float alpha);
+    void configure(const ITensor *input0, const ITensor *input1, ITensor *output, float alpha, bool is_interleaved, const GEMMReshapeInfo &reshape_info = GEMMReshapeInfo());
     /** Static function to check if given info will lead to a valid configuration of @ref NEGEMMMatrixMultiplyKernel
      *
-     * @param[in] input0 Input tensor containing the Matrix A. Data types supported: QS8/QS16/F16/F32
-     * @param[in] input1 Input tensor containing the Matrix B. Data type supported: same as @p input0
-     * @param[in] output Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0
+     * @param[in] input0         Input tensor containing the interleaved Matrix A or the vector A. Data types supported: QS8/QS16/F16/F32
+     * @param[in] input1         Input tensor containing the transposed Matrix B if the first input tensor A is not a vector.
+     *                           If the output tensor is a vector, input1 must contain the matrix B not reshaped. Data type supported: same as @p input0
+     * @param[in] output         Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0.
+     * @param[in] alpha          Weight of the matrix product
+     * @param[in] is_interleaved (Optional) True if input0 and input1 have been reshaped respectively using @ref NEGEMMInterleave4x4Kernel and @ref NEGEMMTranspose1xWKernel
+     * @param[in] reshape_info   (Optional) GEMM reshape info. If is_interleaved_transposed = true, this object must contain the information to understand how the matrix A and matrix B have been reshaped
      *
      * @return a status
      */
-    static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *output);
+    static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *output, float alpha, bool is_interleaved, const GEMMReshapeInfo &reshape_info);
 
     // Inherited methods overridden:
     void run(const Window &window, const ThreadInfo &info) override;
diff --git a/arm_compute/core/NEON/kernels/NEIm2ColKernel.h b/arm_compute/core/NEON/kernels/NEIm2ColKernel.h
index 6d11fbee11..1659b725bb 100644
--- a/arm_compute/core/NEON/kernels/NEIm2ColKernel.h
+++ b/arm_compute/core/NEON/kernels/NEIm2ColKernel.h
@@ -76,28 +76,34 @@ public:
 
     /** Set the input and output of the kernel.
      *
-     * @param[in]  input       The input tensor to convert. 3 lower dimensions represent a single input [width, height, IFM],
-     *                         while every optional dimension from 4 and above represent a batch of inputs. Data types supported: QS8/QS16/QASYMM8/F16/F32
-     *                         Note: QASYMM8 works only for has_bias = false
-     * @param[out] output      The output tensor. Data types supported: Same as @p input
-     * @param[in]  kernel_dims The kernel dimensions (width and height).
-     * @param[in]  conv_info   Contains padding and stride information described in @ref PadStrideInfo.
-     * @param[in]  has_bias    In case biases are provided expands the matrix with 1.
+     * @param[in]  input              The input tensor to convert. 3 lower dimensions represent a single input [width, height, IFM],
+     *                                while every optional dimension from 4 and above represent a batch of inputs. Data types supported: QS8/QS16/QASYMM8/F16/F32
+     *                                Note: QASYMM8 works only for has_bias = false
+     * @param[out] output             The output tensor. Data types supported: Same as @p input
+     * @param[in]  kernel_dims        The kernel dimensions (width and height).
+     * @param[in]  conv_info          Contains padding and stride information described in @ref PadStrideInfo.
+     * @param[in]  has_bias           In case biases are provided expands the matrix with 1.
+     * @param[in]  is_fully_connected Determines whether this kernel will be called by @ref NEFullyConnectedLayer in order to validate the arguments
+     * @param[in]  is_flatten         (Optional) Determines whether this kernel will be called by @ref NEFlattenLayer in order to validate the arguments
      */
-    void configure(const ITensor *input, ITensor *output, const Size2D &kernel_dims, const PadStrideInfo &conv_info, bool has_bias);
+    void configure(const ITensor *input, ITensor *output, const Size2D &kernel_dims, const PadStrideInfo &conv_info,
+                   bool has_bias, bool is_fully_connected = false, bool is_flatten = false);
     /** Static function to check if given info will lead to a valid configuration of @ref NEIm2ColKernel
      *
-     * @param[in] input       The input tensor to convert. 3 lower dimensions represent a single input [width, height, IFM],
-     *                        while every optional dimension from 4 and above represent a batch of inputs. Data types supported: QS8/QS16/QASYMM8/F16/F32
-     *                        Note: QASYMM8 works only for has_bias = false
-     * @param[in] output      The output tensor. Data types supported: Same as @p input
-     * @param[in] kernel_dims The kernel dimensions (width and height).
-     * @param[in] conv_info   Contains padding and stride information described in @ref PadStrideInfo.
-     * @param[in] has_bias    In case biases are provided expands the matrix with 1.
+     * @param[in] input              The input tensor to convert. 3 lower dimensions represent a single input [width, height, IFM],
+     *                               while every optional dimension from 4 and above represent a batch of inputs. Data types supported: QS8/QS16/QASYMM8/F16/F32
+     *                               Note: QASYMM8 works only for has_bias = false
+     * @param[in] output             The output tensor. Data types supported: Same as @p input
+     * @param[in] kernel_dims        The kernel dimensions (width and height).
+     * @param[in] conv_info          Contains padding and stride information described in @ref PadStrideInfo.
+     * @param[in] has_bias           In case biases are provided expands the matrix with 1.
+     * @param[in] is_fully_connected Determines whether this kernel will be called by @ref NEFullyConnectedLayer in order to validate the arguments
+     * @param[in] is_flatten         (Optional) Determines whether this kernel will be called by @ref NEFlattenLayer in order to validate the arguments
      *
      * @return a status
      */
-    static Status validate(const ITensorInfo *input, const ITensorInfo *output, const Size2D &kernel_dims, const PadStrideInfo &conv_info, bool has_bias);
+    static Status validate(const ITensorInfo *input, const ITensorInfo *output, const Size2D &kernel_dims, const PadStrideInfo &conv_info,
+                           bool has_bias, bool is_fully_connected, bool is_flatten = false);
 
     // Inherited methods overridden:
     void run(const Window &window, const ThreadInfo &info) override;