COMPMID-2338: Remove CLGEMMInterleave4x4 and CLGEMMTranspose1xW

Change-Id: I527fc97eac51308de601e5d1d50e75e4d89c5ee5
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1158
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

4 files changed, 2 insertions, 190 deletions

diff --git a/arm_compute/core/CL/CLKernels.h b/arm_compute/core/CL/CLKernels.h
index 70ffe3030b..57e0ade7da 100644
--- a/arm_compute/core/CL/CLKernels.h
+++ b/arm_compute/core/CL/CLKernels.h
@@ -73,7 +73,6 @@
 #include "arm_compute/core/CL/kernels/CLFlattenLayerKernel.h"
 #include "arm_compute/core/CL/kernels/CLFloorKernel.h"
 #include "arm_compute/core/CL/kernels/CLFuseBatchNormalizationKernel.h"
-#include "arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.h"
@@ -92,7 +91,6 @@
 #include "arm_compute/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMReshapeLHSMatrixKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMReshapeRHSMatrixKernel.h"
-#include "arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h"
 #include "arm_compute/core/CL/kernels/CLGatherKernel.h"
 #include "arm_compute/core/CL/kernels/CLGaussian3x3Kernel.h"
 #include "arm_compute/core/CL/kernels/CLGaussian5x5Kernel.h"
diff --git a/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h b/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h
deleted file mode 100644
index 96b01b0237..0000000000
--- a/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * Copyright (c) 2017-2018 ARM Limited.
- *
- * SPDX-License-Identifier: MIT
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to
- * deal in the Software without restriction, including without limitation the
- * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
- * sell copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in all
- * copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-#ifndef __ARM_COMPUTE_CLGEMMINTERLEAVE4X4KERNEL_H__
-#define __ARM_COMPUTE_CLGEMMINTERLEAVE4X4KERNEL_H__
-
-#include "arm_compute/core/CL/ICLKernel.h"
-
-namespace arm_compute
-{
-class ICLTensor;
-
-/** OpenCL kernel which interleaves the elements of a matrix A in chunk of 4x4
- *
- * This function puts the values in a 4x4 block of Matrix A on the same row (Interleaved values)
- *
- * @f[
- * \left( \begin{array}{cccc}
- * a00 & a01 & a02 & a03 \\
- * a10 & a11 & a12 & a13 \\
- * a20 & a21 & a22 & a23 \\
- * a30 & a31 & a32 & a33 \\
- * \end{array} \right)
- * \rightarrow
- * \left( \begin{array}{ccccccccccccccccc}
- * a00 & a10 & a20 & a30 & a01 & a11 & a21 & a31 & a02 & a12 & a22 & a32 & a03 & a13 & a23 & a33 \\
- * \end{array} \right)
- * @f]
- *
- * After this operation, the output matrix will have the following shape: [ height * W, ceil(width / W) ] where W = 4 * mult_interleave4x4_height
- */
-class CLGEMMInterleave4x4Kernel : public ICLKernel
-{
-public:
-    /** Default constructor */
-    CLGEMMInterleave4x4Kernel();
-    /** Prevent instances of this class from being copied (As this class contains pointers) */
-    CLGEMMInterleave4x4Kernel(const CLGEMMInterleave4x4Kernel &) = delete;
-    /** Prevent instances of this class from being copied (As this class contains pointers) */
-    CLGEMMInterleave4x4Kernel &operator=(const CLGEMMInterleave4x4Kernel &) = delete;
-    /** Allow instances of this class to be moved */
-    CLGEMMInterleave4x4Kernel(CLGEMMInterleave4x4Kernel &&) = default;
-    /** Allow instances of this class to be moved */
-    CLGEMMInterleave4x4Kernel &operator=(CLGEMMInterleave4x4Kernel &&) = default;
-    /** Initialise the kernel's input and output.
-     *
-     * @param[in]  input                     Input tensor. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
-     * @param[out] output                    Output tensor. Data type supported: same as @p input
-     * @param[in]  mult_interleave4x4_height (Optional) Multiplication factor for the height of the 4x4 interleave block
-     * @param[in]  reinterpret_input_as_3d   (Optional) True if the input has to be reinterpreted as 3D tensor
-     * @param[in]  unroll_block              (Optional) True if the 4x4 block has to be unrolled rather than transposed
-     */
-    void configure(const ICLTensor *input, ICLTensor *output, int mult_interleave4x4_height = 1, bool reinterpret_input_as_3d = false, bool unroll_block = false);
-    /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMInterleave4x4Kernel
-     *
-     * @param[in] input                     Input tensor info. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
-     * @param[in] output                    Output tensor info which stores the interleaved matrix. Data type supported: same as @p input.
-     * @param[in] mult_interleave4x4_height Multiplication factor for the height of the 4x4 interleave block
-     * @param[in] reinterpret_input_as_3d   True if the input has to be reinterpreted as 3D tensor
-     *
-     * @return a status
-     */
-    static Status validate(const ITensorInfo *input, const ITensorInfo *output, int mult_interleave4x4_height, bool reinterpret_input_as_3d);
-
-    // Inherited methods overridden
-    void run(const Window &window, cl::CommandQueue &queue) override;
-
-private:
-    const ICLTensor *_input;
-    ICLTensor       *_output;
-    bool             _reinterpret_input_as_3d;
-};
-} // namespace arm_compute
-#endif /* __ARM_COMPUTE_CLGEMMINTERLEAVE4X4KERNEL_H__ */
diff --git a/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h b/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h
index 616c269b0d..e576271780 100644
--- a/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h
@@ -58,7 +58,7 @@ public:
      * @param[in]  input0                    Input tensor containing the interleaved Matrix A. Data type supported: QASYMM8
      * @param[in]  input1                    Input tensor containing the transposed1xW Matrix B. Data type supported: same as @p input0
      * @param[out] output                    Output tensor to store the result of matrix multiplication. Data type supported: S32
-     * @param[in]  is_interleaved_transposed (Optional) True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMReshapeRHSMatrixKernel
+     * @param[in]  is_interleaved_transposed (Optional) True if input0 and input1 have been reshaped respectively using @ref CLGEMMReshapeLHSMatrixKernel and @ref CLGEMMReshapeRHSMatrixKernel
      * @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 ICLTensor *input0, const ICLTensor *input1, ICLTensor *output, bool is_interleaved_transposed = true, const GEMMReshapeInfo &reshape_info = GEMMReshapeInfo());
@@ -67,7 +67,7 @@ public:
      * @param[in] input0                    Input tensor info containing the interleaved Matrix A. Data type supported: QASYMM8
      * @param[in] input1                    Input tensor info containing the transposed Matrix B. Data type supported: same as @p input0
      * @param[in] output                    Output tensor info to store the result of matrix multiplication. Data type supported: S32
-     * @param[in] is_interleaved_transposed True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMReshapeRHSMatrixKernel
+     * @param[in] is_interleaved_transposed True if input0 and input1 have been reshaped respectively using @ref CLGEMMReshapeLHSMatrixKernel and @ref CLGEMMReshapeRHSMatrixKernel
      * @param[in] reshape_info              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
diff --git a/arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h b/arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h
deleted file mode 100644
index 47a4ad515b..0000000000
--- a/arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h
+++ /dev/null
@@ -1,92 +0,0 @@
-/*
- * Copyright (c) 2017-2018 ARM Limited.
- *
- * SPDX-License-Identifier: MIT
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to
- * deal in the Software without restriction, including without limitation the
- * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
- * sell copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in all
- * copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-#ifndef __ARM_COMPUTE_CLGEMMTRANSPOSE1XWKERNEL_H__
-#define __ARM_COMPUTE_CLGEMMTRANSPOSE1XWKERNEL_H__
-
-#include "arm_compute/core/CL/ICLSimple2DKernel.h"
-
-namespace arm_compute
-{
-class ICLTensor;
-
-/** OpenCL kernel which transposes the elements of a matrix in chunks of 1xW, where W is equal to (16 / element size of the tensor)
- *
- * Following an example of how the transposition1xW works when the input data type is F32
- *
- * @f[
- * \left( \begin{array}{cccc}
- * a00 & a01 & a02 & a03 \\
- * a10 & a11 & a12 & a13 \\
- * a20 & a21 & a22 & a23 \\
- * a30 & a31 & a32 & a33 \\
- * \end{array} \right)
- * \rightarrow
- * \left( \begin{array}{ccccccccccccccccc}
- * a00 & a01 & a02 & a03 & a10 & a11 & a12 & a13 & a20 & a21 & a22 & a23 & a30 & a31 & a32 & a33 \\
- * \end{array} \right)
- * @f]
- *
- * Following an example of how the transposition1xW works when the input data type is F16
- *
- * @f[
- * \left( \begin{array}{cccccccc}
- * a00 & a01 & a02 & a03 & a04 & a05 & a06 & a7 \\
- * a10 & a11 & a12 & a13 & a14 & a15 & a16 & 17 \\
- * a20 & a21 & a22 & a23 & a24 & a25 & a26 & 27 \\
- * a30 & a31 & a32 & a33 & a34 & a35 & a36 & 37 \\
- * \end{array} \right)
- * \rightarrow
- * \left( \begin{array}{cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc}
- * a00 & a01 & a02 & a03 & a04 & a05 & a06 & a07 & a10 & a11 & a12 & a13 & a14 & a15 & a16 & a17 & a20 & a21 & a22 & a23 & a24 & a25 & a26 & a27 & a30 & a31 & a32 & a33 & a34 & a35 & a36 & a37\\
- * \end{array} \right)
- * @f]
- *
- * @note The output matrix will have the following shape: [ height * W, ceil(width / W) ], where W = (16 / element size of the tensor) * mult_transpose1xW_width
- *
- */
-class CLGEMMTranspose1xWKernel : public ICLSimple2DKernel
-{
-public:
-    /** Initialise the kernel's input and output.
-     *
-     * @param[in]  input                   Input tensor. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
-     * @param[out] output                  Output tensor. Data type supported: same as @p input
-     * @param[in]  mult_transpose1xW_width (Optional) Multiplication factor for the width of the 1xW transposed block
-     */
-    void configure(const ICLTensor *input, ICLTensor *output, int mult_transpose1xW_width = 1);
-    /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMTranspose1xWKernel
-     *
-     * @param[in] input                   Input tensor. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
-     * @param[in] output                  Output tensor. Data type supported: same as @p input.
-     * @param[in] mult_transpose1xW_width Multiplication factor for the width of the 1xW transposed block
-     *
-     * @return a status
-     */
-    static Status validate(const ITensorInfo *input, const ITensorInfo *output, int mult_transpose1xW_width);
-
-    // Inherited methods overridden:
-    void run(const Window &window, cl::CommandQueue &queue) override;
-};
-} // namespace arm_compute
-#endif /* __ARM_COMPUTE_CLGEMMTRANSPOSE1XWKERNEL_H__ */