APPBROWSER-400: Implement the tensorshift kernel for fixing DC's alignment issue on OpenGL ES

Change-Id: I7a8489bb0fddc72899ea165e414ee87bdbfb45b3
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/118106
Reviewed-by: Joel Liang <joel.liang@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>

2 files changed, 84 insertions, 0 deletions

diff --git a/arm_compute/core/GLES_COMPUTE/GCKernels.h b/arm_compute/core/GLES_COMPUTE/GCKernels.h
index a1f3c278c4..40312d121a 100644
--- a/arm_compute/core/GLES_COMPUTE/GCKernels.h
+++ b/arm_compute/core/GLES_COMPUTE/GCKernels.h
@@ -47,6 +47,7 @@
 #include "arm_compute/core/GLES_COMPUTE/kernels/GCPoolingLayerKernel.h"
 #include "arm_compute/core/GLES_COMPUTE/kernels/GCScaleKernel.h"
 #include "arm_compute/core/GLES_COMPUTE/kernels/GCSoftmaxLayerKernel.h"
+#include "arm_compute/core/GLES_COMPUTE/kernels/GCTensorShiftKernel.h"
 #include "arm_compute/core/GLES_COMPUTE/kernels/GCTransposeKernel.h"
 #include "arm_compute/core/GLES_COMPUTE/kernels/GCWeightsReshapeKernel.h"
 
diff --git a/arm_compute/core/GLES_COMPUTE/kernels/GCTensorShiftKernel.h b/arm_compute/core/GLES_COMPUTE/kernels/GCTensorShiftKernel.h
new file mode 100644
index 0000000000..5f108764b4
--- /dev/null
+++ b/arm_compute/core/GLES_COMPUTE/kernels/GCTensorShiftKernel.h
@@ -0,0 +1,83 @@
+/*
+ * 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_GCTENSORSHIFTKERNEL_H__
+#define __ARM_COMPUTE_GCTENSORSHIFTKERNEL_H__
+
+#include "arm_compute/core/GLES_COMPUTE/IGCKernel.h"
+#include "arm_compute/core/GLES_COMPUTE/OpenGLES.h"
+
+namespace arm_compute
+{
+class IGCTensor;
+/** Interface for the kernel to shift valid data on a tensor.
+ *
+ * For example shifting 3x3 valid data with padding of 1 to right:
+ * @f[
+ * \left( \begin{array}{ccccc}
+ * 0   & 0   & 0   & 0 & 0 \\
+ * a00 & a01 & a02 & 0 & 0 \\
+ * a10 & a11 & a12 & 0 & 0 \\
+ * a20 & a21 & a22 & 0 & 0 \\
+ * 0   & 0   & 0   & 0 & 0 \\
+ * \end{array} \right)
+ * =
+ * \left( \begin{array}{ccccc}
+ * 0  & 0   & 0   & 0   & 0 \\
+ * 0  & a00 & a01 & a02 & 0 \\
+ * 0  & a10 & a11 & a12 & 0 \\
+ * 0  & a20 & a21 & a22 & 0 \\
+ * 0  & 0   & 0   & 0   & 0 \\
+ * \end{array} \right)
+ * @f]
+ */
+class GCTensorShiftKernel : public IGCKernel
+{
+public:
+    /** Default constructor */
+    GCTensorShiftKernel();
+    /** Prevent instances of this class from being copied (As this class contains pointers) */
+    GCTensorShiftKernel(const GCTensorShiftKernel &) = delete;
+    /** Prevent instances of this class from being copied (As this class contains pointers) */
+    GCTensorShiftKernel &operator=(const GCTensorShiftKernel &) = delete;
+    /** Allow instances of this class to be moved */
+    GCTensorShiftKernel(GCTensorShiftKernel &&) = default;
+    /** Allow instances of this class to be moved */
+    GCTensorShiftKernel &operator=(GCTensorShiftKernel &&) = default;
+    /** Default destructor */
+    ~GCTensorShiftKernel() = default;
+    /** Set the input of the kernel.
+     *
+     * @param[in,out] input Source tensor. Data types supported: F16/F32
+     */
+    void configure(IGCTensor *input);
+
+    // Inherited methods overridden:
+    void run(const Window &window) override;
+
+private:
+    IGCTensor    *_input;
+    gles::NDRange _lws;
+};
+}
+#endif /*__ARM_COMPUTE_GCTENSORSHIFTKERNEL_H__ */