COMPMID-1579: Add support for ChannelShuffle operator in NEON

Change-Id: I6d5f91579850906e1eb973ff6c5612195255e631

1 files changed, 80 insertions, 0 deletions

diff --git a/arm_compute/core/NEON/kernels/NEChannelShuffleLayerKernel.h b/arm_compute/core/NEON/kernels/NEChannelShuffleLayerKernel.h
new file mode 100644
index 0000000000..e9ef2d4a51
--- /dev/null
+++ b/arm_compute/core/NEON/kernels/NEChannelShuffleLayerKernel.h
@@ -0,0 +1,80 @@
+/*
+ * Copyright (c) 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_NECHANNELSHUFFLELAYERKERNEL_H__
+#define __ARM_COMPUTE_NECHANNELSHUFFLELAYERKERNEL_H__
+
+#include "arm_compute/core/NEON/INEKernel.h"
+
+namespace arm_compute
+{
+// Forward declarations
+class ITensor;
+
+/** Interface for the channel shuffle kernel */
+class NEChannelShuffleLayerKernel : public INEKernel
+{
+public:
+    const char *name() const override
+    {
+        return "NEChannelShuffleLayerKernel";
+    }
+    /** Default constructor */
+    NEChannelShuffleLayerKernel();
+    /** Prevent instances of this class from being copied (As this class contains pointers) */
+    NEChannelShuffleLayerKernel(const NEChannelShuffleLayerKernel &) = delete;
+    /** Prevent instances of this class from being copied (As this class contains pointers) */
+    NEChannelShuffleLayerKernel &operator=(const NEChannelShuffleLayerKernel &) = delete;
+    /** Allow instances of this class to be moved */
+    NEChannelShuffleLayerKernel(NEChannelShuffleLayerKernel &&) = default;
+    /** Allow instances of this class to be moved */
+    NEChannelShuffleLayerKernel &operator=(NEChannelShuffleLayerKernel &&) = default;
+    /** Default destructor */
+    ~NEChannelShuffleLayerKernel() = default;
+    /** Configure function's inputs and outputs.
+     *
+     * @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]  num_groups Number of groups. Must be greater than 1 and the number of channels of the tensors must be a multiple of the number of groups.
+     */
+    void configure(const ITensor *input, ITensor *output, unsigned int num_groups);
+    /** Static function to check if given info will lead to a valid configuration of @ref NEChannelShuffleLayerKernel
+     *
+     * @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]  num_groups Number of groups. Must be greater than 1 and the number of channels of the tensors must be a multiple of the number of groups.
+     *
+     * @return a status
+     */
+    static Status validate(const ITensorInfo *input, const ITensorInfo *output, unsigned int num_groups);
+
+    // Inherited methods overridden:
+    void run(const Window &window, const ThreadInfo &info) override;
+
+private:
+    const ITensor *_input;
+    ITensor       *_output;
+    unsigned int   _num_groups;
+};
+} // namespace arm_compute
+#endif /* __ARM_COMPUTE_NECHANNELSHUFFLELAYERKERNEL_H__ */