diff options
author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2021-01-18 21:15:59 +0000 |
---|---|---|
committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2021-01-20 16:28:27 +0000 |
commit | 7d61ff041826782d14e67b7f5b7a2864905ff38b (patch) | |
tree | 2e69c8a5fdabc6717b0691acdbbe7374d856902f /src/core/gpu/cl/kernels/ClBatchConcatenateKernel.h | |
parent | da6a6eb3bc06ce8869ae3290853970d4c0ce412e (diff) | |
download | ComputeLibrary-7d61ff041826782d14e67b7f5b7a2864905ff38b.tar.gz |
Make all CL Concatenate kernels and functions state-less
Resolves COMPMID-3995
Change-Id: I84172bed20924f1d9ae3b4d14d7b321e9494296e
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4887
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'src/core/gpu/cl/kernels/ClBatchConcatenateKernel.h')
-rw-r--r-- | src/core/gpu/cl/kernels/ClBatchConcatenateKernel.h | 77 |
1 files changed, 77 insertions, 0 deletions
diff --git a/src/core/gpu/cl/kernels/ClBatchConcatenateKernel.h b/src/core/gpu/cl/kernels/ClBatchConcatenateKernel.h new file mode 100644 index 0000000000..378a08aa4f --- /dev/null +++ b/src/core/gpu/cl/kernels/ClBatchConcatenateKernel.h @@ -0,0 +1,77 @@ +/* + * Copyright (c) 2021 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_CL_BATCH_CONCATENATE_KERNEL_H +#define ARM_COMPUTE_CL_BATCH_CONCATENATE_KERNEL_H + +#include "src/core/common/Macros.h" +#include "src/core/gpu/cl/ClCompileContext.h" +#include "src/core/gpu/cl/IClKernel.h" + +namespace arm_compute +{ +namespace opencl +{ +namespace kernels +{ +/** Interface for the batch concatenate kernel. + * The src tensor will be concatenated into the destination tensor. + */ +class ClBatchConcatenateKernel : public IClKernel +{ +public: + /** Default constructor */ + ClBatchConcatenateKernel(); + ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClBatchConcatenateKernel); + /** Initialise the kernel's source and destination + * + * @param[in] compile_context The compile context to be used. + * @param[in] src Source tensor. Data types supported: All. + * @param[in] batch_offset The offset on axis # 3. + * @param[in,out] dst Destination tensor. Data types supported: Same as @p src. + * + * @note: The dst tensor's low two dimensions can't be smaller than the src one's. + * @note: The gaps between the two lowest dimensions of src and dst need to be divisible by 2. + * + */ + void configure(const CLCompileContext &compile_context, ITensorInfo *src, unsigned int batch_offset, ITensorInfo *dst); + /** Static function to check if given info will lead to a valid configuration of @ref ClBatchConcatenateKernel + * + * @param[in] src Input tensor info. Data types supported: All. + * @param[in] batch_offset The offset on axis # 3. + * @param[in] dst Destination tensor info. Data types supported: Same as @p src. + * + * @return a status + */ + static Status validate(const ITensorInfo *src, unsigned int batch_offset, const ITensorInfo *dst); + + // Inherited methods overridden: + void run_op(ITensorPack &tensors, const Window &window, ::cl::CommandQueue &queue) override; + +private: + unsigned int _batch_offset; +}; +} // namespace kernels +} // namespace opencl +} // namespace arm_compute +#endif /* ARM_COMPUTE_CL_BATCH_CONCATENATE_KERNEL_H */ |