concat.cpp

/*
 * The MIT License (MIT)
 *
 * Copyright (c) 2015-2022 Advanced Micro Devices, Inc. All rights reserved.
 *
 * 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.
 */
#include <migraphx/shape.hpp>
#include <migraphx/argument.hpp>
#include <migraphx/gpu/device/concat.hpp>
#include <migraphx/gpu/device/contiguous.hpp>

namespace migraphx {
inline namespace MIGRAPHX_INLINE_NS {
namespace gpu {
namespace device {

argument concat(hipStream_t stream,
                const migraphx::shape&,
                std::vector<migraphx::argument> args,
                std::vector<std::size_t> offsets)
{
    auto ninputs = args.size() - 1;
    for(std::size_t j = 0; j < ninputs; j++)
    {
        auto&& arg        = args[j];
        auto offset       = offsets[j];
        auto byte_offset  = offset * arg.get_shape().type_size();
        auto output_shape = shape{
            arg.get_shape().type(), arg.get_shape().lens(), args.back().get_shape().strides()};
        auto output = argument{output_shape, args.back().data() + byte_offset};
        contiguous(stream, output, arg);
    }
    return args.back();
}

} // namespace device
} // namespace gpu
} // namespace MIGRAPHX_INLINE_NS
} // namespace migraphx