/*
 * 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/gpu/device/where.hpp>
#include <migraphx/gpu/device/tensor.hpp>
#include <migraphx/gpu/device/types.hpp>
#include <migraphx/gpu/device/launch.hpp>

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

template <class Shape>
constexpr auto get_rank(const Shape&)
{
    return decltype(typename Shape::hip_index{}.size()){};
}

void where(hipStream_t stream,
           const argument& result,
           const argument& arg0,
           const argument& arg1,
           const argument& arg2)
{
    hip_visit_all(result, arg1, arg2)([&](auto output, auto x, auto y) {
        hip_visit_all(arg0)([&](auto cond) {
            if constexpr(get_rank(cond.get_shape()) == get_rank(output.get_shape()))
            {
                gs_launch(stream, arg1.get_shape().elements())([=](auto idx) __device__ {
                    auto i    = output.get_shape().multi(idx);
                    output[i] = cond[i] ? x[i] : y[i];
                });
            }
        });
    });
}

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