onednn-src 0.1.13

/*******************************************************************************
 * Copyright 2025 Intel Corporation
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 *******************************************************************************/

#ifndef GRAPH_BACKEND_DNNL_EXECUTABLES_SUM_HPP
#define GRAPH_BACKEND_DNNL_EXECUTABLES_SUM_HPP

#include "graph/backend/dnnl/executables/base.hpp"

namespace dnnl {
namespace impl {
namespace graph {
namespace dnnl_impl {

struct sum_executable_t : public op_executable_t {
    DECLARE_DESC_CLASS_AND_CREATOR(dnnl::sum::primitive_desc);
    DECLARE_ARG_INDICES_GETTER;

    sum_executable_t(std::shared_ptr<op_t> &op, const dnnl::engine &p_engine,
            pd_cache_t &pd_cache, const fpmath_t &fpmath,
            bool use_block_layout) {
        auto desc
                = create_desc(op, p_engine, pd_cache, fpmath, use_block_layout);
        prim_ = dnnl::sum(desc);
    }

    void execute(const stream &stream,
            const std::unordered_map<int, memory> &args) const override {
        prim_.execute(stream, args);
    }

#ifdef DNNL_WITH_SYCL
    std::optional<::sycl::event> execute_sycl(const stream &stream,
            const std::unordered_map<int, memory> &args,
            const std::vector<::sycl::event> &deps) const override {
        auto e = dnnl::sycl_interop::execute(prim_, stream, args, deps);
        if (stream.get_engine().get_kind() == engine::kind::cpu) e.wait();
        return e;
    }
#endif

#if DNNL_GPU_RUNTIME == DNNL_RUNTIME_OCL
    cl_event execute_ocl(const stream &stream,
            const std::unordered_map<int, memory> &args,
            const std::vector<cl_event> &deps) const override {
        auto e = dnnl::ocl_interop::execute(prim_, stream, args, deps);
        return e;
    }
#endif

private:
    dnnl::sum prim_;
};

} // namespace dnnl_impl
} // namespace graph
} // namespace impl
} // namespace dnnl

#endif // GRAPH_BACKEND_DNNL_EXECUTABLES_SUM_HPP