onednn-src 0.1.13

Source of oneAPI Deep Neural Network Library (oneDNN)
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78

/*******************************************************************************
 * 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_GEN_INDEX_HPP
#define GRAPH_BACKEND_DNNL_EXECUTABLES_GEN_INDEX_HPP

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

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

#if DNNL_GPU_RUNTIME != DNNL_RUNTIME_NONE \
        && DNNL_GPU_VENDOR == DNNL_VENDOR_INTEL
using namespace dnnl::impl::gpu::intel;
#define MAX_NDIMS 6
#endif
struct genindex_executable_t : public op_executable_t {
    DECLARE_ARG_INDICES_GETTER;

    genindex_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);

    void execute(const stream &stream,
            const std::unordered_map<int, memory> &args) const override;
    void execute_impl(const stream &stream,
            const std::unordered_map<int, memory> &args) const;

#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;
    std::optional<::sycl::event> execute_sycl_impl(const stream &stream,
            const std::unordered_map<int, memory> &args,
            const std::vector<::sycl::event> &deps) const;
#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;
    cl_event execute_ocl_impl(const stream &stream,
            const std::unordered_map<int, memory> &args,
            const std::vector<cl_event> &deps) const;
#endif

private:
    int axis_, nelems_, ndims_;
    dims_t output_dims_, output_strides_;
    std::string info_;

#if (DNNL_GPU_RUNTIME != DNNL_RUNTIME_NONE) \
        && (DNNL_GPU_VENDOR == DNNL_VENDOR_INTEL)
    compute::kernel_t kernel_;
#endif
};

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

#endif // GRAPH_BACKEND_DNNL_EXECUTABLES_GEN_INDEX_HPP