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

/*******************************************************************************
* Copyright 2019 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.
*******************************************************************************/

#include "gpu/gpu_impl_list.hpp"

#include "common/utils.hpp"
#include "gpu/gpu_sum_pd.hpp"

#include "gpu/generic/ref_sum.hpp"

#if DNNL_GPU_VENDOR == DNNL_VENDOR_INTEL
#include "gpu/intel/sum/many_inputs.hpp"
#include "gpu/intel/sum/multi_po_reorder.hpp"
#include "gpu/intel/sum/simple.hpp"
#include "gpu/intel/sum/xe.hpp"
#endif

#if DNNL_GPU_VENDOR == DNNL_VENDOR_NVIDIA
#include "gpu/nvidia/cudnn_sum.hpp"
#endif

#ifdef GENERIC_SYCL_KERNELS_ENABLED
#include "gpu/generic/sycl/ref_sum.hpp"
#include "gpu/generic/sycl/ref_sum_many_inputs.hpp"
#endif

namespace dnnl {
namespace impl {
namespace gpu {

namespace {

// clang-format off
constexpr impl_list_item_t impl_list[] = REG_SUM_P({
        GPU_SUM_INSTANCE_INTEL(intel::sum::multi_po_reorder_t)
        GPU_SUM_INSTANCE_INTEL(intel::sum::xe_t)
        GPU_SUM_INSTANCE_INTEL(intel::sum::many_inputs_t)
        GPU_SUM_INSTANCE_INTEL(intel::sum::simple_t<data_type::f32>)
        GPU_SUM_INSTANCE_NVIDIA(nvidia::cudnn_ref_sum_t)
        GPU_SUM_INSTANCE_GENERIC_SYCL(generic::sycl::ref_sum_t)
        GPU_SUM_INSTANCE_GENERIC_SYCL(generic::sycl::ref_sum_many_inputs_t)
        GPU_SUM_INSTANCE_GENERIC(generic::ref_sum_t)
        nullptr,
});
// clang-format on

} // namespace

const impl_list_item_t *get_sum_impl_list() {
    return impl_list;
}

} // namespace gpu
} // namespace impl
} // namespace dnnl