matmul_kernel.h 1.6 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18
// Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
//
// 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.

#pragma once

#include "paddle/pten/api/lib/utils/storage.h"
#include "paddle/pten/core/dense_tensor.h"
C
Chen Weihang 已提交
19
#include "paddle/pten/infermeta/binary.h"
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

namespace pten {

template <typename T, typename Context>
void MatmulKernel(const Context& context,
                  const DenseTensor& x,
                  const DenseTensor& y,
                  bool transpose_x,
                  bool transpose_y,
                  DenseTensor* out);

template <typename T, typename Context>
DenseTensor Matmul(const Context& context,
                   const DenseTensor& x,
                   const DenseTensor& y,
                   bool transpose_x,
                   bool transpose_y) {
  auto out_meta = MatmulInferMeta(x.meta(), y.meta(), transpose_x, transpose_y);
  DenseTensor dense_out(
      pten::make_intrusive<paddle::experimental::SharedStorage>(
          context.GetPlace()),
      std::move(out_meta));
  MatmulKernel<T, Context>(context, x, y, transpose_x, transpose_y, &dense_out);
  return dense_out;
}

}  // namespace pten