You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

batched_matrix_mul.cpp 949 B

1234567891011121314151617181920212223242526272829
  1. /**
  2. * \file dnn/test/cpu/batched_matrix_mul.cpp
  3. * MegEngine is Licensed under the Apache License, Version 2.0 (the "License")
  4. *
  5. * Copyright (c) 2014-2020 Megvii Inc. All rights reserved.
  6. *
  7. * Unless required by applicable law or agreed to in writing,
  8. * software distributed under the License is distributed on an
  9. * "AS IS" BASIS, WITHOUT ARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  10. */
  11. #include "test/cpu/fixture.h"
  12. #include <chrono>
  13. #include "test/common/checker.h"
  14. #include "test/common/matrix_mul.h"
  15. using namespace megdnn;
  16. using namespace test;
  17. //! check batch=1 and batch_stride is arbitrarily
  18. TEST_F(CPU, BATCHED_MATRIX_MUL_BATCH_1) {
  19. matrix_mul::check_batched_matrix_mul(
  20. dtype::Float32{}, dtype::Float32{}, dtype::Float32{}, handle(),
  21. nullptr, 1e-3,
  22. std::vector<matrix_mul::TestArg>{
  23. {5, 5, 5, 0, 5, 5, 5, 1, 5, 5, 5}});
  24. }
  25. // vim: syntax=cpp.doxygen

MegEngine 安装包中集成了使用 GPU 运行代码所需的 CUDA 环境,不用区分 CPU 和 GPU 版。 如果想要运行 GPU 程序,请确保机器本身配有 GPU 硬件设备并安装好驱动。 如果你想体验在云端 GPU 算力平台进行深度学习开发的感觉,欢迎访问 MegStudio 平台