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.

option.cpp 2.1 kB

adreno image shader + fp16 + fp16a (#1714) * wip * wip * fix * image and imageview can not be destroyed until command execution ends * fast copy path for tightly packed data * wip * texture load works * 1d 3d image * record clone image, multiple commands share one image reference * upload download image * layer forward accept vkimagemat * vkimagemat graph works * staging vkimagemat for passing dynamic parameters, macro for fp32+image shader, padding image shader * vkimagemat elemsize * convolution test pass * conv1x1s1 image shader * fast staging image allocator from host memory, pooling image shader * convolutiondepthwise image shader * innerproduct image shader * packing image shader * crop deconvolution image shader * resolve spirv binding types * image fp16 and fp16a, cast image shader * eltwise image shader * wip * absval image shader * deconvolutiondepthwise image shader * concat image shader, squeezenet works * noop split image shader * uniform precision hint * layer support_image_storage * wip * vulkan device utility operator * command is storage and packing option aware * fallback to cpu on image allocation failed, mobilenetssd works * flatten image shader, enable more test * ci test * check imgfp32 imgfp16 imgfp16a features * fix ci test * fix ci test * upgrade swiftshader * wip * opt aggressive * imgfp16p * opt none * convolution winograd image shader * fix flush range, fast copy path for continous buffer * minor fix * fix innerproduct * wip ... * wip * cast fix * packing test * wip * image fp16p is fp16p * wip * silence * more line info * code clean * softmax image shader
6 years ago
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879
  1. // Tencent is pleased to support the open source community by making ncnn available.
  2. //
  3. // Copyright (C) 2019 THL A29 Limited, a Tencent company. All rights reserved.
  4. //
  5. // Licensed under the BSD 3-Clause License (the "License"); you may not use this file except
  6. // in compliance with the License. You may obtain a copy of the License at
  7. //
  8. // https://opensource.org/licenses/BSD-3-Clause
  9. //
  10. // Unless required by applicable law or agreed to in writing, software distributed
  11. // under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
  12. // CONDITIONS OF ANY KIND, either express or implied. See the License for the
  13. // specific language governing permissions and limitations under the License.
  14. #include "option.h"
  15. #include "cpu.h"
  16. namespace ncnn {
  17. Option::Option()
  18. {
  19. lightmode = true;
  20. num_threads = get_physical_big_cpu_count();
  21. blob_allocator = 0;
  22. workspace_allocator = 0;
  23. #if NCNN_VULKAN
  24. blob_vkallocator = 0;
  25. workspace_vkallocator = 0;
  26. staging_vkallocator = 0;
  27. pipeline_cache = 0;
  28. #endif // NCNN_VULKAN
  29. openmp_blocktime = 20;
  30. use_winograd_convolution = true;
  31. use_sgemm_convolution = true;
  32. use_int8_inference = true;
  33. use_vulkan_compute = false; // TODO enable me
  34. use_bf16_storage = false;
  35. use_fp16_packed = true;
  36. use_fp16_storage = true;
  37. use_fp16_arithmetic = true;
  38. use_int8_packed = true;
  39. use_int8_storage = true;
  40. use_int8_arithmetic = false;
  41. use_packing_layout = true;
  42. use_shader_pack8 = false;
  43. use_subgroup_basic = false;
  44. use_subgroup_vote = false;
  45. use_subgroup_ballot = false;
  46. use_subgroup_shuffle = false;
  47. use_image_storage = false;
  48. use_tensor_storage = false;
  49. use_reserved_0 = false;
  50. flush_denormals = 3;
  51. use_local_pool_allocator = true;
  52. use_shader_local_memory = true;
  53. use_cooperative_matrix = true;
  54. use_winograd23_convolution = true;
  55. use_winograd43_convolution = true;
  56. use_winograd63_convolution = true;
  57. use_a53_a55_optimized_kernel = is_current_thread_running_on_a53_a55();
  58. }
  59. } // namespace ncnn