Google Git
Sign in
android / platform / external / pytorch / 82986a17a6 / . / torch / csrc / jit / passes / onnx
tree: 05786f20e21c2fbb5823c7f14ec0bbe783af9dd0 [path history] [tgz]
  1. pattern_conversion/
  2. cast_all_constant_to_floating.cpp
  3. cast_all_constant_to_floating.h
  4. constant_fold.cpp
  5. constant_fold.h
  6. constant_map.cpp
  7. constant_map.h
  8. eliminate_unused_items.cpp
  9. eliminate_unused_items.h
  10. eval_peephole.cpp
  11. eval_peephole.h
  12. fixup_onnx_controlflow.cpp
  13. fixup_onnx_controlflow.h
  14. fold_if_node.cpp
  15. fold_if_node.h
  16. function_substitution.cpp
  17. function_substitution.h
  18. helper.cpp
  19. helper.h
  20. list_model_parameters.cpp
  21. list_model_parameters.h
  22. peephole.cpp
  23. peephole.h
  24. prepare_division_for_onnx.cpp
  25. prepare_division_for_onnx.h
  26. preprocess_for_onnx.cpp
  27. preprocess_for_onnx.h
  28. README.md
  29. remove_inplace_ops_for_onnx.cpp
  30. remove_inplace_ops_for_onnx.h
  31. scalar_type_analysis.cpp
  32. scalar_type_analysis.h
  33. shape_type_inference.cpp
  34. shape_type_inference.h
  35. unpack_quantized_weights.cpp
  36. unpack_quantized_weights.h
torch/csrc/jit/passes/onnx/README.md

The optimization passes in this directory work exclusively on ONNX-style IRs, e.g., IRs that have had ToONNX applied to them. ONNX defines operators differently from ATen, so there are different opportunities for peephole optimization.