Zhengxu Chen d459e79500 [jit][edge] Remove usage of shared_ptr<mobile::Code>. (#68037) ...

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/68037

Right now mobile::Code doesn't outlive its enclosing Function, and all accesses to Code happens inside interpreter loop which doesn't outlive the module, so we don't need to use std::shared_ptr here. This also should saves us 1-2 KB for binary size, because shared_ptr seems to bloat on arm64 android.
ghstack-source-id: 145818696

Test Plan: eyes.

Reviewed By: qihqi, tugsbayasgalan

Differential Revision: D32264616

fbshipit-source-id: d83f538d6604cf75fd7728a25127b4849ce7ab2a

2021-12-16 13:11:46 -08:00

..

callstack_debug_info_serialization.cpp

[PyTorch] Adopt IValue::toTupleRef() where obvious (#65505)

2021-11-02 10:22:18 -07:00

callstack_debug_info_serialization.h

[Pytorch Delegated Backend] Save operator name and function name in (#57441)

2021-05-25 13:17:54 -07:00

export_bytecode.cpp

[jit][edge] Remove usage of shared_ptr<mobile::Code>. (#68037)

2021-12-16 13:11:46 -08:00

export_bytecode.h

[jit][edge] Remove usage of shared_ptr<mobile::Code>. (#68037)

2021-12-16 13:11:46 -08:00

export_module.cpp

[jit][edge] Remove usage of shared_ptr<mobile::Code>. (#68037)

2021-12-16 13:11:46 -08:00

export.cpp

[ONNX] Add BFloat16 type support when export to ONNX (#66788)

2021-12-14 12:23:32 -08:00

export.h

[ONNX] Update onnx function export with comments and clean up (#66817) (#67803)

2021-11-05 10:35:35 -07:00

import_export_constants.h

[Pytorch, Mobile] Serialize inlined callstack pointer with debug handle. (#55062)

2021-05-04 09:21:12 -07:00

import_export_functions.h

[PyTorch] Add tuple inline storage (#64066)

2021-10-15 12:16:51 -07:00

import_export_helpers.cpp

Add SourceView which doesn't own source text as base class of Source (#65309)

2021-10-18 23:17:22 -07:00

import_export_helpers.h

Add SourceView which doesn't own source text as base class of Source (#65309)

2021-10-18 23:17:22 -07:00

import_legacy.cpp

[PyTorch] Add tuple inline storage (#64066)

2021-10-15 12:16:51 -07:00

import_legacy.h

Add another torch::jit::load API to load PyTorch model with shared_ptr PyTorchStreamReader input (#48802)

2020-12-06 18:09:25 -08:00

import_read.cpp

[package] track storages across lifetime of PackageExporter (#59735)

2021-06-29 14:16:54 -07:00

import_read.h

[package] track storages across lifetime of PackageExporter (#59735)

2021-06-29 14:16:54 -07:00

import_source.cpp

[jit] Remove graph() call from abstract Function interface. (#65967)

2021-10-27 11:54:26 -07:00

import_source.h

[jit] Remove graph() call from abstract Function interface. (#65967)

2021-10-27 11:54:26 -07:00

import.cpp

Support Union in TorchScript (#64234)

2021-09-03 06:12:24 -07:00

import.h

[package] track storages across lifetime of PackageExporter (#59735)

2021-06-29 14:16:54 -07:00

onnx.cpp

irange-ify 13b (#62476)

2021-08-11 13:13:44 -07:00

onnx.h

[ONNX] Utilize ONNX shape inference for ONNX exporter (#40628)

2020-08-30 18:35:46 -07:00

pickle.cpp

Remove WindowsTorchApiMacro.h in favor of Export.h (#69585)

2021-12-09 17:30:09 -08:00

pickle.h

Remove WindowsTorchApiMacro.h in favor of Export.h (#69585)

2021-12-09 17:30:09 -08:00

pickler.cpp

[jit] Reduce refcounting of Types (#65345)

2021-10-08 09:03:04 -07:00

pickler.h

Remove WindowsTorchApiMacro.h in favor of Export.h (#69585)

2021-12-09 17:30:09 -08:00

python_print.cpp

[jit] Remove graph() call from abstract Function interface. (#65967)

2021-10-27 11:54:26 -07:00

python_print.h

Remove WindowsTorchApiMacro.h in favor of Export.h (#69585)

2021-12-09 17:30:09 -08:00

source_range_serialization_impl.h

Lock unpickling of source ranges

2021-09-22 20:41:02 -07:00

source_range_serialization.cpp

[PyTorch] Adopt IValue::toTupleRef() where obvious (#65505)

2021-11-02 10:22:18 -07:00

source_range_serialization.h

Add SourceView which doesn't own source text as base class of Source (#65309)

2021-10-18 23:17:22 -07:00

storage_context.h

[package] fix storage serialization collision (#61806)

2021-07-19 18:22:36 -07:00

type_name_uniquer.cpp

[jit] Fix name collision on load (#35720)

2020-04-01 00:02:38 -07:00

type_name_uniquer.h

[jit] Fix name collision on load (#35720)

2020-04-01 00:02:38 -07:00

unpickler.cpp

[PyTorch] Avoid reading file from stream for 0 byte Tensor storage (#67787)

2021-11-09 21:45:05 -08:00

unpickler.h

Remove WindowsTorchApiMacro.h in favor of Export.h (#69585)

2021-12-09 17:30:09 -08:00