pytorch

OSSForks/pytorch

Fork 0

mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-07 00:21:07 +01:00

Commit Graph

Author	SHA1	Message	Date
Scott Wolchok	176d3c6fb4	[PyTorch] Fix many Tuple::elements() callsites (#64065 ) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/64065 It is only safe to mutate Tuple elements if you are the sole owner of the tuple. The most efficient way to do this, then, is `std::move(*std::move(tupleIValue).toTuple()).elements()` (the innermost move allows `IValue::toTuple()` to avoid a refcount bump and the outermost move allows the element vector to be moved out of the tuple), but many callsites write simply `tupleIValue.toTuple().elements()`, which incurs many extra refcount bumps. ghstack-source-id: 139468088 Test Plan: CI Reviewed By: ezyang Differential Revision: D30592621 fbshipit-source-id: e8312de866de09b9ea2a62e5128cbf403ee16f09	2021-10-01 11:36:05 -07:00
Scott Wolchok	5d4efed83e	[PyTorch] Add OpCode cache in ByteCodeDeserializer (#64110 ) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/64110 As the code comment says, we can exploit pickler string interning to accelerate OpCode parsing. No more strcmp! ghstack-source-id: 137978946 Test Plan: Pixel 3 before: https://www.internalfb.com/intern/aibench/details/591414145082422 Pixel 3 after: https://www.internalfb.com/intern/aibench/details/484557404703261 new mean is 292 ms, down from 302 ms. Reviewed By: dhruvbird Differential Revision: D30615052 fbshipit-source-id: 9707625e778388a7920ab72704d71ad57ddaac17	2021-09-14 14:22:10 -07:00
Martin Yuan	30a7c768d7	[RFC] Modularize functions of parsing bytecode (#61862 ) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/61862 Modularize functions of parsing bytecode tables so that they can be used as needed in situations other than mobile lite interpreter. * The decoupled functions are re-used by current lite interpreter loader. * The bytecode can be serialized/deserialized from other formats. * The decoupled functions have minimum dependencies on other PyTorch components. Next: Build a driver binary to include the parser and interpreter, but only has necessary dependency on other PyTorch components. ghstack-source-id: 137867287 Test Plan: As an example, a simple bytecode is parsed to a mobile function, and directly run in the added unit test, `RunTimeTest:ParseBytecode`. It contains basic control flow (if, else) and basic data orchestration (list construction). CI Reviewed By: larryliu0820 Differential Revision: D29798382 Pulled By: iseeyuan fbshipit-source-id: 1c173a5f5d37097e3a97baec3f3e48e1eea1400f	2021-09-11 22:24:05 -07:00

Author

SHA1

Message

Date

Scott Wolchok

176d3c6fb4

[PyTorch] Fix many Tuple::elements() callsites (#64065 )

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/64065

It is only safe to mutate Tuple elements if you are the sole owner
of the tuple. The most efficient way to do this, then, is
`std::move(*std::move(tupleIValue).toTuple()).elements()` (the
innermost move allows `IValue::toTuple()` to avoid a refcount bump and
the outermost move allows the element vector to be moved out of the
tuple), but many callsites write simply
`tupleIValue.toTuple().elements()`, which incurs many extra refcount
bumps.

ghstack-source-id: 139468088

Test Plan: CI

Reviewed By: ezyang

Differential Revision: D30592621

fbshipit-source-id: e8312de866de09b9ea2a62e5128cbf403ee16f09

2021-10-01 11:36:05 -07:00

Scott Wolchok

5d4efed83e

[PyTorch] Add OpCode cache in ByteCodeDeserializer (#64110 )

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/64110

As the code comment says, we can exploit pickler string interning to accelerate OpCode parsing. No more strcmp!
ghstack-source-id: 137978946

Test Plan:
Pixel 3 before: https://www.internalfb.com/intern/aibench/details/591414145082422
Pixel 3 after: https://www.internalfb.com/intern/aibench/details/484557404703261

new mean is 292 ms, down from 302 ms.

Reviewed By: dhruvbird

Differential Revision: D30615052

fbshipit-source-id: 9707625e778388a7920ab72704d71ad57ddaac17

2021-09-14 14:22:10 -07:00

Martin Yuan

30a7c768d7

[RFC] Modularize functions of parsing bytecode (#61862 )

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/61862

Modularize functions of parsing bytecode tables so that they can be used as needed in situations other than mobile lite interpreter.
* The decoupled functions are re-used by current lite interpreter loader.
* The bytecode can be serialized/deserialized from other formats.
* The decoupled functions have minimum dependencies on other PyTorch components.

Next:
Build a driver binary to include the parser and interpreter, but only has necessary dependency on other PyTorch components.
ghstack-source-id: 137867287

Test Plan:
As an example, a simple bytecode is parsed to a mobile function, and directly run in the added unit test, `RunTimeTest:ParseBytecode`. It contains basic control flow (if, else) and basic data orchestration (list construction).
CI

Reviewed By: larryliu0820

Differential Revision: D29798382

Pulled By: iseeyuan

fbshipit-source-id: 1c173a5f5d37097e3a97baec3f3e48e1eea1400f

2021-09-11 22:24:05 -07:00

3 Commits