Summary:
We can implement this as a builtin instead of as a registered op.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/37886
Differential Revision: D21414329
Pulled By: eellison
fbshipit-source-id: 6e130fa83fbf7ba4d4601f509cb169a2fa804108
Summary:
PyTorch users write programs and save them as serialized Torchscript. When this Torchscript is loaded it contains symbols like "aten::div" describing some of the program's behavior. If the behavior of these symbols has changed since the program was serialized, however, then the original program's semantics may not be preserved.
For example, when we make aten::div always perform "true" division, like NumPy, Python3, and JAX, then serialized Torchscript programs relying on aten::div performing floor division on integral inputs will break.
This PR demonstrates the "Versioned Symbol" pattern that lets symbols be remapped into Torchscript builtins that preserve their historic behavior. Using this pattern, after we update aten::div to always perform true division, we could remap it in older Torchscript programs to a builtin that implements its historic behavior.
The pattern is described in the [Versioned Symbols] note in the code and is implemented like this:
- If BuiltinModule is given a version, before it returns a symbol it queries to see if another symbol should be substituted for it.
- versioned_symbol.cpp has a map for symbols and the version range for which another symbol should be substituted for them.
- The substitutions are implemented as builtin functions.
An example using the new, test-only _subcmul function is implemented to test this behavior. A test in jit/test_save_load.py follows the pattern described in the [Versioned Symbols] note and uses a fixture serialized with file version 2 to verify that the historic behavior is preserved.
In the future we will likely need a slightly more complex mechanism with multiple substitutions with distinct version ranges, and this just requires changing the map to be Symbol->Iterable.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/36300
Differential Revision: D21058990
Pulled By: mruberry
fbshipit-source-id: 2b7c732878c0ecfcd9f0a6205fb6d6421feeaf61
Summary:
This one doesn't actually do anything so we don't need an op for it.
It is used inside `torch.nn.functional.unfold` which is already tested
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34509
Pulled By: driazati
Differential Revision: D20676445
fbshipit-source-id: b72d1308bdec593367ec4e14bf9a901d0b62e1cc
Summary:
Desugar prim::shape to aten::size so that passes don't need to reason about both ops. Serialized models still resolve to `prim::shape` so this doesn't break BC.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34286
Differential Revision: D20316818
Pulled By: eellison
fbshipit-source-id: d1585687212843f51e9396e07c108f5c08017818
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/35115
This commit runs the newly added tools/clang_format.py on the JIT
codebase and includes all of the formatting changes thus produced.
Testing:
Ran the script, CI.
Test Plan: Imported from OSS
Reviewed By: eellison
Differential Revision: D20568523
Pulled By: SplitInfinity
fbshipit-source-id: e09bdb982ccf090eecfb7c7b461b8d0681eef82b
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34515
Once upon a time we thought this was necessary. In reality it is not, so
removing it.
For backcompat, our public interface (defined in `api/`) still has
typedefs to the old `script::` names.
There was only one collision: `Pass` as a `Stmt` and `Pass` as a graph
transform. I renamed one of them.
Test Plan: Imported from OSS
Differential Revision: D20353503
Pulled By: suo
fbshipit-source-id: 48bb911ce75120a8c9e0c6fb65262ef775dfba93
Summary:
Fixes#30775
This adds TorchScript implementations (copied from `python_variable.cpp`) for the remainin `Tensor` properties that were missing from the jit, in addition to a test that ensures new properties will trigger a failure so we can decide whether we want to add them as well.
For `some_tensor`, adds:
* `some_tensor.T`
* `some_tensor.ndim`
* `some_tensor.is_leaf`
* `some_tensor.name`
](https://our.intern.facebook.com/intern/diff/20153288/)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/33906
Pulled By: driazati
Differential Revision: D20153288
fbshipit-source-id: 2ddc48a14267077bc176065267e5ce52181b3d6b
