[PyTorch] Avoid schema parsing in lightweight dispatch (#74069)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74069
RFC: pytorch/rfcs#40
In #69881 we added the ability to generate codegen unboxing source files. Notice that the generated code to register an operator looks like this:
```
// aten::add.Tensor(Tensor self, Tensor other, *, Scalar alpha=1) -> Tensor
OperatorGenerator(
TORCH_SELECTIVE_SCHEMA("aten::add.Tensor(Tensor self, Tensor other, *, Scalar alpha=1) -> Tensor"),
[](Stack & stack) {
RECORD_FUNCTION("add", std::vector<c10::IValue>());
at::unboxing::add_Tensor(stack);
},
aliasAnalysisFromSchema()
),
```
However, this means we have to parse the schema and get back arguments with default values in static init time. As written in the RFC, there's a more performant option: providing these arguments with default values using codegen, then we don't have to do expensive regex pattern matching in parsing. Here's how it looks like:
```
// aten::add.Tensor(Tensor self, Tensor other, *, Scalar alpha=1) -> Tensor
OperatorGenerator(
"aten::add",
"Tensor",
{
c10::Argument("self", nullptr, c10::nullopt, c10::IValue(c10::nullopt)),
c10::Argument("other", nullptr, c10::nullopt, c10::IValue(c10::nullopt)),
c10::Argument("alpha", nullptr, c10::nullopt, c10::IValue(1))
},
{
c10::Argument("")
},
[](Stack & stack) {
RECORD_FUNCTION("add", std::vector<c10::IValue>());
at::unboxing::add_Tensor(stack);
},
aliasAnalysisFromSchema()
),
```
We also added corresponding APIs in `operator.h` to take in the arguments.
Test Plan: Rely on CI
Reviewed By: kimishpatel
Differential Revision: D33077733
fbshipit-source-id: e7f13a2f162c70d4e506b4f64cdbb7afec39f4e6
(cherry picked from commit 08a076935f480d5ab11c75e78d8627a8e2ba7d1a)
