mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-06 12:20:52 +01:00
c5cd993add
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/53068 Adds a ```bool is_available()``` method to the backend contract: it returns ```true``` if ```compile()``` and ```execute()``` can be called; ```false``` otherwise. It is used to implement the following changes in the ```LoweredModule```: * ```compile()``` in ```__setstate__``` will run if ```is_available()```, else ```__setstate__``` throws an exception (“Backend not available.”). * ```compile()``` at ```LoweredModule``` creation will run if ```is_available()```, else a WARNING will be thrown. * ```execute()``` will only be executed if ```is_available()``` returns true; else throws an exception (“Backend not available.”). The goal of these changes is to ensure we have a well defined behaviour for the different combinations of backend availability on-host and on-target. More specifically, backends may have different capabilities to compile and/or execute the Module, depending whether this happens on-host (i.e. where the program is being written) or on-target (where the program is being executed). First of all, we know that "preprocess" always takes place, and that only happens on-host at creation time. So, we can assume that any compilation is needed/possible on-host then all of it could be pushed here. Overall, we want to ensure the following: **On host** | compile | execute | Outcome | | -- | -- | -- | | No | No | On module creation, LoweredModule is generated, with a warning (since compilation and execution can still take place on-target). On module load, throws an exception (since execution is not possible). | | No | Yes | This configuration should not be possible. This assumes the full compiler is not available, even if some work was done in preprocess the program cannot be finalized for execution. | | Yes | No | In this case, the expectation would be for is_available() to return false, and compilation logic to move into preprocess. | | Yes | Yes | All good. This is the only case that is_available() should return true. | **On target** | compile | execute | Outcome | | -- | -- | -- | | No | No | Loading the LoweredModule throws an exception. Since execution is not possible. | | No | Yes | Basically this is another instance of Yes/Yes: compilation per se may not be possible on device, which means compile() can be called without issue but it is a no-op, and thus is_available should return true. Consequently, loading the LoweredModule: Succeeds, if the preprocessed module is ready for execution. Fails with exception otherwise. | | Yes | No | This configuration should not be possible. Just putting here for completeness. | | Yes | Yes | All good. This, along with No/Yes case (because compilation is assumed to have happened on-host, so it's just another instance of Yes/Yes), are the cases where is_available() should return true. | **Refactoring existing code** This change also updates other backends (Glow) code, to implement the is_available() method to have the same behaviour as before this change (i.e. always available). This should not cause backward incompatibilities with already saved models since we're adding a new method to the PyTorchBackendInterface. Models saved with the old interface that didn't have is_available() will still find the other 2 methods in the bound object (i.e. compile and execute), and the saved LoweredModule logic will be the old one. **Future** We plan to use is_available() to implement support for fallback to the PyTorch interpreter. ghstack-source-id: 123498571 Test Plan: Added C++ (test_backend.cpp) and Python (test_backends.py) tests to validate the exceptions. Reviewed By: jackm321, spaugh, iseeyuan Differential Revision: D26615833 fbshipit-source-id: 562e8b11db25784348b5f86bbc4179aedf15e0d3
85 lines
2.6 KiB
C++
85 lines
2.6 KiB
C++
#include <torch/csrc/jit/backends/backend.h>
|
|
|
|
namespace torch {
|
|
namespace jit {
|
|
// This test JIT backend is intended to do the minimal amount of work
|
|
// necessary to test that the JIT backend registration endpoints and
|
|
// code generation are working correctly. It is not intended to
|
|
// produce numerically correct results.
|
|
template <bool isAvailable>
|
|
class TestBackend : public PyTorchBackendInterface {
|
|
public:
|
|
// Constructor.
|
|
explicit TestBackend() {}
|
|
virtual ~TestBackend() = default;
|
|
|
|
bool is_available() override {
|
|
return isAvailable;
|
|
}
|
|
|
|
c10::impl::GenericDict compile(
|
|
c10::IValue processed,
|
|
c10::impl::GenericDict method_compile_spec) override {
|
|
auto spec =
|
|
c10::impl::toTypedDict<std::string, at::IValue>(method_compile_spec);
|
|
|
|
// Return the same string as a value for every key in method_compile_spec.
|
|
auto handles = c10::Dict<std::string, std::string>();
|
|
for (const auto& it : spec) {
|
|
handles.insert(it.key(), it.key());
|
|
}
|
|
return c10::impl::toGenericDict(handles);
|
|
}
|
|
c10::impl::GenericList execute(
|
|
c10::IValue handle,
|
|
c10::impl::GenericList inputs) override {
|
|
TORCH_INTERNAL_ASSERT(handle.isString());
|
|
TORCH_INTERNAL_ASSERT(inputs.size() > 0);
|
|
|
|
c10::List<at::Tensor> output_list;
|
|
|
|
// Implement simple accumulator and negative accumulator (?) ops. Return one
|
|
// or both of them depending on the handle to make sure multiple outputs are
|
|
// handled.
|
|
c10::IValue value = inputs[0];
|
|
at::Tensor accum = value.toTensor();
|
|
accum = accum.clone();
|
|
at::Tensor sub_accum = value.toTensor();
|
|
sub_accum = sub_accum.clone();
|
|
|
|
for (size_t i = 1, e = inputs.size(); i < e; ++i) {
|
|
value = inputs[i];
|
|
accum.add_(value.toTensor(), 1.0);
|
|
sub_accum.sub_(value.toTensor(), 1.0);
|
|
}
|
|
|
|
if (handle.toStringRef() == "accum") {
|
|
output_list.emplace_back(accum);
|
|
} else if (handle.toStringRef() == "sub_accum") {
|
|
output_list.emplace_back(sub_accum);
|
|
} else if (handle.toStringRef() == "forward") {
|
|
output_list.emplace_back(accum);
|
|
output_list.emplace_back(sub_accum);
|
|
}
|
|
|
|
return c10::impl::toList(output_list);
|
|
}
|
|
};
|
|
|
|
namespace {
|
|
c10::IValue preprocess(
|
|
const Module& mod,
|
|
const c10::Dict<IValue, IValue>& method_compile_spec) {
|
|
return mod._ivalue();
|
|
}
|
|
|
|
static auto cls_available =
|
|
torch::jit::backend<TestBackend<true>>("test_backend", preprocess);
|
|
static auto cls_unavailable = torch::jit::backend<TestBackend<false>>(
|
|
"test_backend_unavailable",
|
|
preprocess);
|
|
} // namespace
|
|
|
|
} // namespace jit
|
|
} // namespace torch
|