mirror of
https://github.com/saymrwulf/pytorch.git
synced 2026-05-14 20:57:59 +00:00
f4a921600a
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/54284 In order to bring mobile deployment, via lite interpreter, on feature parity with JIT, with respect model level debug information we must make model level debug information available to mobile runtime. At the moment, model level debug information is stored in SourceRange which associates node's of graph to where the come from in original python source code. This information is serialized as part of debug_pkl and deserialized when JIT loads the model and reads the model code. On lite interpreter, we do not have access to all the functionality of JIT and hence we cannot load model in the same way as JIT, by reading code, constructing module hierarchy and graph corresponding module methods etc. Instead in, lite interpreter, only bytecode corresonding to the compiled graph, Code, is saved. Thus in order to annotate OPs in the bytecode with equivalent SourceRange information we do the following: 1. During model serialization, we create a unique tag for each source range of the model. 2. Create a map of <SourceRange, tag> 3. During debug_pkl serialization we save tag along with SourceRange, on top of byte offset. 4. During bytecode generation, the methods of the top module are lowered. During this process methods are inlined. In the inlined graph, when the node of a graph is lowered to bytecode, we query node's source range and look it up against the map. 5. Resulting source range tag is serialized in module_debug_info. 6. During model deserialization, we read all the debug_pkl records in the archieve and create a map of <tag, SourceRange> 7. This map can be used to find source code information. During mobile runtime: 1. We read all the debug_pkl records and create <tag=debug_handle, SourceRange> map. 1.1 This map, MobileDebugInfo, is a member of mobile Module. 2. Interpreter catches appropriate exceptions and sets the thread local debug handle and rethrows the exception. 3. In Function's run method we catch exception and query current debug handle where the exception happened. 4. Query MobileDebugInfo with debug handle to retrieve source range and augment error with source range info. This information is still incomplete as it does not contain entire callstack. In the following diffs we will serialize InlinedCallStack directly. Note that compilation is gated by SYMBOLICATE_MOBILE_DEBUG_HANDLE macro, so that mobile builds can avoid building MobileDebugInfo, source range and source range pickler/unpickler. Later we will add path where, if building without debug support stack trace will contain only debug handles. They can be symbolicated later. Test Plan: Ported bunch of source range tests from test_jit.py. Added on more test in test_lite_interpreter.py Imported from OSS Reviewed By: raziel Differential Revision: D27174722 fbshipit-source-id: a7b7c6088ce16dec37e823c7fefa4f0b61047e12 |
||
|---|---|---|
| .. | ||
| backward_compatibility | ||
| benchmark_utils | ||
| bottleneck_test | ||
| cpp | ||
| cpp_api_parity | ||
| cpp_extensions | ||
| custom_backend | ||
| custom_operator | ||
| distributed | ||
| distributions | ||
| error_messages | ||
| expect | ||
| fx | ||
| jit | ||
| jit_hooks | ||
| mobile | ||
| onnx | ||
| optim | ||
| package | ||
| quantization | ||
| scripts | ||
| test_img | ||
| typing | ||
| HowToWriteTestsUsingFileCheck.md | ||
| linear.py | ||
| run_test.py | ||
| simulate_nccl_errors.py | ||
| test_ao_sparse.py | ||
| test_autograd.py | ||
| test_binary_ufuncs.py | ||
| test_bundled_images.py | ||
| test_bundled_inputs.py | ||
| test_complex.py | ||
| test_cpp_api_parity.py | ||
| test_cpp_extensions_aot.py | ||
| test_cpp_extensions_jit.py | ||
| test_cuda.py | ||
| test_cuda_primary_ctx.py | ||
| test_dataloader.py | ||
| test_datapipe.py | ||
| test_determination.py | ||
| test_dispatch.py | ||
| test_expecttest.py | ||
| test_foreach.py | ||
| test_function_schema.py | ||
| test_functional_autograd_benchmark.py | ||
| test_futures.py | ||
| test_fx.py | ||
| test_fx_experimental.py | ||
| test_import_time.py | ||
| test_indexing.py | ||
| test_jit.py | ||
| test_jit_cuda_fuser.py | ||
| test_jit_disabled.py | ||
| test_jit_fuser.py | ||
| test_jit_fuser_legacy.py | ||
| test_jit_fuser_te.py | ||
| test_jit_legacy.py | ||
| test_jit_profiling.py | ||
| test_jit_simple.py | ||
| test_jit_string.py | ||
| test_kernel_launch_checks.py | ||
| test_license.py | ||
| test_linalg.py | ||
| test_logging.py | ||
| test_metal.py | ||
| test_mkldnn.py | ||
| test_mobile_optimizer.py | ||
| test_model_dump.py | ||
| test_module_init.py | ||
| test_multiprocessing.py | ||
| test_multiprocessing_spawn.py | ||
| test_namedtensor.py | ||
| test_namedtuple_return_api.py | ||
| test_native_functions.py | ||
| test_nn.py | ||
| test_nnapi.py | ||
| test_numba_integration.py | ||
| test_numpy_interop.py | ||
| test_op_aliases.py | ||
| test_openmp.py | ||
| test_ops.py | ||
| test_optim.py | ||
| test_overrides.py | ||
| test_package.py | ||
| test_profiler.py | ||
| test_pruning_op.py | ||
| test_public_bindings.py | ||
| test_pytree.py | ||
| test_quantization.py | ||
| test_reductions.py | ||
| test_segment_reductions.py | ||
| test_serialization.py | ||
| test_set_default_mobile_cpu_allocator.py | ||
| test_shape_ops.py | ||
| test_show_pickle.py | ||
| test_sort_and_select.py | ||
| test_sparse.py | ||
| test_sparse_csr.py | ||
| test_spectral_ops.py | ||
| test_static_runtime.py | ||
| test_tensor_creation_ops.py | ||
| test_tensorboard.py | ||
| test_tensorexpr.py | ||
| test_tensorexpr_pybind.py | ||
| test_testing.py | ||
| test_throughput_benchmark.py | ||
| test_torch.py | ||
| test_type_hints.py | ||
| test_type_info.py | ||
| test_type_promotion.py | ||
| test_typing.py | ||
| test_unary_ufuncs.py | ||
| test_utils.py | ||
| test_view_ops.py | ||
| test_vmap.py | ||
| test_vulkan.py | ||
| test_xnnpack_integration.py | ||