Support multi-module exports in Inspector and ETRecord

[cptspacemanspiff]

So, this is a prototype of changes required to get performance data out of a multi-method export with ETRecords and ETDump.

I do not have a good understanding of if this is correct/the best way, and my understanding of the performance analysis stuff is limited.

What this does:

1. In _etrecord.py, it allows for having a blank edge_dialect_program, and just exporting the ETRecord with export_modules:

export_modules [Optional]: **Should be ignored by OSS users**. A dictionary of graph modules with the key being the user provided name and the
            value being the corresponding exported module. The exported graph modules can be either the
            output of `torch.export()` or `exir.to_edge()`.

2. In the inspector tool, adds the ability to specify the module/method to pull the data from the ETRecord (since we are not using the global edge_program_method.)

FWIW I was able to get the statistics table with node labeling with these changes.

From the sounds of this this might be used internally and there is probably a better way to handle this?

related to #8030

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8336

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 5 New Failures, 2 Cancelled Jobs

As of commit becb19a with merge base d99970b ():

NEW FAILURES - The following jobs have failed:

• Build documentation / build (buck2) / Build doc (gh)
  RuntimeError: Command docker exec -t e055a6d13ba2c6a3fd25ba4cccf9069032953acee1debc61a83108cc6e94ad2e /exec failed with exit code 1
• pull / android / run-emulator (gh)
  The process '/usr/bin/sh' failed with exit code 1
• pull / test-static-llama-qnn-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 0d2deb485109356fd15242f4de510a525b8d05fdaa1c7a31a315cba64cd82f70 /exec failed with exit code 127
• pull / unittest / linux / linux-job (gh)
  devtools/inspector/tests/inspector_test.py::TestInspector::test_inspector_print_data_tabular
• pull / unittest / macos / macos-job (gh)
  devtools/inspector/tests/inspector_test.py::TestInspector::test_inspector_print_data_tabular

CANCELLED JOBS - The following jobs were cancelled. Please retry:

• pull / test-eval_llama-mmlu-linux / linux-job (gh)
  ##[error]The operation was canceled.
• pull / test-llava-runner-linux / linux-job (gh)
  ##[error]The operation was canceled.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[cptspacemanspiff]

@JacobSzwejbka

[shoumikhin]

@JacobSzwejbka, @tarun292, @Gasoonjia can you take a look please?

[tarun292]

I'm not sure i fully understand why you needed to add this check here?

[tarun292]

What is module name intended to be here?

[byjlw]

@cptspacemanspiff any update on this? I'm seeing a couple open questions to the code still