Qualcomm AI Engine Direct - Add the argument to specify soc model

[shewu-quic]

No description provided.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5211

• 📄 Preview Python docs built from this PR

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

✅ No Failures

As of commit d34cd1a with merge base c5a385e ():
💚 Looks good so far! There are no failures yet. 💚

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

[shewu-quic]

Hi @cccclai and @guangy10,
I think we could add the argument soc_mode to make soc model configurable.
Could you please help to take a look?

Thanks

[cccclai]

Looks good. Thank you

[cccclai]

I think we need have this table somewhere in the qualcomm backend

[shewu-quic]

let me change it to

    qnn_partitioner = QnnPartitioner(
        generate_qnn_executorch_compiler_spec(
            soc_model=getattr(QcomChipset, soc_model),
            backend_options=backend_options,
            debug=False,
            saver=False,
            shared_buffer=shared_buffer,
            profile=False,
        ),
        skip_node_id_set,
        skip_node_op_set,
    )

[cccclai]

oh is it possible to have a function inside qualcomm like

def get_soc_table():
      return soc_chip_table = {
        "SM8650": QcomChipset.SM8650,
        "SM8550": QcomChipset.SM8550,
        "SM8475": QcomChipset.SM8475,
        "SM8450": QcomChipset.SM8450,
    }

and call it here?

[cccclai]

that's actually what I meatn..and the previous version seems good actually

[shewu-quic]

Thanks for your advice.
But I think we don't want to add this table for maintenance convenience.
Because if we would like to add new soc, we will need to maintain extra table.

[facebook-github-bot]

@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[cccclai]

Thanks - will merge when CI finishes