NXP backend: Add support for aten.clamp.default.

[MartinPavella]

Summary

This PR adds support for the aten.clamp.default operator no NXP backend.

Test plan

Unit-tests provided.

cc @robert-kalmar @JakeStevens @digantdesai

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17327

• 📄 Preview Python docs built from this PR

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

❌ 3 New Failures

As of commit caacdc0 with merge base c7c7c0a ():

NEW FAILURES - The following jobs have failed:

• pull / test-binary-size-linux-gcc / linux-job (gh)
  RuntimeError: Command docker exec -t 3c7a06b296b33beb32cd48bea38f3ec55a14cca9fa28f2a09a5d724bb7fcac29 /exec failed with exit code 1
• pull / test-samsung-models-linux / linux-job (gh)
  RuntimeError: Command docker exec -t fc14dcd14f824cdd95c41db224f510bdbe8cbdd2291c23747fb052e486f7e80d /exec failed with exit code 1
• pull / test-samsung-quantmodels-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 9029705e035ded61a9e6bfbafd19e773f463dff84b97af8bd749bd37e160e379 /exec failed with exit code 1

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

[MartinPavella]

Internal build: https://bamboo3.sw.nxp.com/browse/MLTECE-EXIGH76-1

[MartinPavella]

@novak-vaclav can you please take a look at this PR?

[MartinPavella]

The failing checks are unrelated and the internal build is passing. Merging.

[zingo]

Hi this might have got the size tests to fail I see you got
pull / test-binary-size-linux-gcc / linux-job (gh)

And see this in the hud: https://hud.pytorch.org/hud/pytorch/executorch/main/1?per_page=50&name_filter=test-binary-size&useRegexFilter=true

Note sure why as this PR seem to only touch NXP backend stuff, so it might be unrelated.

[MartinPavella]

Hi this might have got the size tests to fail I see you got pull / test-binary-size-linux-gcc / linux-job (gh)

And see this in the hud: https://hud.pytorch.org/hud/pytorch/executorch/main/1?per_page=50&name_filter=test-binary-size&useRegexFilter=true

Note sure why as this PR seem to only touch NXP backend stuff, so it might be unrelated.

I have no idea what that test relates to, so I don't know how to investigate the failure. Can I rely on you to find out what's wrong? Or is there something I can do?