Arm backend: Move the portable kernels section to bigger memory

[gggekov]

This patch moves the portable kernels from the ITCM to the BRAM so that we don't overflow on the ITCM when linking the application

cc @digantdesai @freddan80 @per @zingo @oscarandersson8218

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12955

• 📄 Preview Python docs built from this PR

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

✅ You can merge normally! (1 Unrelated Failure)

As of commit 51d8fbd with merge base b0dda93 ():

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• trunk / test-models-macos-coreml (emformer_transcribe) / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

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

[digantdesai]

This is OK. FWIW, we added PTE based dtype selective build, in addition to existing per op selective build to further reduce the size of these op_*_cpp.obj files :)

FYI @BujSet

[Sebastian-Larsson]

Unrelated CI errors. Approved

[digantdesai]

@GeorgeARM do we need this also for CS320 for U85?

[gggekov]

On the CS320, the .text section is stored in the BRAM and we have 2MB of BRAM, so we haven't seen link time failures due to building with more portable kernels.
On the CS300, the .text section is in the ITCM and we have 512KB of ITCM, hence we saw link time errors on some models, that's why I've only changed the placement of the portable kernels for the CS300.