Arm backend: Bump amount of DDR in corstone320#18315
Arm backend: Bump amount of DDR in corstone320#18315perheld wants to merge 1 commit intopytorch:mainfrom
Conversation
Make it the same as corstone300 to be able to run larger models. Signed-off-by: per.held@arm.com Change-Id: Ic180de91ec25544a35474e2850d99b0b8b925b59
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18315
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 2 Cancelled Jobs, 3 Unrelated FailuresAs of commit 2848472 with merge base fb90480 ( NEW FAILURE - The following job has failed:
CANCELLED JOBS - The following jobs were cancelled. Please retry:
BROKEN TRUNK - The following jobs failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
There was a problem hiding this comment.
Pull request overview
Updates the Corstone-320 executor runner linker script to provide a larger DDR region (matching Corstone-300) so larger models can be linked/loaded for Arm backend bare-metal examples.
Changes:
- Increase Corstone-320 DDR memory region length from
0x10000000to0x60000000. - Update the copyright header year range.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
You can also share your feedback on Copilot code review. Take the survey.
|
This might not be the way to solve this. I need to investigate this further. |
Make it the same as corstone300 to be able to run larger models.
Signed-off-by: per.held@arm.com
Change-Id: Ic180de91ec25544a35474e2850d99b0b8b925b59
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell