Skip to content

[BUG] Improper tiling implementation in PULPOpen for Slice and ReduceMean operators #134

Description

@diaconuccalin

Describe the bug

The tiling system currently does not support list values as replacement variables, which affects the Slice and ReduceMean operators. These operators use arbitrary numbers of axes for input and output, which results in their data_in and data_out dimensions producing lists as replacement values.

To Reproduce

Run:

cd DeeployTest
python testRunner_tiled_siracusa.py -t Tests/testFloatDemoTinyViT/ --cores=8 --l1 4000

When checking the generated Network.c file, no tiling for Slice or ReduceMean operations

Expected behavior

Successful tiling for Slice and ReduceMean operations, that will be obtained by adjustings the templates and tiling constraints.

Additional context

Will need to also implement extra testing for Slice and ReduceMean operations.

Activity

  1. linked a pull request that will close this issueFP32 ReduceMean operator improvement #137on Dec 12, 2025
  2. moved this from Done to In progress in Deeployon Dec 24, 2025
  3. added this to the Release 0.2.1 milestone on Dec 24, 2025
  4. Xeratec commented on Feb 3, 2026

    @Xeratec
    Member

    @diaconuccalin If I remember correctly, this issue cannot yet be closed as you only implemented the tiling for the ReduceMean operator, correct?

  5. diaconuccalin commented on Feb 3, 2026

    @diaconuccalin
    ContributorAuthor

    Exactly, once PR #140 is finished, we can mark this as solved. I did not have time to work on this recently, but I will try to get back to it this week or next week at the latest.

  6. diaconuccalin commented on Nov 4, 2026

    @diaconuccalin
    ContributorAuthor

    Will be solved by PR #190

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

BugSomething isn't working

Type

Projects

  • Status
    In progress

Relationships

None yet

Development

No branches or pull requests

Issue actions