Separate the logical/allocation domain update of original tensorview from replay in rfactor

Open
#5,208 0 comments 0 reactions 1 assignee View on GitHub

@Priya2698 is already working on this.

Since Sep 22, 2025.

Assessment

This issue has not been assessed yet.

Description

cleanup

Follow-up to #5090.
Specifically, move the updateRfactorDomain that modifies the logical and allocation domain of original tensorview outside of handle(..).

The new structure should loosely resemble:

ReplayRfactor replay (...) -> generates the replay map using loop domain. Creates new IDs corresponding to the original IDs

updateLogicalDomain() -> updates the original tensorview such that it contains the rfactor IDs. This does not create any new IDs.

updateAllocationDomain()

CC: @naoyam. Please let me know if this aligns with your request.

Dominant language
C++
Stars
404
Forks
84
PR merge metrics
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from NVIDIA/Fuser

All issues in NVIDIA/Fuser

Similar issues

More C++ issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.