Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

T26 — Segmented fused factorization with dependency counters (issues #82, #109, #110)

Open
  • Is something wrong?
#26 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
25/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Active
Tech stack
julia
Domain
backend, ci-cd, hpc

Research direction

Read the T26 section of TASKS.md first, then the PLAN.md sections it names and the Report blocks from previous tasks; #25 must be merged before work starts. Identify the tests listed there and run them on the KA CPU backend and the CUDA/AMDGPU self-hosted runners, including Aqua. Done means the tests pass, TASKS.md is updated with an honest report, and the required reviewed PR is created.

Written by the indexing model from the issue text.

Description

task

Task T26 of TASKS.md — milestone M11 — Performance. (Renamed on 2026-10-09: hybrid memory moved to T27, see STATE.md §8.)

Depends on: #25 (T25) must be merged first; tasks are strictly sequential.

Summary (from TASKS.md): adopt bench/fact_fused.jl (PR #107). First verify #110 (host synchronizations per refactorization; asynchronous vendor potrf if confirmed); solve #109 (block lifetimes on the execution order, or budgeted private slots in memory_estimates); then one kernel per segment of levels with workgroup roles and per-front dependency counters, segments split at the wide-front groups (full overlap deadlocks), atomic extend-add with the level-synchronous path as the atomic-free variant; subtree_budgets default re-measured; the #75 remainder and the #96 re-measurement. Report: refactorization and refactor+solve vs cuDSS, launches per refactorization (#82), stack bytes. Closes #82, #109, #110.

Scope and deliverables: the section T26 of TASKS.md on main is the single source of truth; it is not copied here so it cannot drift.

Definition of done:

  • Every test listed in the task passes on the KA CPU backend and on the CUDA self-hosted runner (Run tests and Aqua green on the PR).
  • The task's status marker in TASKS.md is set and its Report block is filled in honestly (CUDA counts come from CI).
  • A PR titled T26: … from branch task/T26-<slug> with Closes #26 in its body, reviewed by the Claude reviewer with VERDICT: APPROVE.
  • Out-of-scope bugs or follow-ups found on the way are opened as separate issues (label found-by-agent), not fixed silently.

How it starts: add the label claude:implement (the pipeline does this automatically after the previous task's PR merges; label on-hold to prevent that).

Dominant language
Julia
Stars
4
Forks
0
Avg merge
4h 1m
Merged PRs (30d)
73

Getting set up

  • No Dockerfile or Docker Compose file
  • Has a pull request template
  • No contributing guide

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 exanauts/SparseDirectSolver.jl

All issues in exanauts/SparseDirectSolver.jl

Similar issues

More Julia issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.