NVIDIA / NVIDIA/cuCascade

Make some kind of scheduling policy for satisfying reservations

Open
#20 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request improvement
Dominant language
C++
Stars
59
Forks
35
Avg merge
17h 38m
Merged PRs (30d)
3

Description

We currently have a pretty simple FIFO way of satisfying reservations. What we really want is to define policies that can be used to order these and handle situations where one can't be satisfied so it can move on to another. Mads first proposal was prioritizing those that would eventually free up the most memory.

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.

Research direction

Start by locating the existing FIFO reservation-scheduling implementation and reading how unsatisfied reservations are handled. Compare that behavior with the proposed policy of prioritizing reservations that would eventually free the most memory. Done means an agreed policy is implemented for ordering reservations and allowing an unsatisfied reservation to yield to another.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
backend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.