NASA-IMPACT / NASA-IMPACT/science-support

Investigate potential of Arm based instances

Open
#77 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
No language data
Stars
3
Forks
0
PR merge metrics
No merged PRs in 30d

Description

We have a new team likely to start using MAAP and one question that came up, was if MAAP Hub and DPS could support Arm processor instances. This isn't a requirement, but a potential nice to have as it may speed up some of their computationally intensive matrix math. So I've outlined some basic questions to answer. We don't need this answer until the end of the PI in September.

Acceptance criteria

  • Can the Hub run Arm instances, assuming Conda - JH @aprilmj @yuvipanda
  • Does Pangeo have Arm builds of it's containers? - Sc @wildintellect
  • Can DPS have Arm based job queues - JPL @sujen1412
  • What's the cost difference? i.e. how much faster does it need to be to make it worthwhile

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 with the open acceptance criterion for cost difference, using the MAAP Hub, DPS job queues, and Pangeo container questions as context. Compare Arm and non-Arm pricing and performance for the relevant workloads, then document whether the speed improvement makes Arm instances worthwhile.

Written by the indexing model from the issue text.

Assessment

Domain
cloud
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.