stan-dev / stan-dev/rstanarm

[Feature Request] Use GPU for QR decomp?

Open
#400 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature
Dominant language
R
Stars
401
Forks
136
PR merge metrics
No merged PRs in 30d

Description

Summary:

gpuR has a qr method that can be used to speedup the QR decomp in stan_glm.

Description:

For the QR code in stan_glm.fit we can use gpuR for the QR decomp. I recently ran into a problem where the QR decomp took about as long as the stan sampling itself. The GPU method above should speed things up a bit for large models.

I'm pretty sure I know what the code would look like, though I'm not sure where that option should go since there are already quite a few. We could add opencl and opencl_options where opencl is boolean and opencl_options is a list of OpenCL device and platform info

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 reading the QR decomposition in R/stan_glm.fit.R around line 273 and the gpuR qr method linked in the issue. Determine how large-model QR timing should be compared with the existing path and where the proposed OpenCL options would belong. Done means the GPU path and its option behavior are defined and validated without disrupting existing stan_glm use.

Written by the indexing model from the issue text.

Assessment

Tech stack
r
Domain
performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.