Try stan threads option

WardBrian commented 3 years ago

Checklist

[x] Used a personal fork of the feedstock to propose changes
[ ] Bumped the build number (if the version is unchanged)
[x] Re-rendered with the latest conda-smithy (Use the phrase code>@<space/conda-forge-admin, please rerender in a comment in this PR for automated rerendering)
[x] Ensured the license file is being packaged.

Resolves #6

conda-forge-linter commented 3 years ago

Hi! This is the friendly automated conda-forge-linting service.

I just wanted to let you know that I linted all conda-recipes in your PR (recipe) and found it was in an excellent condition.

WardBrian commented 3 years ago

@conda-forge-admin, please rerender

WardBrian commented 3 years ago

From Sebastian Weber, who has led a lot of the threading work on CmdStan:

Our tests were done for single-core, single-chain performance tests. Under these circumstances I would say that turning on threading for macos and Linux is really ok. For Windows we look at an up to 20% performance. Loss. This could have changed by the new g++ 8 from the new rtools and this could look different due to now having to consider running 4. Chains. In. parallel. If you want to test this, then use an ODE based model with an RK45 integrator. That will stress the memory system a lot.

I should look into some testing. As he mentions, in the next version this will not really apply, as running chains in parallel will be much easier.

WardBrian commented 3 years ago

Closing, see https://github.com/stan-dev/cmdstanpy/issues/436#issuecomment-956252365

conda-forge / cmdstan-feedstock

Try stan threads option #7