# Benchmarking of PPL

**URL:** <https://discourse.julialang.org/t/benchmarking-of-ppl/37850>\
**Category:** Probabilistic Programming\
**Created:** [April 19, 2020, 2:05pm UTC](https://discourse.julialang.org/t/benchmarking-of-ppl/37850 "2020-04-19T14:05:41Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![mystis](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/mystis/32/9327_2.png) [@mystis](https://discourse.julialang.org/u/mystis)\
**Post date:** [April 19, 2020, 2:05pm UTC](https://discourse.julialang.org/t/benchmarking-of-ppl/37850/1 "2020-04-19T14:05:41Z")

</div>

Hi all, I’ve seen the perf benchmark or sampling for Turing vs Stan but I was wondering if we have benchmarks for Pyro, pymc3, tensorflow-probabiliy with one chain and with multiple chains (since tfp seems to benefit from vectorizing chains?).

Thanks for the feedback!

---

<div class="post-metadata">

**Author:** ![mohamed82008](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/mohamed82008/32/18171_2.png) [@mohamed82008](https://discourse.julialang.org/u/mohamed82008)\
**Post date:** [April 19, 2020, 2:38pm UTC](https://discourse.julialang.org/t/benchmarking-of-ppl/37850/2 "2020-04-19T14:38:09Z")

</div>

I think extending the Turing vs Stan benchmarks [here](https://github.com/TuringLang/TuringExamples/tree/master/benchmarks) should be relatively straight-forward. Also, we have a GSoC project for this so it may be worked on soon.

---

<div class="post-metadata">

**Author:** ![ChrisRackauckas](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/chrisrackauckas/32/77_2.png) [@ChrisRackauckas](https://discourse.julialang.org/u/ChrisRackauckas)\
**Post date:** [April 19, 2020, 3:33pm UTC](https://discourse.julialang.org/t/benchmarking-of-ppl/37850/3 "2020-04-19T15:33:29Z")

</div>

We have some benchmarks of ODE solvers in PPLs as well:

[https://benchmarks.sciml.ai/html/ParameterEstimation/DiffEqBayesFitzHughNagumo.html](https://benchmarks.sciml.ai/html/ParameterEstimation/DiffEqBayesFitzHughNagumo.html)

[https://benchmarks.sciml.ai/html/ParameterEstimation/DiffEqBayesLotkaVolterra.html](https://benchmarks.sciml.ai/html/ParameterEstimation/DiffEqBayesLotkaVolterra.html)

Note that there’s a third benchmark which needs an update but Stan currently fails to be able to estimate it well, so for now we’re leaving that one off (we’ll need to decrease the timespan or something to make it easier to estimate for Stan).

---

<div class="post-metadata">

**Author:** ![trappmartin](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/trappmartin/32/1165_2.png) [@trappmartin](https://discourse.julialang.org/u/trappmartin)\
**Post date:** [April 19, 2020, 6:03pm UTC](https://discourse.julialang.org/t/benchmarking-of-ppl/37850/4 "2020-04-19T18:03:13Z")

</div>

We have applications of GSoC students that will conduct benchmarks comparing Turing with various existing PPLs including pyro and TF-probability.

---

<div class="post-metadata">

**Author:** ![mystis](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/mystis/32/9327_2.png) [@mystis](https://discourse.julialang.org/u/mystis)\
**Post date:** [April 21, 2020, 8:23pm UTC](https://discourse.julialang.org/t/benchmarking-of-ppl/37850/5 "2020-04-21T20:23:30Z")

</div>

Thank you all for the answers, I’m looking forward to it!