# Pure Julia HINT benchmark

**URL:** https://discourse.julialang.org/t/pure-julia-hint-benchmark/88055
**Category:** General Usage
**Created:** [September 30, 2022, 8:04pm UTC](https://discourse.julialang.org/t/pure-julia-hint-benchmark/88055 "2022-09-30T20:04:31Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![dlakelan](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/dlakelan/32/8491_2.png) [@dlakelan](https://discourse.julialang.org/u/dlakelan)
#### Post date: [September 30, 2022, 8:04pm UTC](https://discourse.julialang.org/t/pure-julia-hint-benchmark/88055/1 "2022-09-30T20:04:31Z")

</div>

Back in the day John Gustafson and friends invented a really great benchmark called HINT (Hierarchical INTegration).

It measures quality improvements per second (quips) as a function of memory used… So produces a curve of quips vs size.

> **[Hierarchical INTegration](https://en.m.wikipedia.org/wiki/Hierarchical_INTegration)**
>
> Hierarchical INTegration, or HINT for short, is a computer benchmark that ranks a computer system as a whole (i.e. the entire computer instead of individual components). It measures the full range of performance, mostly based on the amount of work a computer can perform over time. A system with a very fast processor would likely be rated poorly if the buses were very poor compared to those of another system that had both an average processor and average buses. For example, in the past, Macintosh ...

[https://web.archive.org/web/20130724124556/http://hint.byu.edu/](https://web.archive.org/web/20130724124556/http://hint.byu.edu/)

Originally this was hosted at iastate.edu anyway the C code is available.

[http://www.cs.kent.edu/~farrell/cc11/reference/hint/](http://www.cs.kent.edu/~farrell/cc11/reference/hint/)

It’s really not a complicated program and I think would be pretty easy for someone to write a pure Julia version of. I know you code golfers and benchmark people are just itching to make stuff run fast. Perhaps someone wants to do this rewrite? It truly was a great benchmark design.

Note: multi threaded and clustered versions also worthwhile to think about!

Note, the wiki article also links to the original paper which is worth reading

> **[article.pdf](https://zenodo.org/record/1269297/files/article.pdf?download=1)**
>
> 926.70 KB