# Massive performance penalty for Float16 compared to Float32

**URL:** <https://discourse.julialang.org/t/massive-performance-penalty-for-float16-compared-to-float32/6864>\
**Category:** Performance\
**Tags:** performance\
**Created:** [November 3, 2017, 7:16pm UTC](https://discourse.julialang.org/t/massive-performance-penalty-for-float16-compared-to-float32/6864 "2017-11-03T19:16:50Z")\
**Posts on this page:** 1\
**Showing post:** 3

<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:** [November 3, 2017, 7:23pm UTC](https://discourse.julialang.org/t/massive-performance-penalty-for-float16-compared-to-float32/6864/3 "2017-11-03T19:23:12Z")

</div>

> [@zenon](#):
>
> Why is it allocating memory in the first place

Don’t benchmark in the global scope. Put that in a function and run twice.

---

_[View the full topic](https://discourse.julialang.org/t/massive-performance-penalty-for-float16-compared-to-float32/6864)._