At Supercomputing 2015, NVIDIA announced Jetson TX1. This platform is the first available to natively expose mixed precision instructions. However, this instruction set requires that operations on 16-bit precision floating points are done in pairs, requiring usage of the half2 type which pairs two values in a single register.
Poster GTC 2016 – Using CLANG/LLVM Vectorization to Generate Mixed Precision Source Code
![](http://www.altimesh.com/wp-content/uploads/2016/03/gtc-2016-poster-thumb-1.png)