News for hackers. Stuff that matters.

A comment on Future instruction set: AVX-512. Parent comment

Re:Future instruction set: AVX-512 by jey on Thursday October 10, 2013 @01:39AM (#6525837)
The original post that started this thread was saying that chips should support decimal floating point natively in silicon instead of only base-2 floating point. Yes, those are different things: https://en.wikipedia.org/wiki/IEEE754#Basic_formats
[ Parent | on HN ]
Re:Future instruction set: AVX-512 by drewcrawford on Friday October 11, 2013 @07:20PM (#6536454)
I am well aware of the difference between base 2 and base 10.

You asked "why not just use doubles?" And my answer is "because one often multiplies by powers of ten."

[ Parent | on HN ]