News for hackers. Stuff that matters.

A comment on Making floating point math highly efficient for AI hardware.

Re:Making floating point math highly efficient for AI hardware by saagarjha on Friday November 09, 2018 @09:54PM (#18419659)
I find it interesting that they were able to find improvements even on hardware that is presumably optimized for IEEE-754 floating point numbers.
[ Parent | on HN ]
Re:Making floating point math highly efficient for AI hardware by nestorD on Saturday November 10, 2018 @10:50AM (#18421795)
It is a trade-of : they find improvements by losing precision where they believe it is not useful for their use case.
[ Parent | on HN ]