Beating Floating Point at Its Own Game: Posit Arithmetic [pdf]
johngustafson.net
Beating Floating Point at Its Own Game: Posit Arithmetic [pdf]
1–10 of 53 posts
Re: Beating Floating Point at Its Own Game: Posit Arithmetic [pdf]
#2I read the book on Type I Unums, it was quite interesting but I'm not an expert in this field. However, I appreciate the fact you don't have to buy a book to find his new research.
Re: Beating Floating Point at Its Own Game: Posit Arithmetic [pdf]
#3That looks really cool. Is there hardware support for posits anywhere?
Re: Beating Floating Point at Its Own Game: Posit Arithmetic [pdf]
#4HN discussion from 2 years ago:
Re: Beating Floating Point at Its Own Game: Posit Arithmetic [pdf]
#5That looks really cool. Is there hardware support for posits anywhere?
John Gustafson is on the board of Rex Computing, a small semi startup. They claim to have taped out last year, but I don't know if the chip has been validated or if it had posits in silicon, but I know that is one of their longer term goals.
I find Gustafson's UNUMS 2.0 more compelling than the first version.
Re: Beating Floating Point at Its Own Game: Posit Arithmetic [pdf]
#6That looks really cool. Is there hardware support for posits anywhere?
John Gustafson is on the board of Rex Computing, a small semi startup. They claim to have taped out last year, but I don't know if the chip has been validated or if it had posits in silicon, but I know that is one of their longer term goals. I find Gustafson's UNUMS 2.0 more compelling than the first version.
John's presentation more or less mirrors the topics covered in the paper: https://www.youtube.com/watch?v=aP0Y1uAA-2Y
Re: Beating Floating Point at Its Own Game: Posit Arithmetic [pdf]
#7Here's a C/C++ partial implementation of posits:
Re: Beating Floating Point at Its Own Game: Posit Arithmetic [pdf]
#8That looks really cool. Is there hardware support for posits anywhere?
John Gustafson is on the board of Rex Computing, a small semi startup. They claim to have taped out last year, but I don't know if the chip has been validated or if it had posits in silicon, but I know that is one of their longer term goals. I find Gustafson's UNUMS 2.0 more compelling than the first version.
Founder of REX Computing here, we taped out in July of 2016 and got our silicon brought up and working back in February. I gave a talk at Stanford showing our hardware and a tiny bit of software: https://www.youtube.com/watch?v=ki6jVXZM2XU
Type 2 unums are pretty much entirely deprecated by type 3 unums (now given the name 'posits' as referred to in the OP's linked paper)... they are basically superior in every way, and I recommend watching John's February 2nd talk at Stanford.
Re: Beating Floating Point at Its Own Game: Posit Arithmetic [pdf]
#9Here's a C/C++ partial implementation of posits: https://github.com/libcg/bfp
Thanks! Can you elaborate on what's missing?
Re: Beating Floating Point at Its Own Game: Posit Arithmetic [pdf]
#10HN discussion from 2 years ago: https://news.ycombinator.com/item?id=9943589
This is different from unums which it says so in the second line of the Abstract.