[libre-riscv-dev] Yehowshua - Interested in open GPU dev

[Jacob Lifshay]

On Mon, Jan 6, 2020 at 7:25 AM Luke Kenneth Casson Leighton
<lkcl at lkcl.net> wrote:
> one othet thing we need is an implementation in nmigen of a dadda multiplier
> https://en.m.wikipedia.org/wiki/Dadda_multiplier
>
> however we need to also be able to partition it.

It might be a good idea to work on other things first, since the
integer multiplier we have works and is good enough (though may not be
the smallest, fastest, and/or most efficient) and there are other
things that aren't implemented at all yet such as floating-point
exception flag handling and/or dynamically-partitionable
fmul-add/fadd/fsub/fmul.

see https://salsa.debian.org/Kazan-team/simple-soft-float for some
reference code I wrote, which should match the IEEE 754 FP standard
(it matches Berkeley soft-float for all the cases I tested).

simple-soft-float uses RealAlgebraicNumber, which is a type that
behaves like an infinitely-precise real number which I used instead of
something else since I think that makes the logic easier to
understand.

Jacob