[Libre-soc-isa] [Bug 817] Big Integer Math (sv.adde, sv.subfe, sv.madded, 128 by 64-bit -> 64-bit div/rem, maybe more...)

bugzilla-daemon at libre-soc.org bugzilla-daemon at libre-soc.org
Mon Apr 25 00:33:41 BST 2022


--- Comment #24 from Luke Kenneth Casson Leighton <lkcl at lkcl.net> ---
how about inverting un and vn if -ve then correcting if signs not equal?

inversion of bigint can be done with RB=scalar-zero, subtract RA as vector.

in case where n=1 then inversion of scalar v is easy.

leaves overflow etc to deal with but not a big deal.

am all for avoiding adding unnecessary ops here.

You are receiving this mail because:
You are on the CC list for the bug.

More information about the Libre-SOC-ISA mailing list