[libre-riscv-dev] [isa-dev] Re: FP transcendentals (trigonometry, root/exp/log) proposal
luke.leighton at gmail.com
Wed Aug 14 14:56:03 BST 2019
On Monday, August 12, 2019 at 6:52:16 PM UTC+1, MitchAlsup wrote:
> On Sunday, August 11, 2019 at 10:20:28 PM UTC-5, lkcl wrote:
> I would like to point out that the general implementations of ATAN2 do a
> bunch of special case checks and then simply call ATAN.
if there's no objections, i'll put ATAN back in [where it was formerly an
alias ATAN(x)=ATAN2(1.0, x)]. that will require implementors to microcode
the algorithm that Mitch described, and allow them to keep both 3D and UNIX
Profiles optimal without compromise of either profile.
More information about the libre-riscv-dev