[Libre-soc-isa] [Bug 1057] split out all int/fp min/max ops into their own RFC ls013

bugzilla-daemon at libre-soc.org bugzilla-daemon at libre-soc.org
Wed Apr 26 03:03:55 BST 2023


--- Comment #29 from Jacob Lifshay <programmerjake at gmail.com> ---
(In reply to Jacob Lifshay from comment #28)
> It produces the exact same results because min/max is independent of
> precision/range and has no round off error, it behaves identically for
> f32/f64/f32-in-f64/etc. the only part that varies is which bits it reads
> from and sets for quieting sNaNs, and the changes caused by SINGLE/DOUBLE
> (only relevant for not-really-f32 in f32-in-f64), which is only relevant for
> f32, not f64/f32-in-f64.

clarification, "only relevant for f32" is referring only to which bits are
read/set (basically f32's exponent/mantissa fields are in a different place), I
added the SINGLE/DOUBLE part after and forgot to update the rest of the

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

More information about the Libre-SOC-ISA mailing list