[Libre-soc-bugs] [Bug 1044] SVP64 implementation of pow(x,y,z)

bugzilla-daemon at libre-soc.org bugzilla-daemon at libre-soc.org
Mon Oct 9 08:50:36 BST 2023


--- Comment #37 from Luke Kenneth Casson Leighton <lkcl at lkcl.net> ---
ok a correction there.  i *believe* that 1<<r3 and/or REMAP on
a Scalar with VF mode would give us the level of efficiency.
as this is your task it is down to you to attempt to use them.

if they *don't work* then we can carry out a re-assessment,
and design some new (future) SVP64 features.

even if we run out of time to actually complete the algorithm
the conditions of the grant have still been met *because we did
the assessment*.

but just going straight to something inefficient (such as the
loop-unrolled mul256 algorithm you wrote, although it gets us
one incremental step ahead), this is *not* satisfying the conditions
of the grant.

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

More information about the libre-soc-bugs mailing list