[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 10:22:43 BST 2023


--- Comment #42 from Luke Kenneth Casson Leighton <lkcl at lkcl.net> ---
(In reply to Jacob Lifshay from comment #39)
> (In reply to Luke Kenneth Casson Leighton from comment #37)
> > 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.
> which definition of efficiency are you using?

the one that meets customer requirements which i repeated many times:
top priority on code size. number of regs second.

it is down to the hardware to merge VF and HF elements into
 "issue batches".  which is here repeatedly everyone including
you keeps assuming VF is incapable of doing that "thrrefore it
musy be inefficient performance wise". this assumption is
100% false.

(In reply to Jacob Lifshay from comment #40)

> algorithm in a relatively short amount of time, I am not very confident I
> can write a vertical-first divmod at all and would probably need to go by
> way of writing a horizontal-first algorithm and then transforming it into a
> vertical-first algorithm anyway.

i don't have a problrm with that at all. good call, go for it.

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

More information about the libre-soc-bugs mailing list