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

[bugzilla-daemon at libre-soc.org]

https://bugs.libre-soc.org/show_bug.cgi?id=1044

--- Comment #6 from Jacob Lifshay <programmerjake at gmail.com> ---
(In reply to Luke Kenneth Casson Leighton from comment #5)
> (In reply to Jacob Lifshay from comment #4)
> 
> > how long is overly long?
> 
> greater than fits into 3-4 cache lines, absolute maximum.
> the goal here is to eliminate TLB and L1 cache lookups.
I assume you mean misses rather than lookups.

> this is for an embedded scenario not a supercomputing
> scenario.

ok, using O(n^2) multiplication could work since embedded cares less about
speed and we can assume rsa is infrequently run so power doesn't really matter.
I also already have code for O(n^2) mul in bigint-presentation-code.

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