[V2] riscv: Implement Zbb based strlen and prefer it over the RVV based strlen implementation when Zbb is available

[Jeffrey Law]

On 7/5/2026 6:20 AM, Florian Weimer wrote:
> * Jeffrey Law:
>
>> I'm seeing some really weird results and I wish camel-cdr had data on
>> a Zbb implemenation to correlate against -- his data has been
>> incredibly helpful in confirming the vector behavior as well as the
>> generic implementation behavior.  But he didn't have a zbb variant.
>>
>> Basically it appears yours is meaningfully slower for small strings.
>> It starts off about 50% slower, but closes the gap for each 2^n length
>> bucket.  The crossover point is around 128 bytes after which it blows
>> away the other zbb variant -- it was still widening the gap at the 8k
>> bucket where it was about 60% faster.  *BUT* the loop itself is
>> unchanged and while it appears there's one less architectural register
>> in use, I'd be amazed if that one register was enough to make this
>> kind of difference at the uarch level.
> Hmm, maybe it's not working correctly and incorrectly returning early?
That was my suspicion.   I'll need to see what make check reports when 
I'm back home and I don't have to fight internet connection drops.  I 
certainly don't see anything obvious when I look at the code.

> As I said, it's untested.  Or maybe it's related to the .p2align?
That's a secondary possibility as well.  I recall the K1 having a loop 
buffer of some sort, so the K3 might as well.  The details were quite 
scarce, but I could imagine the possibility that if we the main loop's 
location within a icache line changed that we may or may not be running 
out of the loop buffer.
>
> The dependency chains should be equal or shorter even for short strings,
> so the regression is surprising.  And the loop really should not get any
> faster.
That's my read of the code as well.  Hence my confusion.

jeff