4x faster strlen with 4 char sentinel

[Jay Norwood via Digitalmars-d-announce]

On Tuesday, 28 June 2016 at 09:18:34 UTC, qznc wrote:
> Did you also compare to strlen from libc? I'd guess GNU libc 
> uses a lot more tricks like vector instructions.

I did test with the libc strlen, although the D libraries did not 
have a strlen for dchar or wchar.  I'm currently using this for 
comparison, and playing around with shorter string lengths:

nothrow pure size_t strlen(const(char)* c) {
   if (c is null )
     return 0;
   const(char)* c_save = c;
   while (*c) {
     c++;
   }
   return c - c_save;
}

I'm also trying some tests on a PA device where I have tools to 
look at cache hits, misses, branches mispredicted.  Similar C 
code.