From: rick.c.hodgin@nospicedham.gmail.com   
      
   On Saturday, June 24, 2017 at 5:50:14 PM UTC-4, Terje Mathisen wrote:   
   > Rick C. Hodgin wrote:   
   > > Can anybody help me optimize this code?   
   > [snip]   
   > > It's designed to be used as a custom assembly algorithm for a   
   > > stricmp() algorithm which follows this general pattern, which   
   > > is designed to be the target of a qsort() callback:   
   > >   
   > >     int caseless_compare(const void *p1, const void *p2)   
   > >     {   
   > >         int d;   
   > >         const unsigned char *s1 = p1;   
   > >         const unsigned char *s2 = p2;   
   > >   
   > >         while ((d = tolower(*s1) - tolower(*s2)) == 0 && *s1)   
   > >             s1++, s2++;   
   > >   
   > >         return d;   
   > >     }   
   > >   
   >   
   > Just writing a version of this code which can handle national 8-bit   
   > character sets is more interesting, you pretty much have to use some   
   > form of lookup table, i.e.   
   >   
   >    while (d = tolower[c = *s1++] - tolower[*s2++] && c) {};   
      
   This minor tweak has given the best results so far:   
      
       Rick2   = 123   
       Bart    = 117   
       Ben     = 116   
       RickAsm = 105   
       BartAsm = 104   
       Terje C = 96   
      
   The original algorithm yours was based off is the Ben score above.   
   Your little tweak gave it a 20-point gain.   
      
   FWIW, Terje, I am always impressed with your optimization skills.   
   That sentiment dates back to the 90s as well.  I've always viewed   
   you as the best assembly developer I know, and I admire your mind   
   and skills in considering the variables in tasks like this.   
      
   Thank you,   
   Rick C. Hodgin   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)