A few thoughts from Mr. Spock...
Logically, for the old routines to be faster than the new routines there a 2 possible choices here:
1) The old routines (from exec) were patched with a CMQ patch which has faster routines than the new routines (from Copymemquicker2.
OR
2) The old routines (from exec) are faster than the new routines (from Copymemquicker2.
P.S. If the old routines (from exec) are really faster than why would anyone bother coding or using CMQ patches?
This still doesn't make sense. Although I think I'm starting to get your logic, it's rather confusing to the layman. Trying to dumb it down for the average person, I'd still write it like this:
Performance of routines without any patch: x
Performance of routines with version of patch you released a month or so back: y
Performance of routines with new version of patch you released this week: z
Logically, that should be a descending sequence of numbers. I.e., if it takes 20 seconds without any patch, 15 seconds with the old version of patch, and 10 seconds with the latest new and improved version of the patch. Why would you write a new version of the patch that's slower than the old version of the patch?
Would still like to see a speed comparison against this version, BTW!
http://aminet.net/package/util/boot/CopyMemAnyhow, just messing with ya. Keep up the good work!