On Wed, 8 Oct 2003, Leopold Toetsch wrote: > Dan Sugalski <[EMAIL PROTECTED]> wrote: > > > ... (More bizarrely, it's actually *faster* to use Integer PMCs, which > > do MMD, than it is to use PerlInt PMCs, which don't do MMD. Go figure :) > > I don't have that here (Athlon). They are equally fast. PerlInts have > some overhead due to possible type morphing, though.
Hrm. This system's showing the PerlInt at about 25% slower for a tight division loop, though that's the most expensive case) > > I'll see about getting some docs into the system so this stuff is actually > > usable. > > That would be really necessary. I've some troubles to follow the flow of > execution with MMD and how all these methods play together. Prelim docs are in. Dan