Peter Farley's points are interesting ones.  My numbers tell a very
different tale, and I suspect that these differences turn on when such
measurements are taken.

The first appearances of new instructions, millicoded ones anyway, do
often exhibit 'bad' performance; but this performance sometimes, even
usually, improves rapidly.

Working with millicoded instructions has taught me two important
lessons: Their performance is a moving target, and early measurements
of it are usually misleading.  It often improves significantly in the
interval that would be required to replace them with alternative
sequences.

John Gilmore, Ashland, MA 01721 - USA

Reply via email to