Hi, Joe:

Packed decimal arithmetic is inherently a CISC kind of operation. Machines without microcode
and the ability to execute whole subroutines in microcode (including the PowerPC family) are at
a disadvantage, because the compiler must either generate a call to runtime routines or generate
quite a few in-line instructions to do the job.

Some time ago, Mr. Dave McKenzie posted some details on the MI400 list. Here is a link:
http://archive.midrange.com/mi400/200703/msg00003.html
Stop speculating, and do some reading. Educate yourselves. :-)

Enjoy!

Mark S. Waterbury

> Joe Pluta wrote:
Walden H. Leverich wrote:
I assume you mean you doubt the MI codes use the wrong instructions. I
doubt it too, but they why such a difference? I guess it's just a nature
of the beast given that the integer math is mostly shift and other
low-cycle (single-cycle) operations where the packed math is
multi-cycle. But I would have assumed that the built-in hardware was
optimized for just that purpose, almost an ASIC on a CPU. :)
Perhaps when the machine was moved from CISC to RISC, any CPU-level packed decimal opcodes were removed.

Joe

As an Amazon Associate we earn from qualifying purchases.

This thread ...

Replies:

Follow On AppleNews
Return to Archive home page | Return to MIDRANGE.COM home page

This mailing list archive is Copyright 1997-2024 by midrange.com and David Gibbs as a compilation work. Use of the archive is restricted to research of a business or technical nature. Any other uses are prohibited. Full details are available on our policy page. If you have questions about this, please contact [javascript protected email address].

Operating expenses for this site are earned using the Amazon Associate program and Google Adsense.