🚀 go-pugleaf

In article <27935@winchester.mips.COM> mash@mips.COM (John Mashey) writes:
 >The REAL question is: how much difference does it really make?
 >Everybody please remember this was a "what-if" analysis, not an
 >analysis that claimed that it really cost 1.6X in performance.
 >At least several vendors who ahve looked at this and did care about
 >COBOL didn't think that it was this much degradation to overall system
 >performance, or at least, in designing their RISCs, included a few
 >simple instructions to help the issue, and chose to stop there.

If I may throw in my $.02 worth:  Decimal arithmetic is alive and
well and not merely an artifact of old COBOL implementations.  We
do everything in C and require decimal arithmetic because of the
business nature of our applications.  It is a constant disappointment
when the scientific-oriented hardware industry forgets that some of
us need to have 100 pennies == 1 dollar.  Interest calculations
carried out to 3 or 4 decimal places need to round correctly.
Converting to binary and back to decimal is not the answer (as
I explained in a previous posting).

Fortunately, business applications are usually I/O bound so the
decimal math can be simulated in software without a perceived
performance penality (unless you bring in an unethical benchmark).

If decimal add and subtract are too costly in the hardware then
why not a simple decimal adjust instruction (like on the 80x86)?
That instruction alone is a great savings when you consider the
software alternatives.  The 3B2 has *nothing* to help decimal
arithmetic.

-- 
Scott Amspoker
Basis International, Albuquerque, NM
(505) 345-5232