🚀 go-pugleaf

In article <6196@orca.wv.tek.com> andrew@frip.wv.tek.com writes:
:	"for the most part, I really like the 88K, but the $#@ MUL
:	instruction is totally brain-damaged. It's a 32x32 giving 32
:	multiply, and it DOESN'T TELL YOU if it overflows!"
:
:I kinda like this instruction.  The lion's share of Unix workstation
:multiplies seem to discard all but the low 32 bits of the result, and
:don't check for overflow.  By implementing a 32x32 -> 32 multiply
:instruction, you get two small RISCy wins:
:If you want more than 32 bits of result, or overflow detection, there
:are two relatively cheap ways to get there: multiply in
:double-precision floating point mode (no problem since every 88k has an
:FPU), or have a routine which fires off the three integer multiplies

Uh, I suggest you go back and check your arithmetic. There is no
way to multiply two 32-bit integers together using double precision
floating point multiplies. The IEEE spec specifies a 53-bit mantissa
for 64-bit double multiply. So how does one compute a 32x32 multiply
in 53 bits?

-- 
Bob Silverman
#include <std.disclaimer>
Internet: bs@linus.mitre.org; UUCP: {decvax,philabs}!linus!bs
Mitre Corporation, Bedford, MA 01730