> On Aug 22, 2015, at 10:31 PM, Chuck Guzis <ccl...@sydex.com> wrote:
> 
> On 08/22/2015 06:26 PM, Paul Koning wrote:
> than the usual rule).
>>> 
>>> I recall the "integer multiply" feature (i.e. optional) available
>>> on the 6000.  IXi  Xj*Xk, but it didn't provide any more precision
>>> than the usual unnormalized double-precision multiply  DXi  Xj*Xk,
>>> but saved some time spent fiddling with exponent fields.
>> 
>> ???  Never heard of any such thing.  IXi Xj*Xk is a defined opcode,
>> but it's simply a synonym for Dxi Xj*Xk.
> 
> Well, we were always the guinea pig for QSEs in SSD.  It's not described in 
> the Cyber 70 docs, but we had Cybers fitted with the option.  It did make its 
> way into the 170s however:
> 
> In 60456100A, re: the 42 instruction (page 4-24, second column):
> 
> "This instruction is used in multiple-precision floating-point calculations.  
> This instruction also provides for integer multiplication capabilities where 
> both operands have an exponent value of plus or minus zero and neither 
> coefficient has been normalized.  The integer result sent to Xi is *48 bits 
> with a 60-bit sign extension* (emphasis mine)."

Ok, but that is simply the standard 6000 series double multiply.  That's not an 
optional feature; the behavior you describe is how it always works and why 
IXX*X is a synonym for DXX*X.  All that's going on here is that the exponent 
field remains zero, so it acts as an extended sign field.

        paul

Reply via email to