Re: MI400 Digest, Vol 5, Issue 5

i thank both of you for your posts .. have lost track of Dr Frank .. and no 
ideation of the
XXXXX appeance which has been mentioned .. 

the sites provided, i have reviewed and am entirely thankful that individuals 
are 'following' this progress

the 3x5 example is of humor ... i have had the privilege of knowing one of 

those (4?) , who reported that one can factor 15 .. by 'Quantum' methods    
an IBM Reseach triumph 

but actually the ideation of 'Big' Numbers i will roll over to another topic

i have interest in exploiting 'Linear Congruence Psuedo' on the i-platform ... 
buried in a 'simulation' model .. which could be repeatable .. 

with respect b wilson

  

----- Original Message ----
From: "mi400-request@xxxxxxxxxxxx" <mi400-request@xxxxxxxxxxxx>
To: mi400@xxxxxxxxxxxx
Sent: Friday, March 30, 2007 10:00:08 AM
Subject: MI400 Digest, Vol 5, Issue 5


Send MI400 mailing list submissions to
    mi400@xxxxxxxxxxxx

To subscribe or unsubscribe via the World Wide Web, visit
    http://lists.midrange.com/mailman/listinfo/mi400
or, via email, send a message with subject or body 'help' to
    mi400-request@xxxxxxxxxxxx

You can reach the person managing the list at
    mi400-owner@xxxxxxxxxxxx

When replying, please edit your Subject line so it is more specific
than "Re: Contents of MI400 digest..."


Today's Topics:

   1. Re: 'Big Integers' -re a Fall06 thread ADDLC (Dave McKenzie)
   2. Re: 'Big Integers' -re a Fall06 thread ADDLC (Walden H. Leverich)


----------------------------------------------------------------------

message: 1
date: Wed, 28 Mar 2007 11:05:51 -0700
from: Dave McKenzie <davemck@xxxxxxxxxxxxx>
subject: Re: [MI400] 'Big Integers' -re a Fall06 thread ADDLC

Bruce Wilson wrote:
<snip>

-- the POWER6 overview presented recently noted that this 'technology'
includes native 'decimal arithmatic'  .. the 'puff' piece said that it
is a response to federal requirements that 3 x 5 = will never be
14.999999999...

<snip>


Here's a link to a 'puff' piece about POWER6:

http://news.zdnet.com/2100-9584_22-6124451.html

The 14.999999 they mention would only occur if you used binary
floating-point.  If you use all fixed-point decimal operands for
calculating either 3 x 5, or as the article mentions, .1 x $1.50, you
would get exactly 15 (or 15 cents).

Currently, POWER chips can do fixed-point arithmetic only in binary,
which requires some elaborate machine code to do decimal arithmetic.
Here's an example of the iSeries machine code generated in an MI pgm for
adding two 9-digit packed fields (42 machine instructions!):

http://groups.google.com/group/comp.arch/msg/f7b8a64c7e85591e

The wikipedia page:

http://en.wikipedia.org/wiki/POWER6

links to some descriptions of the new DFPU (Decimal Floating Point Unit)
in POWER6.

Sounds like it will do floating point operations directly on decimal
data, to eliminate the 14.999999 approximations caused by conversions to
and from binary.  It should also greatly reduce the number of machine
instructions generated.

--Dave






------------------------------

message: 2
date: Thu, 29 Mar 2007 10:50:15 -0400
from: "Walden H. Leverich" <WaldenL@xxxxxxxxxxxxxxx>
subject: Re: [MI400] 'Big Integers' -re a Fall06 thread ADDLC

Sounds like it will do floating point operations directly on decimal
data, to eliminate the 14.999999 approximations caused by conversions

to

and from binary.  It should also greatly reduce the number of machine
instructions generated. 

Per Dr. Frank at NEUGC Tuesday night the mainframe folks "demanded"
decimal math on the chip as part of moving the mainframe to Power6.
You're exactly correct, there will now be chip instructions that perform
decimal math -- should make it _much_ faster. Um, and the 4-5 GHZ clock
speed won't hurt either.

-Walden

PS. Disclaimer -- As Dr. Frank pointed out at the start of his talk,
we'd all had access to the open bar so we might have imagined anything
he said. <G>