Thread Links Date Links
Thread Prev Thread Next Thread Index Date Prev Date Next Date Index

Re: I vote NO on Motion P1788/M0024.02:RoundedOperations



> From: "Nate Hayes" <nh@xxxxxxxxxxxxxxxxx>
> To: "Dan Zuras Intervals" <intervals08@xxxxxxxxxxxxxx>,
> 	"Ulrich Kulisch" <Ulrich.Kulisch@xxxxxxxxxxx>
> Cc: <stds-1788@xxxxxxxxxxxxxxxxx>,
> 	"Dan Zuras Intervals" <intervals08@xxxxxxxxxxxxxx>
> Subject: Re: I vote NO on Motion P1788/M0024.02:RoundedOperations
> Date: Sun, 15 May 2011 11:05:51 -0500
> 
> Dan Zuras wrote:
> > Ulrich,
> >
> > I quote from your motion:
> >
> > Instead, a future interval arithmetic standard should
> > require that EVERY FUTURE PROCESSOR shall provide the
> > 16 operations listed above as distinct instructions.
> >
> > (emphasis yours in bold).
> 
> Dan,
> 
> You are quoting version 1 of the motion from 4/15/2011.
> 
> We are voting on the friendly amedment made by Prof. Kulisch on 4/29/2011 
> which changed that passage to:
> 
> "The operations with the directed roundings should be implemented directly 
> in hardware for efficiency reasons."
> 
> There were also a few other changes based on comments made earlier by Prof. 
> Fahmy and others.
> 
> I hope people are basing their votes on the right motion!
> 
> Nate

	Hmm.  Interesting.  We have 3 files here.

	The file Prof Kulisch posted on 4/15 is called RoundOper.pdf

	I am quoting from the file that is on the motions website as
	documentation for motion 24 which is motion24roundOper.pdf.

	It is the file I consulted when I made up my mind & it contains
	the passage you see above.

	But you are correct, the file Ulrich posted on 4/29 under the
	name RoundOper1.pdf contains the modified passage:

		The operations with the directed roundings SHOULD be
		implemented directly in hardware for efficiency reasons.

	However, the paragraph that now preceeds that passage states:

		Every IEEE 1788 compliant system SHALL provide the 8
		operations with the directed roundings by distinct
		operation codes. Each of the 8 operations SHALL be
		callable as a single instruction. The rounding SHALL
		be an integral part of the arithmetic operation.
		Employing an operation with a directed rounding must
		be as simple as employing the corresponding operation
		with rounding to nearest.

	(emphasis his in bold).

	Do you REALLY think that's an improvement?

	I think the intent is clear & it does not change my mind.
	All my arguments apply to this motion as well as the other.

	I guess I vote NO whichever is the correct motion.


				Dan