denormals/subnormals are heading for extinction

[dewar@gnat.com]

<<What sort of non-theoretical evidence is there?
The cited paper is dated 1984, before most of the
architectures listed above even existed.
>>

That does not make the paper invalid, since the value of denormals
is an architecture independent issue ...

<<What?!!  Performance on denormals is abysmal on
typical implementations of the following architectures:

   ALPHA, SPARC, PA-RISC, IA32, IA64

IBM's POWER and PPC implementations have good performance on denormals.
(Are there any others?)
>>

That's excessive rhetoric. Indeed abysmal, like very is one of those words
that people use when they do not have relevant quantitative data. I have
not seen any application on the ia32 where the overall performance is
significantly affected by the denormal implementation, and would be
very interested to see counter examples. Again, I am thinking about
the entire overall performance of a complete application (nothing
else is relevant).