[Beowulf] Moores Law is dying

Greg Lindahl lindahl at pbm.com
Tue Apr 14 11:24:40 PDT 2009


On Tue, Apr 14, 2009 at 10:55:22AM -0700, Jon Forrest wrote:

> I claim that there's a memory-related constant that hasn't been
> widely recognized. This is that the amount of address space for
> a program's text segment will never exceed 32 bits. Note that
> I am *not* talking about the data segment.

You're right, the "large" memory model doesn't exist in x86-64,
because no one ever thought about it. (Check the gcc manpage for
-mcmodel=large ... it's not implemented, but it's spec'd out.)

> The reason for this is that it's simply too hard to write
> a program whose instructions require even close to the
> 32 bit address space.

There are disciplines like EDA which generate large programs today.
Computer generated, of course. Companies like Intel and AMD use these
programs to design microprocessors. So yes, their architects are well
aware of this issue.

> But, it's important
> to realize that this limit exists, and unless
> we get much smarter, isn't likely to go away.

Uhuh. You should call this "Forrest's Law".

-- greg






More information about the Beowulf mailing list