Re: Apple, Jobs, and the irony of it

[Sheldon Simms <sheldonsimms@yahoo.com>]

On Mon, 25 Aug 2003 18:20:35 +0000, Michael J. Mahon wrote:

> Further, the IA-32 code analysis/translation parts are needed
> only because of IA-32 compatibility, and could be dispensed with
> in a more modern design.  These parts of the implementation
> 1) represent additional complexity not required at execution
> time, and 2) are doing a partial parallization job on-the-fly with
> very limited knowledge and resources, compared to what a
> modern optimizing compiler can bring to bear.

And yet it seems that people are having trouble writing compilers
that generate good code for the Itanium. There are even voices
starting to be heard suggesting that the next Itanium generation
may be an out of order processor.

I don't have enough knowledge of CPU engineering to make authoritative
statements, but I have heard people who do design CPUs say that the
cost of decoding x86 instructions is only a very small part of the
transistor and power budgets on todays CPUs. Removing the x86
decoders might do no more than reduce power dissipation by 5%,
die area by 2% and 1 or 2 pipeline stages.

comp.arch is a good newsgroup for this type of discussion. They
talk about this sort of thing all the time.