gallier2 (gallier2.delete@this.gmx.de) on August 22, 2013 12:35 pm wrote:
> David Hess (davidwhess.delete@this.gmail.com) on August 22, 2013 10:55 am wrote:
> > Dan Fay (daniel.fay.delete@this.gmail.com) on August 21, 2013 1:13 pm wrote:
> > > Ricardo B (ricardo.b.delete@this.xxxxxx.xx) on August 20, 2013 3:27 pm wrote:
> > > >
> > > > I also like to think it would have been a good time to come up with a new,
> > > > cleaner, encoding scheme. But that's probably just wishful thinking.
> >
> > Someone did this (the guy who did all of the work on processor emulation?) when he published
> > his analysis of the scheme AMD used. I remember reading the article after the AMD64 instruction
> > set details were published but did not keep the link and my GoogleFu is weak.
> >
>
> Darek Mihocka who wrote Atari emulators for a living wrote about a better encoding that could have been made
>
> http://www.emulators.com/docs/nx05_vx64.htm
>
> he was recruted by Intel after that series of article.

That is the one I was thinking of. Thank you for providing the link.

His article about the instruction encoding reminded me a lot of a similarly themed article discussing an alternative DNA/RNA codon to amino acid code that exactly mapped the standard amino acids into 64 codons and removed the start/stop ambiguity from the existing code.