[music-dsp] digital circuit bending (was: DSP vs analog circuits)

[Robert Marsanyi]

Yeah, there was.  In a later revision of the 56000, Motorola implemented an
illegal instruction trap.  I was trying to use it (according to the docs)
but the version of the chip I was using didn't have the implementation.

--rbt

----- Original Message -----
From: Glen <mclilith at ezwv.com>
To: <music-dsp at shoko.calarts.edu>
Sent: Thursday, October 11, 2001 11:49 AM
Subject: Re: [music-dsp] digital circuit bending (was: DSP vs analog
circuits)


> At 01:09 PM 10/11/01 , douglas irving repetto wrote:
>
> >Robert Marsanyi has a couple really neat pieces called "Lurch" and
> >"Study for Lurch" in which he let a 56k dsp write its own opcodes. while
> >developing the piece he managed to burn out a dsp by generating illegal
> >opcodes! that's so cool. after that he put in code to make sure that all
> >opcodes generated were valid...
>
> That's very interesting. I wonder if the CPU in a PC might also
self-destruct,
> if fed the proper combination of bytes? That would be a virus writer's
> dream-come-true. I hope that the chip makers have taken precautions to
avoid
> this.
>
> Personally, I think there must be some sort of hardware flaw in a DSP or
CPU
> that would allow mere code to destroy the chip.
>
> Later,
> Glen
>
> dupswapdrop -- the music-dsp mailing list and website: subscription info,
> FAQ, source code archive, list archive, book reviews, dsp links
> http://shoko.calarts.edu/musicdsp/
>
>


dupswapdrop -- the music-dsp mailing list and website: subscription info,
FAQ, source code archive, list archive, book reviews, dsp links
http://shoko.calarts.edu/musicdsp/