From: Ben Goertzel (email@example.com)
Date: Thu Sep 08 2005 - 15:53:25 MDT
IMO, Loosemore is correct. *Coding* for parallel machines is no problem.
And, designing algorithms to do simple things like matrix manipulations on
parallel architectures may be relatively easy. But designing and analyzing
complex algorithms on parallel architectures is an extremely difficult part
of computer science.
I have published in this area, and programmed for a Connection Machine, so I
am well aware of the subtleties involved here.
-- Ben G
> -----Original Message-----
> From: firstname.lastname@example.org [mailto:email@example.com]On Behalf Of Michael
> Sent: Thursday, September 08, 2005 5:42 PM
> To: firstname.lastname@example.org
> Subject: Re: Introduction
> Richard Loosemore wrote:
> > J. Andrew Rogers wrote:
> >> Parallel == Serial == Parallel. It is not special, just
> complicated, and
> >> fairly vanilla large systems design knowledge these days. It
> is complex,
> >> but not *that* complex. I deal with this every day.
> > Oh, spare me!! I'm sorry, but this is complete BS. If you deal with
> > massively parallel programming every day, and you think it is no harder
> > than anything else, then you have never seen it in your life.
> I'm with James on this on; Richard is once again showing a tendency
> to dramatise. Parallel programming has its own set of problems and
> techniques, and programmers often make a hash of things because they
> try to implement parallel systems without first becoming familiar with
> the relevant tools and pitfalls. But there's nothing particularly
> special about designing parallel systems; the problems involved can
> be easy or very difficult, depending on what you're trying to build,
> but the expertise required to do so is pretty straightforward to
> accquire. This is engineering, not blue sky research like AGI. I
> have employed and continue to use numerous forms of parallelism in
> my software engineering career, and I find the amount of whining in
> the industry that 'parallelism is so difficult - oh no we have to
> learn something new and actually do algorithm design in advance!'
> highly amusing (and I gather most computer hardware engineers share
> this amusement). Sure parallelism makes things incrementally more
> difficult, but that's trivial compared to the difficulty of the real
> challenges in AGI.
> * Michael Wilson
> To help you stay safe and secure online, we've developed the all
> new Yahoo! Security Centre. http://uk.security.yahoo.com
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:52 MDT