Re: AMD planning 45nm 12-Core 'Istanbul' Processor ?

On May 22, 10:40 am, Robert Redelmeier <red...@[EMAIL PROTECTED]
> wrote:
> Robert Myers <rbmyers...@[EMAIL PROTECTED]
> wrote in part:
>
> > On May 21, 11:01 am, Robert Redelmeier <red...@[EMAIL PROTECTED]
> wrote:
> > A recent poster to comp.arch referred to the "cubic dollars"
> > that AMD and Intel had spent to make the instruction decoding
> > problem go away, so I assume that the investment was large.
> > The software quality problem is huge and a huge investment to
> > solve it is more than justified.
>
> Uhm ... err ... when did you start believing USENET uncritically?
> "cubic dollars" I take as BILLIONS, and AMD has never had this to
> spend on development.

The poster was an AMD architect.

> > Market mechanisms were adequate to drive a solution to
> > the RISC vs.  CISC problem, but market mechanisms do not
> > always work.
>
> This depends entirely on your definition of "work", and you
> must expect different people to have different values.
>
That's easy.  Markets that "work" are left alone.  Markets that don't
"work" are regulated.

> > You have only to look at the pharmaceutical industry.
> > I urge you not to take me on about this one.  I lost a good
> > friend three summers ago because of the long term effects
> > of a miracle drug that was introduced before we had our
> > current system of regulation.
>
> Uhm ... err ... the US FDA has been around since the 1930s.
> They were somewhat lax until the Thalidomide debacle in the
> late 1950s, clamped down and predictably have been relaxing
> ever since, especially in the past 15 years.
>
You went there, anyway.  The thalidomide debacle was not the only
one.  Spare me your um's and errs.  My friend is *dead*.

> > The system of drug regulation we have now is far from perfect,
> > but a stroll around Cambidge****t on the edge of the MIT campus
> > will clue you in that lots of money is being made, in spite of
> > hugely burdensome regulatory requirements like drug trials.
>
> Why do you think spending and flash cash equates to
> money being made?  Real money is invisible -- Omaha NE.
>
I thought financial wizards knew how to estimate risk.

> >> Quality is a variable to be optimized, not some
> >> deity to be wor****pped.  "Beware false gods".
>
> > I can just imagine hanging that as a motto in someone's office.
> > You're kidding, right?  Heard of ISO 9000?  Prepare to wor****p a
> > false god.  From what I've seen of it, I'm not keen on ISO 9000,
> > but the success of something so clunky should be a clue.
>
> Interesting you should bring that up.  I have much more than a clue.
> At work, I've been an ISO-certified internal auditor for 5 years.
> The ISO 9000 series really isn't onerous at all: "say what you do,
> and do what you say".  It is mostly just good management and some
> do***entation that you really should have been keeping all along.
>
It depends on the business you're in, I suppose.

> > It doesn't matter what it proves.  No one will be asking
> > George Bush's advice about war making except as a learning
> > from mistakes exercise.
>
> Maybe so, but it is far from proven that Hil Obamacaine
> would have done any better.
>
This is not a discussion of politics.  I brought him up as another
"expert" that no one who knew recent history would cite.  Financial
institutions claim that one of their areas of special expertise is
management of risk.  Recent history has proven that they are at best
unreliable.

> > Similarly, citing financial institutions as expert in risk
> > management would have worked before Long Term Capital Management.
> > As it is, the financial industry, like George Bush, is a study
> > in the catastrophic consequences of being overconfident.
>
> You should study Taleb's book "Black Swans"
>
Looks like an interesting book.  Thanks for calling it to my
attention.

The difference is that most software risk is not unexpected and can be
eliminated.

> > The funny thing about risk, like NASA's estimates of risks
> > to the shuttles, is that you learn that the methodology is
> > faulty only after a catastrophic failure.  A statement of
> > confidence about handicapping of risk should tell you to
> > find another handicapper.
>
> No, you just need to realize that failure of imagination
> can have serious conequences.  "unknown unknowns"
>
As painful as the shuttle disasters were, we learned things from each
one.  They have resulted in changes in methodology, not drugs to
increase imaginative capacity.  What will *not* happen, unfortunately,
is to recognize the behavior patterns of managers present in both
cases and to eliminate such people from critical decision-making
roles.

> > Big changes are on the way.  Maybe later rather than sooner,
> > but they will come.  If you're going to plug into the internet,
> > you will be regulated.  I'm not happy about that, but I see no
> > way around it.
>
> Please rail away.  I don't mind.  IPv6 has some threats built-in.
> But short of technically, managerially and socially infeasible total
> packet capture there really is no way to regulate the internet.
> Smart people have tried with at best partial success.
>
ISP's are packet-capturing now.  CISCO has just released an appliance
with mind-bending bandwidth.

Robert.