From: Ian Collins on
On 03/22/10 05:29 PM, Peter Olcott wrote:

> I can't reply to this post with quoting turned off. I always
> reply point for point, but, with quoting turned off it would
> be too difficult to see who said what. Is there any way that
> you can report your reply with quoting turned on?

There's nothing wrong with David's quoting, but there everything wrong
with your agent's. Google for "outlook quote fix"

--
Ian Collins
From: David Schwartz on
On Mar 21, 9:29 pm, "Peter Olcott" <NoS...(a)OCR4Screen.com> wrote:

> It seems you may have missed this point machine A and
> machine C are given to have identical processors, and the
> ONLY difference between them is that machine C has much
> faster access to RAM  than machine A.

You have previously said: "The new machines CPU is only 11% faster
than the prior
machine."

Unless the access to RAM is 8 times faster on machine C than machine
A, you cannot explain the performance difference as performance
scaling with RAM bandwidth.

DS
From: Eric Sosman on
On 3/21/2010 11:58 PM, Peter Olcott wrote:
> [...]
> (1) Machine A performs process B in X minutes.
> (2) Machine C performs process B in X/8 Minutes (800%
> faster)

The Rant, Reloaded: I could agree to "87.5% less time,"
and I could even accept "700% faster" with some reluctance.
But "800% faster" means X/9 minutes! (And yes: My teeth itch
every time a data-compression maven talks about "compression
ratios," because they make the same error. It's a fascination
with big, impressive-sounding numbers, that's all. Bah!)

Now, where did I put that supply of anti-psychotic pills?

--
Eric Sosman
esosman(a)ieee-dot-org.invalid
From: Peter Olcott on
RAM access speed by itself is 600% faster, and it has
32-fold more cache (8MB compared to 256KB) that is 200%
faster than the other machines cache and 13-fold faster than
the other machines RAM. These stats come from MemTest86.

"David Schwartz" <davids(a)webmaster.com> wrote in message
news:cbffa3f2-e9b8-49d8-8d89-c2ad0732f894(a)s2g2000prd.googlegroups.com...
On Mar 21, 9:29 pm, "Peter Olcott" <NoS...(a)OCR4Screen.com>
wrote:

> It seems you may have missed this point machine A and
> machine C are given to have identical processors, and the
> ONLY difference between them is that machine C has much
> faster access to RAM than machine A.

You have previously said: "The new machines CPU is only 11%
faster
than the prior
machine."

Unless the access to RAM is 8 times faster on machine C than
machine
A, you cannot explain the performance difference as
performance
scaling with RAM bandwidth.

DS


From: Peter Olcott on

"Eric Sosman" <esosman(a)ieee-dot-org.invalid> wrote in
message news:ho7mab$hln$1(a)news.eternal-september.org...
> On 3/21/2010 11:58 PM, Peter Olcott wrote:
>> [...]
>> (1) Machine A performs process B in X minutes.
>> (2) Machine C performs process B in X/8 Minutes (800%
>> faster)
>
> The Rant, Reloaded: I could agree to "87.5% less
> time,"
> and I could even accept "700% faster" with some
> reluctance.
> But "800% faster" means X/9 minutes! (And yes: My teeth
> itch
> every time a data-compression maven talks about
> "compression
> ratios," because they make the same error. It's a
> fascination
> with big, impressive-sounding numbers, that's all. Bah!)
>
> Now, where did I put that supply of anti-psychotic
> pills?
>
> --
> Eric Sosman
> esosman(a)ieee-dot-org.invalid

Yah got me! It is really like this, machine C takes X
minutes. Machine A takes 8X minutes.

If I would have said 800% of the time, instead of 800%
faster, I would have had it right.