Lawrence Glickman wrote:
On 04 Dec 2004 19:00:43 GMT, Ian Stirling
wrote:


In rec.crafts.metalworking Lawrence Glickman wrote:

On 04 Dec 2004 17:10:21 GMT, Ian Stirling
wrote:


I can't imagine running anything my 2.5 giger can't handle. It gets
the job done.

A 2.5Ghz pentium may only be a couple of times faster than a P100, for
some tasks.

If it requires random access to large (greater than the on-chip cache)
amounts of memory, random access speed of chips hasn't really changed
in the past decade.

Some 'supercomputer' type computers took extreme measures to get round this.

OK, I put in 512MB of RAM and this thing is working as advertised.
Less than 512 is not a good idea, because I can see from my stats that
I only have 170MB of unused physical memory at the moment.

Once you get enough RAM so you don't have to do HD read/writes, you're
on your way to speed. But M$ has shafted everybody, because M$ loves

Not for all tasks.
For a few scientific computing tasks (nuclear simulations are a big one),
the big bottleneck is how long it takes you to read a dozen bytes from a
'random' location in memory.
All the information is in memory - it's just that the memory isn't fast
enough.
The increase in random access speed has not nearly matched the increase
in streaming speed.

IIRC, a 20 year old 30 pin 1Mb SIMM would typically take 150ns (billionths
of a second) for the first byte, then 100ns for the next one.

A modern 1Gb memory DIMM might read out the second (and subsequent) bytes
a hundred times faster than the 1Mb SIMM.
But the initial access to any location in that DIMM is still only around
at best 3-4 times faster.

In some tasks, this can be the limiting factor for calculation.


No calculation my computer is ever going to need to make.
We're talking apples and oranges here. I'm talking about getting a
motorcycle up to 200 mph, you're talking about taking a truck up to
200 mph. Yes, they are going to require different engines.

For my purposes ( motorcycle ), the load my CPU has to deal with,
things appear normal in human time. I am not simulating nuclear
detonations in virtual reality. Any nanosecond speed differences are
not perceptible to this human unit.

I just performed 170! ( factorial of 170 ). That's the limit on my
*engine*

I got an answer of 7.2574E+306 before I could even take my finger off
the enter key. Is that not fast enough for a *consumer computer*
???????

Lg

The method I employed was to set up an array of integers of the F size.
e.g. Not so easy to guess when the numbers get large, but 1000! is under 2000 digits.

Then take the first two numbers and multiply, place the results into the array.
Multiply that by the next number - and when done, make sure each array element is a
single digit. If not - bump it up.... and re-test...

This then takes massive numbers and puts them into very simple baby talk numbers.
Any system can handle one digit vs. another. (unless it were a 4 bit o.s. :-) )

Martin

--
Martin Eastburn, Barbara Eastburn
@ home at Lion's Lair with our computer
NRA LOH, NRA Life
NRA Second Amendment Task Force Charter Founder