diep at xs4all.nl
Fri Jan 13 06:01:59 PST 2012
On Jan 12, 2012, at 6:35 PM, Ellis H. Wilson III wrote:
> On 01/12/2012 10:56 AM, Vincent Diepeveen wrote:
>> On Jan 12, 2012, at 2:58 PM, Ellis H. Wilson III wrote:
>>> I think this is likely the reason why many
>>> introductory engineering classes incorporate use of Lego Mindstorm
>>> robots rather than lunar rovers (or even overstock lunar rovers :D).
>> I didn't comment on other complete wrong examples, but i want to
>> one. Your example of a lego robot actually is disproving your
> It was a price comparison, and without diving into the nitty-gritty
> of how good or bad both the Arduino and the Mindstorms are in their
> respective areas, it was spot on. Jim wants to give each student a
> 10 node cluster on the cheap (i.e. 20 to 30 bucks per node = 300
> bucks), universities want to give each student (or teams of
> students sometimes) a robot (~280). Both provide an approachable
> level of difficulty and potential for education at a reasonable price.
> Feel free to continue to disagree for the sake of such. It was
> just an example.
It's not even spot on. You're lightyears away with your comparision.
You're comparing one of the best available robots that gets mass
with some freak thing where there is 100 alternatives which work way
alternatives are 500x faster, and if you want to also cheaper,
and above all achieve the original goal better of demonstrating SMP
as the freak hardware, thanks to real low clocked type of CPU,
has a neglectible latency to other cpu's.
Where the robot shows you how to work with robots, the educational
purpose as Jim wrote down,
you won't get very well with the embedded cpu's, as the equipment has
none of the typical problems you can encounter in
a normal SMP system let alone a cluster environment, meanwhile it
has total other problems,
which you will never encounter at CPU's.
Such as that embedded cpu's have severely limited caches and can
execute just 1 instruction at a time.
Embedded programming is total different from CPU programming and
latencies embedded, thanks to the slow processor speed,
are not even comparable with SMP programming between cores of 1 cpu.
Such multicore box definitely has a cost below $300.
On ebay i see nodes with 8 cores for $200.
And those are 500x faster.
Myself i'm looking at some socket 771 Xeon machines say with a L5420.
Though they eat a lot more power than intel claims,
it's still i guess a 170 watt a machine or so under full load.
Note we still skipped the algorithmic discussion, as from algorithmic
viewpoint, if i look to artificial intelligence, getting something to
at 70Mhz machines is gonna behave total different and needs total
different approach than todays hardware. It's not even in the same
More information about the Beowulf