Under water wireless networking is a much harder
problem than you might expect. Electro-magnetic
Waves don't travel very far in water, so you'd have to line the ocean with repeaters...
It might be possible if the diver had a bouy above
where he was diving. He would transmit to the
bouy (that he couldn't be too far from), and the
bouy would repeat the signal to a ground base.
It'd add a bit of latency, so quake while your
diving would still be out of the question:)
His answer to this question implies that it would not distribute well D-Net style. If a 100mbit connection isn't enough bandwidth, then There's no way that a D-Net style aproach would work.
Weather forecasting in general. (Score:5, Interesting) by Matt2000
Ok, a two parter:
As I understood it weather models are a fairly hard thing to paralleliz (how the hell do you spell that?) because of the interdependence of pieces of the model. This would seem to me to make a Beowulf cluster a tough choice as it's inter-CPU bandwidth is pretty low right? And that's why I thought most weather prediction places chose high end super-computers because of their custom and expensive inter-CPU I/O?
Greg:
Weather models are moderately hard to parallelize; in order to process the weather in a given location, you need to know about the weather to the north, south, east, and west. For large numbers of processors, this does require more bandwidth than fast ethernet provides, and that's why we used the Myrinet interconnect, which provides gigabit bandwidth, and which scales to thousands of nodes with high bisection bandwidth, unlike gigabit ethernet.
As far as disk I/O goes, yes, most clusters are fairly weak at disk I/O compared to traditional supercomputers from Cray. We are using the CentraVision filesystem from ADIC along with fibre channel RAID controllers and disks. This is more expensive than normal SCSI or IDE disks, but provides much, much greater bandwidth for our shared filesystem.
Slashdot Mirror
Under water wireless networking is a much harder problem than you might expect. Electro-magnetic Waves don't travel very far in water, so you'd have to line the ocean with repeaters...
It might be possible if the diver had a bouy above where he was diving. He would transmit to the bouy (that he couldn't be too far from), and the bouy would repeat the signal to a ground base.
It'd add a bit of latency, so quake while your diving would still be out of the questionis when slashdot equates your name to 'smart'. What an ego trip that must be :)
Look through the budget, and there's no entry for motherboards. That is unless you can get a AMD K62 450 + mobo for 64 dollars.
His answer to this question implies that it would not distribute well D-Net style. If a 100mbit connection isn't enough bandwidth, then There's no way that a D-Net style aproach would work.
Weather forecasting in general.
(Score:5, Interesting)
by Matt2000
Ok, a two parter:
As I understood it weather models are a fairly hard thing to paralleliz (how the hell
do you spell that?) because of the interdependence of pieces of the model. This
would seem to me to make a Beowulf cluster a tough choice as it's inter-CPU
bandwidth is pretty low right? And that's why I thought most weather prediction
places chose high end super-computers because of their custom and expensive
inter-CPU I/O?
Greg:
Weather models are moderately hard to parallelize; in order to process the weather in
a given location, you need to know about the weather to the north, south, east, and
west. For large numbers of processors, this does require more bandwidth than fast
ethernet provides, and that's why we used the Myrinet interconnect, which provides
gigabit bandwidth, and which scales to thousands of nodes with high bisection
bandwidth, unlike gigabit ethernet.
As far as disk I/O goes, yes, most clusters are fairly weak at disk I/O compared to
traditional supercomputers from Cray. We are using the CentraVision filesystem from
ADIC along with fibre channel RAID controllers and disks. This is more expensive
than normal SCSI or IDE disks, but provides much, much greater bandwidth for our
shared filesystem.
If reduced power and higher speed come out of this new process, when will transmeta join the boat? IBM was manufacturing their processor, right?
If linus could sue LinuxOne, Theres no way they'd have enough money to have there little bogus IPO
I usually do believe everything on slashdot **cough** but is there any proof of this?