Slashdot Mirror
Slashback: Grids, Netscape, AMD
And Campbell's puts glass marbles in their soup pictures. Roland Piquepaille writes "We saw several grid computing announcements in the last couple of days.Of course, Gateway stole the show. In 'Gateway makes store PCs work overtime,' you can read that 'Gateway's network of 8,000 PCs can deliver 14 teraflops.' This is plain wrong. You all know that this number of 14 teraflops is meaningless. It's just the addition of the peak speed of all the PCs -- never reached anyway on individual PCs. You need specialized software to work efficiently with a grid. And two companies are releasing new products to power grids. Avaki rolled out what it believes is the first Java-based data grid software for enterprise-class IT environments. Kontiki, for its part, on Monday released a grid server that brings its content delivery system into the server realm, whereas previously it was only available for PCs. Check this column for a summary, or this article for more details."
Why aren't those things called 'stick-up' ads, anyhow? Internet Ninja writes "Netscape today released version 7.01 of Netscape based on Mozilla 1.0.2. Back in is popup blocking which they got a lashing for in 7.0 as well as tabs as home pages just like Mozilla. Release notes here and there's a couple articles on Netscape devedge which may be of interest to developers."
And they will continue to have produced my Athlon, too. schnoz writes "And you thought AMD was quitting the PC chip market? Then check out this article on Business Week. Not only are they releasing new chips and plan to continue to do so, they're also still very active research wise, working on new transistor making techniques such as the double gate design as well as metal-rather-than-silicon design. Keep going at it AMD!!"
i confirmed it on my 3.6 ghtz athlon system (dual 1.8 MPs)...
MARIJUANA, SHROOMS, X: ONLINE?! - E
"And you thought AMD was quittingthe PC chip market?"
I didn't think they were quitting the PC Chip market. I actually read the article.
I bet the next version of IE will have a popup blocking feature.
Sex - Find It
Like, there's one where the mom is home alone with her little kid, and everyone knows that women are only motivated to actually cook when there's a hunky man around. So she's about to make the kid a FROZEN PIZZA when the kid holds up a drawing from school and says "Look, Mommy, I drawded you a pitcher!" and Mom oohs over it and to reward the kid she puts away the frozen pizza and instead the kid gets A BOWL OF CAMPBELL'S SOLID PINK "TOMATO" SOUP for lunch. This is love in the same sense that this is nutrition. Lumpless flesh-colored soup. Remember how Campbell's tried to use the slogan "Soup Is Good Food" for a few months until enough dieticians complained that that was an outright lie in the case of Campbell's watery slime? Remember how they got busted for always showing pictures of soup with the few measly pathetic little veggie bits standing on the surface of the soup because the bowls were always filled with GLASS MARBLES to hold up the little fragments of orange-gray carrots and caved-in peas?
Physicists are more than thinking about the Grid, I should know as they're funding my PhD in Data Grid Computing 8*).
The main reason for this is the Large Hadron Collider, which is due to go into production at CERN in about 2007. For the younger members of the audience, CERN was where Tim Berners-Lee developed the World Wide Web in the early 1990's
When it goes online it has 4 major experiments, each of which stores data at 100-400MB/sec, and I stress stores data at 100+ MB/sec, the first level is processing 40Terabytes a second. This equals a few petabytes a year (1PB = 1000TB = 1000000GB) which then has to be shipped to sites around Europe and the US.
All this is going to have data, processing and network requirements which make most techies gasp, i.e. Google only has a 20TB database, current physics ones are at 650TB+. At this level 14TFlops is kinda a cute little toy.
And yes, most of it's open source and based on the Globus Toolkit.
i sure hope not. i don't want the average joe to be blocking pop-ups. once pop-up blocking becomes mainstream then the advertisers are going to switch to a format that is harder to deal with. i like using mozilla and blocking pop-ups, but if the advertisers change their format to a harder to block type, then i'll be seeing ads again.
working on new transistor making techniques such as the double gate design as well as metal-rather-than-silicon design.
This reminds me of one of my favorite IBM stories told to me by an ex-IBMer professor a few years back.
It would appear that some time in the 70s (it's been a few years since I heard this story), IBM was having problems with boules* falling over and breaking, costing a great deal of money. IBM being what it was, put out a solicitation for employee suggestions on how to remedy the problem.
One technician was very disappointed to hear that the boules were made of silicon and suggested using a stronger material. It was his wager that a stainless steel boule would be much more resistant to breaking. So, he suggested replacing all the silicon boules with stainless steel.
True story.
* Boules are very tall cylinders of monocrystalline silicon. They are sliced up into fairly thin, circular wafers. These wafers are then processed through the steps that make chips and lastly diced into the silicon chips we commonly see put on plastic or ceramic packages.
Rather than having window.open() return a null handle, have it return a real handle, but simply don't create the window. Better yet, have it optionally load the contents of the window, so the remote site never even knows that the window simply was never popped up.
Agreed. The physicists are putting massive resources into grid computing... trying to get all the scientific equipment onto a common paradigm of network resource access. I should also know, as I was co-opted into testing grid resources and grid algorithms when I was working for the University.
I think that there are a few more reasons than just the Hadron Collider, however.
The astrophysicists have got their Hubble Telescope and the radio telescopes which the SETI@Home project gets it's data from. The nuclear medical technicians have their magnetic resonance imagers (nMRI) and their picture archiving and communication systems (PACS). The geologists have got their seismographs. And the geneticists have got their DNA databases.
Surprisingly, a lot of scientific equipment is actually able to generate between 100MB to 1GB of data per second. Not just a collider or accelerator, although they are certainly known for generating alot of information.
Information is cheap and free, if you understand how to generate digital content. MRI scanners, for instance, are able to generate that much information, and are nearly always underclocked because physicians generally aren't looking at the atomic or molecular level.
Agreed on the Google point. It goes to show that high end computing is still order's of magnitude faster than home appliances (PCs). I was impressed at college with the virtual reality workstations we used to navigate the grid network (Internet2 connection, via the CERN group, Argonne National Laboratories, Enrico Fermi Institute, et al. I happend to have studied under one of the Globus Toolkit authors, working out of Argonne, for a very short while.).
Anyhow, a moderate scientific/medical workstation nowdays has perhaps 4 to 32 GB of RAM. We would use that RAM to generate immersive 3D rendering of nucleic acids, genomes, proteins, biotech designs, astrometic simulations, and so forth. Now, considering a stereoscopic projection monitor, you've got anywhere between 2 and 16 GB of data streaming to you, per second, per eye, via the projection monitor. Stereoscopic photorealistic virtual environments, grid overlays, you name it. It can definately be information overload at times.
The interesting thing, I found, was that at 2GB of information, per second, per eye, was the threshhold before I really and truly began to get mentally 'tricked' into being totally immersed, visually. That is, 20/20 vision, photorealistic, full spectrum color, stereoscopic, requires about 4 GB of memory to acurately and artificially calculate and project a pixel for each rod/cone in the human retina. A little bit of neurobiology for you, I suppose. Yep, them darn Turring machines are pretty neat, when they're hooked up to a grid network.
I went to a presentation yesterday by Platform (the guys that make LSF) who talked about grid computing. Each person that spoke gave a different definition of what 'grid computing' is: It's clusters of clusters, it's clusters plus processing on individual machines, etc.
The upside is that such processing using PCs is already taking place, in the form of distributed.net, folding@home and seti@home among many others. If gateway wants to use its spare cycles to create a supercomputer capable of many teraflops, then go for it.
On the other hand, apps that are well suited to such distributed computing are those that require little I/O and more number crunching. That is, you don't want to use BLAST (comparing gene sequences) as the data sets are on the order of GB. But simple number crunching, like the examples already given, do not require sending much data to the clients for processing.
BTW, LSF has software to do the same thing with desktop boxes.
As far as new ad formats, right on devedge page linked from the artice, you are seeing the future of web advertising.
Instead of popup windows (which are *SO* 90's), we will have popup div layers, positioned to cover the page. Look at Netscape's own popup detection example. They show you how to detect a popup blocker, and open up a fixed position DIV to give visitor a "warning". How long do you think it will take an ad network programmer to figure out that instead of the warning, this DIV can actually be used to show the ad itself?
Better yet, if the window failed to open, you can open the div with an IFRAME in it that points to the same URL. And no popups. :)
Welcome to the future. Doesn't it look a lot like the past?
Are you on drug(s)?!! Why not?
you are right; game consoles do use RDRAM. But in the end, RDRAM is not killed because it's bad technology, but because othere stuff.
first on the tech. (REALLY quick brief)
1) RDRAM has a faster interface (duh)
2) and it has a much more narrow bus
3) but to make chips drive at such a high frequency ON THE CIRCUIT BOARD, the bus interface for RDRAM is totally wacky
explanation: RDRAM is serially connected, *kinda* like... SCSI, or COAX ethernet back in the days. and it's heavily terminated. and because the signal goes so damn fast (remember, circuit board made of FR4 here - not cache->CPU interconnects), the routing of the signal traces, while sparse (something they tout - and it's true, DDR has like 2-4 time the wire density as RDRAM on the board), has very small tolerance for length difference. furthermore because the high speed, the chips must have a very strict output impedance (which is why mem-makers got shitty yields at the beginning and the RDRAM price were so high).
performance wise / practically speaking, since it's the signal routing / RIMM detection and delay adjustment (remember no trace length differences etc) that's difficult and causes trouble - in game consoles where you will never add memory, RDRAM is actually better (easier to work with / better performance - better perf because you don't incur additional delays in the trace by adding more modules, everything is fixed). Same time on PCs, when you do it right, RDRAM still offers better bandwidth than DDR; DDR-2 i am not so sure, but that won't be in massive production for a while so don't wait for it yet. depending on architecture (P4 is, have to say, on the side of "optimized for RDRAM"), you would get better performance out of RDRAM for a little while longer.
now the non-tech side:
RAMBUS charges royalty. 2% i think? now - memory business is not high-margin business (or else there won't be only like 4-5 memory makers left!), so when 2% is actually like 40% from the margin - if you can do away with RAMBUS (even at a performance hit), it would enable you to survive, or make more money - depending on the company.
so... the moral of the story? RDRAM is not bad technology (i.e. has its uses - like in consoles), but it's not GREAT technology, and certainly not good enough to warrent the margin cut and the headaches in engineering (output impedence - and these days they are going to 32/64 bit so the sparse signal lines is less and less of a advertisable benefit). But I expect that it will maintain it's little niche and won't just die off suddenly one day. i mean, heck - even if they only supplied for the game consoles, (especially with the large chunck of change intel gave to RAMBUS) they can survive for quite a while. RAMBUS as a company I think will eventually fail if they continue this path of IP-only, though - for other reasons. but this is getting long already.
My life in the land of the rising sun.