I aways wondered if this could be done. I consided
hooking such a device up to the overhead air blowers they
have on commercial airplanes to charge cell phones and laptops. There is probably a FAA law against this however.
Show of hands. How Many people knew about CentOS before this story?
How many do now? If this gets picked up by other
news outlets, CentOS will probably get rather well known.
Having a pile of servers does not mean you have a grid. To use the electrical analogy, there are different electrical grids that are not compatible i.e. European and US electrical grids. If you plug into the wrong electrical gird your device does not work. The same is true for computer grids. they are designed to service specific applications. Getting all the details right is hard -- that is what the Globus project is all about.
Now what IBM has been doing is not Grid. You basically rent a machine for a certain amount of time. You actually start with a small test cluster, then when it works, your "image" is then transfered to the real thing.
Grids are designed so that everything you need for your code is on the grid you are using (including data). On-demand is renting cycles.
...the world would be very unpredictable: different people might see very different versions of it. Life itself would then be hard to conduct, because we would not be able to obtain reliable information about our surroundings... it would typically conflict with what others were experiencing.
Curious, this is how I experienced the US election last November. I'll blame it on TV.
It will be difficult to know when it is fixed because there will probably
be a run on paypal
accounts. They may keep it slow for this reason. I am sure anyone with a
few hundred dollars in paypal will move their money out as fast
as they can. Kind of like a "slashdoting a bank"
If some one said this to me, I would take the "Groklaw Approach". I would
ask them first, what are the specific patents and second, how can he be
sure that Linux violates all these patents. It would seem to me
that to do a fair assessment of 283 patents would take a fair amount
of time. So let's see the details.
My guess is that his answers would consist of words like "I", "don't",
and "know".
This is similar to what clusters try and do. It is important to maintain the same OS state on all nodes.
Take a look at Rocks Clusters. Rocks will push the same OS image out to the nodes of the cluster. There is no reason
the cluster nodes could not be workstations on a desk.
My response was a rant, an opinionated response. I'll argue verifiable
facts to support my case if need be. But crafty marketing things like this
interview are FUD. I did not use a phony interview to get my point across.
For example the question which used the word some:
Is it true that some applications don't run well on cluster systems?
Why not?
Gets turned into many in the response:
Terry: Yes, that's true for many HPC applications.
Clever. If the guy owned it as a vendor biased opinion, then I
would give it a bit more respect. But he can't because the marketing
department probably orchestrated this FUD campaign.
Exactly. Cray would love to sell you a system to
do CFD, but guess what, a cluster works just as well
is available now and costs less.
Read carefully. I did not say it was vaporware. I saw a real system.
What I said was, trying to keep up with the
commodity curve is battle that has been lost by
many an HPC vendor. The key is time to market. By the time you get your latest and greatest to market,
the commodity market has passed you by.
this
will never happen. Intelligence is a collective thing not an individual
thing. I have often believe there is a "meta-intelligence" that teaches
us how to think. This meta-intelligence is passed along generation to
generation by language, actions, emotions etc. that we take for granted.
Until we can build machines that learn in this environment, we will always
be "smarter". Even immersing learning machines in the environment may not
work as expected. The human brain is the most highly evolved device for
meta-learning and on average it takes 11-14 years to be smart enough to
reproduce. (I have often thought the onset of puberty is the brain
deciding it has "meta-learned" enough to *figure out* how to care for
offspring).
We can build environement specific intelligence -- like
chess programs. However, a chess program does not know to make an omelet.
So the Sun's "value proposition" will be selling commodity hardware (Opteron) running a GPL'ed OS (Suse). Is this not the way of VA Linux became a software company. Then there is the other suff, SPARC and Solaris are direct
competitors to Linux and commodity hardware. (except at the high end). I have never seen it work when a company competed with itself. Besides they are probably going to buy Cray first.
There never really was a supercomputer market. There was a cold
war, that
subsidized the supercomputer market.
Then there is the cost. Companies stopped making SC because they were too
expensive. If the guy from Ford wants to pay 1 billion for a supercomputer
I am sure someone will build him one. The cost build a FAB is over 4
billion. Why do you think HP teamed with Intel. Why do you think there are
so few processor families? You have to make a living in the commodity
market where you can sell things in the millions because supercomputers
even in their heyday were sold in the hundreds.
Then there is the problem that many problems are solvable on clusters.
So those specialized problems can not depend on other parts of the HPC
market to help subsidized their corner of the market. i.e. clusters make the really hard problems more expensive.
It is question of how much you want to pay to solve your problem? Simple
economics actually. If the numbers don't work, the problem doesn't get
solved. If the Gov. wants to solve some problems (and during the cold war
they did) then they can step in and subsidize the market.
And don't cry about Japan and the Top500. When the top500 has price
column then it will start to be meaningful.
do these gasbags make the assumption that open source software takes away
US intellectual property. Last time I looked, people from all over the
world are contributing their IP to FOSS projects.
So explain to me a again how a software project that started in Finland and
has people from all over the world contributing, is a theft of American
IP?
You know, all this talk about WinFS and probably twenty other "new"
solutions to non-problems, makes me wonder. People are still using Windows
98, it must work for them at some level. Not that I am advocating, Windows
98, but the constant software churn does start to have a real diminishing
return and in some cases a negative return. People will look for alternatives.
Shuffling the technology deck in the middle of
the game to ward of competitors does not seem to work in some cases --
just ask Intel.
So, that in a nutshell is the Microsoft method. Understand the market, and the customers, and then go pedal to the metal, with release after release focused on what the customers need, incorporating their feedback.
Not according to the courts around the world that found Microsoft guitly of illegall acts. Plus all those wonderfully internal memos that talk about how FUD is a great marketing tool.
I guess those (and other) activities do not fit in this guys nutshell.
All I can say to this guy, Sure thing
Skippy, that Microsoft Company, they sure are swell.
I attended the event. It is pretty big news. There was a lot of interesting
presentations and it is really an astounding direction for IBM. As one person from
IBM put it,
IBM has seen how well the Open Source/Community model has worked for
Linux. Now they believe that it will benefit the deployment of POWER
derived technology.
The details are a little sketchy at this point, but Wladawsky-Berger
basically said this is of the same magnitude as the decision to embrace
Linux.
I think I heard the word "community" in almost every other sentence. I
truly
believe IBM "gets it" and is moving forward in bold direction. The people
I talked to afterward were credible and excited.
There will be a longer story on
ClusterWorld tomorrow. (sign up for three free issues of the magazine as well)
I saw the small "Blue Gene" system. Very cool both performance wise
and thermally (32 CPUs in a table top box). I also saw the new Power blade
server. Nice.
I have said this before, if Google thought this would be a problem, they would just buy SCO and throw
them in the trash. I am sure SCO is wishing (maybe part of the plan) that
Google calls them and says "Hey how about stock
swap before we go public?" Guess who woud unload all their shares on day one of the IPO for a nice fat profit. Since plan A did not work (IBM buys SCO), plan B, let's poison someones IPO and see if
they will buy us, might work.
The are claiming rights to methods that they do not own. You can not
protect a method with a copyright (even if you did own the copyright) This
is like saying, I have a mystery novel to sell. If you decide to read any other
mystery novels, you need to pay me because I own the method of
describing a mystery in a novel. You see I might own a copyright to a story some else wrote.
I am not a lawyer
but I know that difference between between the two. I think it is designed
to scare the PHB's that pay attention to this stuff.
Slashdot Mirror
I aways wondered if this could be done. I consided hooking such a device up to the overhead air blowers they have on commercial airplanes to charge cell phones and laptops. There is probably a FAA law against this however.
Show of hands. How Many people knew about CentOS before this story? How many do now? If this gets picked up by other news outlets, CentOS will probably get rather well known.
Now what IBM has been doing is not Grid. You basically rent a machine for a certain amount of time. You actually start with a small test cluster, then when it works, your "image" is then transfered to the real thing.
Grids are designed so that everything you need for your code is on the grid you are using (including data). On-demand is renting cycles.
Now when they make "Old Yeller and the Black Hole" then I'll get excited.
Curious, this is how I experienced the US election last November. I'll blame it on TV.
Good point, but if you are not paying taxes in the first place and don't do what you agreed to do, then thier argumnet sounds a little hollow
It will be difficult to know when it is fixed because there will probably be a run on paypal accounts. They may keep it slow for this reason. I am sure anyone with a few hundred dollars in paypal will move their money out as fast as they can. Kind of like a "slashdoting a bank"
If some one said this to me, I would take the "Groklaw Approach". I would ask them first, what are the specific patents and second, how can he be sure that Linux violates all these patents. It would seem to me that to do a fair assessment of 283 patents would take a fair amount of time. So let's see the details.
My guess is that his answers would consist of words like "I", "don't", and "know".
This is similar to what clusters try and do. It is important to maintain the same OS state on all nodes. Take a look at Rocks Clusters. Rocks will push the same OS image out to the nodes of the cluster. There is no reason the cluster nodes could not be workstations on a desk.
Since when did "thorough(ly) contemplation" have anything to do with elections or politics in this country.
For example the question which used the word some:
Is it true that some applications don't run well on cluster systems? Why not?
Gets turned into many in the response:
Terry: Yes, that's true for many HPC applications.
Clever. If the guy owned it as a vendor biased opinion, then I would give it a bit more respect. But he can't because the marketing department probably orchestrated this FUD campaign.
Read carefully. I did not say it was vaporware. I saw a real system. What I said was, trying to keep up with the commodity curve is battle that has been lost by many an HPC vendor. The key is time to market. By the time you get your latest and greatest to market, the commodity market has passed you by.
I just finished writing a rant about this. Almost pure FUD
We can build environement specific intelligence -- like chess programs. However, a chess program does not know to make an omelet.
So the Sun's "value proposition" will be selling commodity hardware (Opteron) running a GPL'ed OS (Suse). Is this not the way of VA Linux became a software company. Then there is the other suff, SPARC and Solaris are direct competitors to Linux and commodity hardware. (except at the high end). I have never seen it work when a company competed with itself. Besides they are probably going to buy Cray first.
There never really was a supercomputer market. There was a cold war, that subsidized the supercomputer market.
Then there is the cost. Companies stopped making SC because they were too expensive. If the guy from Ford wants to pay 1 billion for a supercomputer I am sure someone will build him one. The cost build a FAB is over 4 billion. Why do you think HP teamed with Intel. Why do you think there are so few processor families? You have to make a living in the commodity market where you can sell things in the millions because supercomputers even in their heyday were sold in the hundreds.
Then there is the problem that many problems are solvable on clusters. So those specialized problems can not depend on other parts of the HPC market to help subsidized their corner of the market. i.e. clusters make the really hard problems more expensive.
It is question of how much you want to pay to solve your problem? Simple economics actually. If the numbers don't work, the problem doesn't get solved. If the Gov. wants to solve some problems (and during the cold war they did) then they can step in and subsidize the market.
And don't cry about Japan and the Top500. When the top500 has price column then it will start to be meaningful.
Better read this first there cowboy. It is not as easy as you think.
So explain to me a again how a software project that started in Finland and has people from all over the world contributing, is a theft of American IP?
Oh, sorry I forgot about the SCO thing.
Shuffling the technology deck in the middle of the game to ward of competitors does not seem to work in some cases -- just ask Intel.
So, that in a nutshell is the Microsoft method. Understand the market, and the customers, and then go pedal to the metal, with release after release focused on what the customers need, incorporating their feedback.
Not according to the courts around the world that found Microsoft guitly of illegall acts. Plus all those wonderfully internal memos that talk about how FUD is a great marketing tool. I guess those (and other) activities do not fit in this guys nutshell.
All I can say to this guy, Sure thing Skippy, that Microsoft Company, they sure are swell.
IBM has seen how well the Open Source/Community model has worked for Linux. Now they believe that it will benefit the deployment of POWER derived technology.
The details are a little sketchy at this point, but Wladawsky-Berger basically said this is of the same magnitude as the decision to embrace Linux.
I think I heard the word "community" in almost every other sentence. I truly believe IBM "gets it" and is moving forward in bold direction. The people I talked to afterward were credible and excited.
There will be a longer story on ClusterWorld tomorrow. (sign up for three free issues of the magazine as well)
I saw the small "Blue Gene" system. Very cool both performance wise and thermally (32 CPUs in a table top box). I also saw the new Power blade server. Nice.
There is now a magazine and a news website dedicated to HPC/Beowulf cluster computing. You may recognize the webpage format.
We are still running our free three month trial issue offer as well.
You may also find ClusterWorld web-site and magazine useful.
I have said this before, if Google thought this would be a problem, they would just buy SCO and throw them in the trash. I am sure SCO is wishing (maybe part of the plan) that Google calls them and says "Hey how about stock swap before we go public?" Guess who woud unload all their shares on day one of the IPO for a nice fat profit. Since plan A did not work (IBM buys SCO), plan B, let's poison someones IPO and see if they will buy us, might work.
I am not a lawyer but I know that difference between between the two. I think it is designed to scare the PHB's that pay attention to this stuff.