"Does research still need supercomputers, though?"
Yes, lots of good, interesting research still going on.
If you think clusters or Hadoop or map reduce or EC2 or cloud computing is going to solve the problems that supercomuter tackle you will be waiting around for a very long time.
"A supercomputer is a device for turning compute-bound problems into I/O-bound problems."Some problems are compute bound, some are memory bound, some are I/O bound. Supercomputers attempt to addresses this for the largest of these types of problems. Distributed storage or distributed process like Hadoop does not solve this except for the most trivial of supercomputer-class problem. There is still a need for supercomputers.
I want IPv4 to run out. The sooner the better.
When Y2K was about to come around, all the businesses who had old code some of it from the '60s, started hiring programmers like crazy. They needed to convert all the dates from two digit year to 4 digits. A massive effort but still only a very small amount of the total codebase that was out there needed to be modified.
Fast forward to 2010, 4-byte IPv4 address running out. A new protocol exists but much of the old software and networks cannot use them. The only solution is to hire a massive number of programmers and rewrite the software..
Think of this, every piece of software on every computer that accesses the internet, has to be rewritten. How big is that codebase? A lot larger than Y2K. I can see this pulling in programmer after programmer like some huge vortex, in a race to be done before last address is given out..
You see why I welcome the new of IPv4. The end of the recession in the tech industry and plethora of new job.
Developing good interfaces and good APIs is harder that you think. This maybe isn't Google finest code but it is not amateur hour either. They may need to bring in some "senior-Google-talent" but for first crack this is not bad.
Just wait till you get to control systems. Even better digital control systems. It's been 20 years for me. I can't even remember the name of the domain. Like Laplace but with discreet time steps.
It's called the Z-transform. I haven't used it in 20 years but I still remember it from college.
My general thoughts on the matter is that we never know what we will need in the future but it is good to start from a solid base. I would never have thought I would need diff eqs. but once a year or so I do. Glad I had that solid base.
I see people getting bogged down in the details of which software architecture/model to use all the time (never mind sort algorithms!), so much so that they lose sight of their objectives. What often happens is that someone (usually me) then does a quick end-run around them in and we eventually move on.
I have seen this quick end-run before. But what happens when your page hits doubles, and suddenly your script fails to scale. No amount of tweaking will fix a bad architecture. Then you call in someone like me to build you a real system. One that is scalable, reliable, secure and fast. First to market only works if you can sustain your advantage.
Is there some speculation in my orginal post. Sure. But remember, this was era when AMD market share was rising very rapidly, >+1% per month. Would they have run out of manufacturing capacity at some point. Possibly. Could they have build more. Sure, if they had the money. But that is exacty the point. Intel made sure they would never get the market share to get the money needed to compete. Never.
Intel, at the time, had the market share, the fabs and the cash but what they didn't have is a superior product and wouldn't have more several years. If you are Intel what do your do? By any means necessary, your make sure your competitor does not get enough market share or money to threaten your monolopy. If you have the break a few laws in the process, so be it. Limit how much of your competitors chip the computer manufacturers will buy. Illegal but sure. Sell chips below cost. Why not.
Now they are being called to task for their past actions. Not by just the FTC but by Japan, South Korea, the EU. They just settled a lawsuit from AMD for $1.25 billion.
I am not saying that AMD is blameless for their current situation. They could have invested more heavily in fab technology. The purchase of ATI was possibly ill advised. They jury is still out on that one. They slipped up with the release of the Barcelona chip. All I am saying is that given a level playing field, things could have turned out much differently.
There is no conspiracy: This is business. Business is inherently anti-competitive. If I'm competing with you, I want you out of the game, and just like in a video game, I will use combo attacks and drop-kick you right as you get up (repeatedly) to keep you from recovering until you throw the controller at me. That's just how the game is played. (See slashdot, we can avoid car analogies!)
Let's make the car analogy... In Indy car racing, you are not allowed to smash into your opponent over and over again until his car is a smoking pile of metal and then run him over as he leaves the flaming wreckage. This is against the rules.
There are rules in business just as in car racing. Intel broke them. Now they have to face the music.
Back when AMD's microprocessors were the state of the art (Athlon), they should have had 50% or more of the chip market. Intel only was able to preserve its market share through illegal means. Eventually, through the billions in extra profit they made, they were able to pull ahead in this technology race.
AMD was deprived of billions is profit which they could have used for more R&D to make their chips more competitive today. I don't know how you restore a market where one player has been cheating illegally for a decade and now has a monolopy, but Good Luck FTC.
Also, economic value of something is not measure by the number of 0s in your paycheque, but by the impact it has insociety, otherwise, the MBAs you scorn have a higher economic value than you do.
The MBAs may have higher economic value than me, but I'll take the extra zero on my paycheck, thank you.
Since I'm not an American I don't know how a drunk stop works, but here in Denmark, you get to blow on a mobile device, if it shows up as drunk you are taken to the hospital for a blood sample and only that blood sample will be used against you.
Are only the mechanical readings being used in the US?
Yes, the mechanical readings from the mobile device is enough to obtain a conviction in the US.
The dirty little secret of the industry has been that Intel has been guilty of unfair business practices for a long time. Basically, they say to their customers, if you cut out AMD we will give you cut rate prices. If you don't we will only give you a limited supply of chips and your competitors will kill you on price and volume. They are like the mafia in business suits.
The European commission made a estimate of the damage Intel did to the market and it came to $60 billion. I would like to see that much given to AMD but I am not holding my breath.
I met Neil Gershenfeld at the Supercomputing Conference in 2007. He has set up these mini-fabs at MIT, Africa, Scandinavia and elsewhere. I remember reading about someone else setting up something similiar in Silicon Valley. Each time, they were a huge success. It gives people a chance to make a one-off prototype of a idea they have. Before this was a terribly expensive proposition. Once the initial capital costs are paid, these shops run fairly inexpensively. This is such a great way to unleash the creativity of so many inventors that normally would not be able to afford it.
The legal issues in this case have been settled long ago. Ford holds the trademark on the image and likeness of its cars. The photographer hold the copyright on the pictures he took. For Ford to uphold its trademark, it has to contest all unlicensed use of its intellectual property.
All that being said there is an easy way to resolve this. I work for a company that sells aftermarket car parts. On our website, we wanted to use the Ford blue oval trademark image to guide people who were looking for Ford car parts. We asked Ford for a royalty-free license to use there trademark and were granted permission. We included mockups of how we were going to use it so their lawyers didn't freak. Everythings was businesslike and professional. Businesses do this all the time.
The idea that only the first one to solve the problem is allowed to use the solution is just nonsense.
You are wrong on this. The first one that comes up with the non-obvious solution gets to use it, exclusively. Everyone can use the obvious solution. That is the patent system.
Agreed. The only worthwhile outcome would have been a punitive judgement against Circuit City and the city of Brooklyn Ohio. He made the judgement that pursuing this end would be too costly for his family. I can't second-guess that judgement, but I can say that this appears to be a loss for everyone.
It was not a loss for everyone, some lawyer got paid $7500 for handling a relatively simple case. I bet he is laughing all the way to the bank.
Finer grained multi-threading just leads to deadlocks and is really hard to debug.
It is statements like this that I just burns me up inside. Let me put the proper qualification on the above statement.
Finer grained multi-threading just leads to deadlocks,if you suck at programming or if you don't know what you are doing and is really hard to debug if you are some clueless hack that cannot keep track of more than one thread in their feeble mind.
"Imagine you're reformatting a hard drive so you can do a clean install but then realize that you have also reformatted the back up hard drive. No problem. You reach for your back up tapes only to find out that the information on the tapes is unreadable..."
Ok, so you go to the primary hard drive and make another backup.
Another question, doesn't anyone test their backup systems?
Slashdot Mirror
I went to school with Ed Felton. He is not an ivory tower intellectual type, he is just extemely bright and extremely curious.
Oh yes, by the way, you can have a beer with him. I have done so many times.
"Does research still need supercomputers, though?"
Yes, lots of good, interesting research still going on.
If you think clusters or Hadoop or map reduce or EC2 or cloud computing is going to solve the problems that supercomuter tackle you will be waiting around for a very long time.
"A supercomputer is a device for turning compute-bound problems into I/O-bound problems."Some problems are compute bound, some are memory bound, some are I/O bound. Supercomputers attempt to addresses this for the largest of these types of problems. Distributed storage or distributed process like Hadoop does not solve this except for the most trivial of supercomputer-class problem. There is still a need for supercomputers.
"...company that doesn't believe in design."
It is not that Microsoft doesn't believe in design, it is that they suck at it. The best case in point is Windows security.
I want IPv4 to run out. The sooner the better. When Y2K was about to come around, all the businesses who had old code some of it from the '60s, started hiring programmers like crazy. They needed to convert all the dates from two digit year to 4 digits. A massive effort but still only a very small amount of the total codebase that was out there needed to be modified.
Fast forward to 2010, 4-byte IPv4 address running out. A new protocol exists but much of the old software and networks cannot use them. The only solution is to hire a massive number of programmers and rewrite the software..
Think of this, every piece of software on every computer that accesses the internet, has to be rewritten. How big is that codebase? A lot larger than Y2K. I can see this pulling in programmer after programmer like some huge vortex, in a race to be done before last address is given out..
You see why I welcome the new of IPv4. The end of the recession in the tech industry and plethora of new job.
If no one codes in assembly these days, who writes the compilers?
This is New Jersey, right?
:-)
Shouldn't the truck be driving around the whole state.
Developing good interfaces and good APIs is harder that you think. This maybe isn't Google finest code but it is not amateur hour either. They may need to bring in some "senior-Google-talent" but for first crack this is not bad.
Lay off these guys unless you can go it better.
Just wait till you get to control systems. Even better digital control systems. It's been 20 years for me. I can't even remember the name of the domain. Like Laplace but with discreet time steps.
It's called the Z-transform. I haven't used it in 20 years but I still remember it from college.
My general thoughts on the matter is that we never know what we will need in the future but it is good to start from a solid base. I would never have thought I would need diff eqs. but once a year or so I do. Glad I had that solid base.
I see people getting bogged down in the details of which software architecture/model to use all the time (never mind sort algorithms!), so much so that they lose sight of their objectives. What often happens is that someone (usually me) then does a quick end-run around them in and we eventually move on.
I have seen this quick end-run before. But what happens when your page hits doubles, and suddenly your script fails to scale. No amount of tweaking will fix a bad architecture. Then you call in someone like me to build you a real system. One that is scalable, reliable, secure and fast. First to market only works if you can sustain your advantage.
I know nothing about the Mac OS X kernel, but I don't understand why such a transition couldn't be done in pieces -- the code is modular, isn't it?
:-)
I do not think you know the meaning of the word monolithic.
I'm sorry Mexico, your copyright expired in 1492.
Is there some speculation in my orginal post. Sure. But remember, this was era when AMD market share was rising very rapidly, >+1% per month. Would they have run out of manufacturing capacity at some point. Possibly. Could they have build more. Sure, if they had the money. But that is exacty the point. Intel made sure they would never get the market share to get the money needed to compete. Never.
Intel, at the time, had the market share, the fabs and the cash but what they didn't have is a superior product and wouldn't have more several years. If you are Intel what do your do? By any means necessary, your make sure your competitor does not get enough market share or money to threaten your monolopy. If you have the break a few laws in the process, so be it. Limit how much of your competitors chip the computer manufacturers will buy. Illegal but sure. Sell chips below cost. Why not.
Now they are being called to task for their past actions. Not by just the FTC but by Japan, South Korea, the EU. They just settled a lawsuit from AMD for $1.25 billion.
I am not saying that AMD is blameless for their current situation. They could have invested more heavily in fab technology. The purchase of ATI was possibly ill advised. They jury is still out on that one. They slipped up with the release of the Barcelona chip. All I am saying is that given a level playing field, things could have turned out much differently.
There is no conspiracy: This is business. Business is inherently anti-competitive. If I'm competing with you, I want you out of the game, and just like in a video game, I will use combo attacks and drop-kick you right as you get up (repeatedly) to keep you from recovering until you throw the controller at me. That's just how the game is played. (See slashdot, we can avoid car analogies!)
Let's make the car analogy... In Indy car racing, you are not allowed to smash into your opponent over and over again until his car is a smoking pile of metal and then run him over as he leaves the flaming wreckage. This is against the rules.
There are rules in business just as in car racing. Intel broke them. Now they have to face the music.
Back when AMD's microprocessors were the state of the art (Athlon), they should have had 50% or more of the chip market. Intel only was able to preserve its market share through illegal means. Eventually, through the billions in extra profit they made, they were able to pull ahead in this technology race. AMD was deprived of billions is profit which they could have used for more R&D to make their chips more competitive today. I don't know how you restore a market where one player has been cheating illegally for a decade and now has a monolopy, but Good Luck FTC.
Also, economic value of something is not measure by the number of 0s in your paycheque, but by the impact it has insociety, otherwise, the MBAs you scorn have a higher economic value than you do.
The MBAs may have higher economic value than me, but I'll take the extra zero on my paycheck, thank you.
Since I'm not an American I don't know how a drunk stop works, but here in Denmark, you get to blow on a mobile device, if it shows up as drunk you are taken to the hospital for a blood sample and only that blood sample will be used against you. Are only the mechanical readings being used in the US? Yes, the mechanical readings from the mobile device is enough to obtain a conviction in the US.
250 Gb/month should be enough for everyone....
The dirty little secret of the industry has been that Intel has been guilty of unfair business practices for a long time. Basically, they say to their customers, if you cut out AMD we will give you cut rate prices. If you don't we will only give you a limited supply of chips and your competitors will kill you on price and volume. They are like the mafia in business suits.
The European commission made a estimate of the damage Intel did to the market and it came to $60 billion. I would like to see that much given to AMD but I am not holding my breath.
I met Neil Gershenfeld at the Supercomputing Conference in 2007. He has set up these mini-fabs at MIT, Africa, Scandinavia and elsewhere. I remember reading about someone else setting up something similiar in Silicon Valley. Each time, they were a huge success. It gives people a chance to make a one-off prototype of a idea they have. Before this was a terribly expensive proposition. Once the initial capital costs are paid, these shops run fairly inexpensively. This is such a great way to unleash the creativity of so many inventors that normally would not be able to afford it.
byteherder
The legal issues in this case have been settled long ago. Ford holds the trademark on the image and likeness of its cars. The photographer hold the copyright on the pictures he took. For Ford to uphold its trademark, it has to contest all unlicensed use of its intellectual property.
All that being said there is an easy way to resolve this. I work for a company that sells aftermarket car parts. On our website, we wanted to use the Ford blue oval trademark image to guide people who were looking for Ford car parts. We asked Ford for a royalty-free license to use there trademark and were granted permission. We included mockups of how we were going to use it so their lawyers didn't freak. Everythings was businesslike and professional. Businesses do this all the time.
The idea that only the first one to solve the problem is allowed to use the solution is just nonsense.
You are wrong on this. The first one that comes up with the non-obvious solution gets to use it, exclusively. Everyone can use the obvious solution. That is the patent system.
Agreed. The only worthwhile outcome would have been a punitive judgement against Circuit City and the city of Brooklyn Ohio. He made the judgement that pursuing this end would be too costly for his family. I can't second-guess that judgement, but I can say that this appears to be a loss for everyone.
It was not a loss for everyone, some lawyer got paid $7500 for handling a relatively simple case.
I bet he is laughing all the way to the bank.
Finer grained multi-threading just leads to deadlocks and is really hard to debug.
It is statements like this that I just burns me up inside. Let me put the proper qualification on the above statement.
Finer grained multi-threading just leads to deadlocks, if you suck at programming or if you don't know what you are doing and is really hard to debug if you are some clueless hack that cannot keep track of more than one thread in their feeble mind.
I will get off my soapbox now
byteherder
"Imagine you're reformatting a hard drive so you can do a clean install but then realize that you have also reformatted the back up hard drive. No problem. You reach for your back up tapes only to find out that the information on the tapes is unreadable..."
Ok, so you go to the primary hard drive and make another backup.
Another question, doesn't anyone test their backup systems?
From the headline, "claims to the ELF magic number."
This my sound like a dumb question but, "What is the ELF magic number?" and "Why is it important?"