I saw a usage of this tech a couple of years ago on a Motorola Star Tac Prototype. The reasen they wernt used was due to the low product yeald of the tech..
I am truly in agreement about the clams of this switch being rather bogus. What few people realize is that its the protocol that is responsible for 90%+ the latency of a packet through a switch, and not the switching it self. Until there is a commercial method to decoded packet headers in fiber with out converting to electrical signals and also a major change in the header complexity/format the latency of packets through a LAN, WAN, or what ever will not be reduced!
Well since everyone on this thread seams not to know a dam thing let me point you all in the direction of www.rapidio.org a new standard that replaces the entire layered bus architecture with in a system with a lightweight switch protocol. Oh and also look at the member roster you'll see all the big names there except AMD who have the Hyper Transport thing-a-ma-gig.
My company used a simulation package called bones, and like most high end software the only choice is a yearly licenseing agrement. IE RENT! Well dont u know it the company that made bones was bought by its competitor and bam no more licenses, thus no more bones!
The use of FPGAs to create Hyper/Super Computers is only applicable to highly specific application based machines. For the computer descried in the article to be a truly general-purpose super computer one would have to change the logic in the FPGAs rather frequently. It should be know that reloading logic into FPGAs to meet the current needs of a software app is a time consuming progress. Also compilers do not exist that can take a standard C program and convert it in to HDL (Hardware Design Language) that is loaded into FPGAs. The cool stuff that is being done is to merge FPGAs with processing cores (such as the SPARC ALU) into one chip thus giving you the speed of FPGA logic for a specific ask and the ALU core tailored to more general apps. Yet no mater what until a compiler comes out that can convert Software code into HDL, as I stated, in an efficient manner then it's just a toy.
I had the same choice in front of me several years ago, and opted for the Computer Engineering Track. The reasons being more than just to work with hardware, the truth is that most engineering programs will require you to learn alot about the various aspect of Electrical Engineering (which CE is apart of). This is a good thing for a wide and veried tachnical footing has alowed me to jump from project to project looking for what I really want to do. Example being I have done cell phone design, computer programing, 10 Giga Bit asic design, Turbo Codes, and now I am designing an asic chip set to run 4 G4+ boards in a clustering enviroment including modifying the LinuxPPC to run on these boards. What Im trying to say it's easy for a Computer Engineer to jump into fields suh as programing, and designing algorithims, but a Computer Scientist cant just jump into the Computer Enginnering Fileds.
Re:light stopped? Or destroyed and re-emitted...
on
Stop, Light.
·
· Score: 1
It seems to me that they aren't slowing
the light so much as absorbing it a few photons at a time as it passes
through the gas, with the resulting spin states in the gas atoms retaining
information about the photons. When they read it out with the second pulse
they aren't getting the original photons with the same properties. I think
this means that the coherence of an entangled state would be destroyed so
it couldn't be used for quantum computing.
There are many who believe this is just a symptom of a much greater problem due to deregulation of the power industry. Its been said that our power grid is inherently unstable today as it was before the US began to regulate it in the late 40's. I would like to know from the people in the power industry if they believe this.
First off, I dont have a spelling problem I CANT SPELL!
Secound, yes crays were super computers but since Compact bought the processor division of Cray when it fell apart. The processors now produced by the compact-cray division I call crays.
Third the carbon scoring was deep into the diamond surface and not just soot!
Fourth this is a very unique solution to multi processing that is not done by SGI (who used to own Cray), EMC, SUN. These super computers rely on switching protocals seperate from the processor bus to handel cache coherency. This method I descriped allows one to do a multy processing solution all on the same bus (beyoud 2 processors). Why is this allowed in the described situation, because by placing the pins on top of one another the bus length is very short compared to a normal bus layout thus creating the electrical properties to allow for a truly multy processing bus system.
So I saw something coller on disply, using diamond waffers with carbon schoring (done by lazers) one can create a heat sick w/ the carbon schoring as heat pipes. these wafers were then used as the "bread" in a process stack sandwidch. It was a stack of crays on top of one another with the diamond waffer heat sinks inbetween them, thus alloing a really short bus width between the processors. Then the stack was sprayed down w/ a colent, getting a supper computer in container the size of a box of tissues.
Ok so the first thing every one is talking about is this "Complete Reverseable" computation. Well thats wrong and taken out of context (trust me Im very adept at this theory and work with it on a daily basis) The nature of quantum gates, which comprise a quantum computer, are not reversable! though there are a few quantum alg that can be reversed it doesent me all can.
Secound - while a quantum computer may be able to do a ton of caculations at the same time we will never know the answers with the current theory of QM and here is why. Think of a Quantum Bit, a QuBit (and we are not building Ark's here), as a unit vector in 3d space. ITs possible for this vector to point in any direction orginating at the orgin, thus creating a "ball" in space. Now when 2 Qubits are put into the system (a Q-gate) u get 2 out puts (one from the first out put = the first imput un-altered, the secound output an altered form of the secound input). So how do we know what we did, well you observe the system, take a measuremnt. To take a measurement in QM you can only measure orthogional states, ie two possible out comes in a QuBit system, by doing so you force the "ball" (which is all possible outcomes) into one of two vectors thus reducing your infinte caculation. And after you take that measurement it doesent mean that the QuBit u measured will give you the same answer if you measure it again!
Slashdot Mirror
I saw a usage of this tech a couple of years ago on a Motorola Star Tac Prototype. The reasen they wernt used was due to the low product yeald of the tech..
I am truly in agreement about the clams of this switch being rather bogus. What few people realize is that its the protocol that is responsible for 90%+ the latency of a packet through a switch, and not the switching it self. Until there is a commercial method to decoded packet headers in fiber with out converting to electrical signals and also a major change in the header complexity/format the latency of packets through a LAN, WAN, or what ever will not be reduced!
Well since everyone on this thread seams not to know a dam thing let me point you all in the direction of www.rapidio.org a new standard that replaces the entire layered bus architecture with in a system with a lightweight switch protocol. Oh and also look at the member roster you'll see all the big names there except AMD who have the Hyper Transport thing-a-ma-gig.
My company used a simulation package called bones, and like most high end software the only choice is a yearly licenseing agrement. IE RENT! Well dont u know it the company that made bones was bought by its competitor and bam no more licenses, thus no more bones!
The use of FPGAs to create Hyper/Super Computers is only applicable to highly specific application based machines. For the computer descried in the article to be a truly general-purpose super computer one would have to change the logic in the FPGAs rather frequently. It should be know that reloading logic into FPGAs to meet the current needs of a software app is a time consuming progress. Also compilers do not exist that can take a standard C program and convert it in to HDL (Hardware Design Language) that is loaded into FPGAs. The cool stuff that is being done is to merge FPGAs with processing cores (such as the SPARC ALU) into one chip thus giving you the speed of FPGA logic for a specific ask and the ALU core tailored to more general apps. Yet no mater what until a compiler comes out that can convert Software code into HDL, as I stated, in an efficient manner then it's just a toy.
I had the same choice in front of me several years ago, and opted for the Computer Engineering Track. The reasons being more than just to work with hardware, the truth is that most engineering programs will require you to learn alot about the various aspect of Electrical Engineering (which CE is apart of). This is a good thing for a wide and veried tachnical footing has alowed me to jump from project to project looking for what I really want to do. Example being I have done cell phone design, computer programing, 10 Giga Bit asic design, Turbo Codes, and now I am designing an asic chip set to run 4 G4+ boards in a clustering enviroment including modifying the LinuxPPC to run on these boards. What Im trying to say it's easy for a Computer Engineer to jump into fields suh as programing, and designing algorithims, but a Computer Scientist cant just jump into the Computer Enginnering Fileds.
It seems to me that they aren't slowing the light so much as absorbing it a few photons at a time as it passes through the gas, with the resulting spin states in the gas atoms retaining information about the photons. When they read it out with the second pulse they aren't getting the original photons with the same properties. I think this means that the coherence of an entangled state would be destroyed so it couldn't be used for quantum computing.
There are many who believe this is just a symptom of a much greater problem due to deregulation of the power industry. Its been said that our power grid is inherently unstable today as it was before the US began to regulate it in the late 40's. I would like to know from the people in the power industry if they believe this.
First off, I dont have a spelling problem I CANT SPELL!
Secound, yes crays were super computers but since Compact bought the processor division of Cray when it fell apart. The processors now produced by the compact-cray division I call crays.
Third the carbon scoring was deep into the diamond surface and not just soot!
Fourth this is a very unique solution to multi processing that is not done by SGI (who used to own Cray), EMC, SUN. These super computers rely on switching protocals seperate from the processor bus to handel cache coherency. This method I descriped allows one to do a multy processing solution all on the same bus (beyoud 2 processors). Why is this allowed in the described situation, because by placing the pins on top of one another the bus length is very short compared to a normal bus layout thus creating the electrical properties to allow for a truly multy processing bus system.
So I saw something coller on disply, using diamond waffers with carbon schoring (done by lazers) one can create a heat sick w/ the carbon schoring as heat pipes. these wafers were then used as the "bread" in a process stack sandwidch. It was a stack of crays on top of one another with the diamond waffer heat sinks inbetween them, thus alloing a really short bus width between the processors. Then the stack was sprayed down w/ a colent, getting a supper computer in container the size of a box of tissues.
Ok so the first thing every one is talking about is this "Complete Reverseable" computation. Well thats wrong and taken out of context (trust me Im very adept at this theory and work with it on a daily basis) The nature of quantum gates, which comprise a quantum computer, are not reversable! though there are a few quantum alg that can be reversed it doesent me all can.
Secound - while a quantum computer may be able to do a ton of caculations at the same time we will never know the answers with the current theory of QM and here is why. Think of a Quantum Bit, a QuBit (and we are not building Ark's here), as a unit vector in 3d space. ITs possible for this vector to point in any direction orginating at the orgin, thus creating a "ball" in space. Now when 2 Qubits are put into the system (a Q-gate) u get 2 out puts (one from the first out put = the first imput un-altered, the secound output an altered form of the secound input). So how do we know what we did, well you observe the system, take a measuremnt. To take a measurement in QM you can only measure orthogional states, ie two possible out comes in a QuBit system, by doing so you force the "ball" (which is all possible outcomes) into one of two vectors thus reducing your infinte caculation. And after you take that measurement it doesent mean that the QuBit u measured will give you the same answer if you measure it again!
well I think thats enough for your to think on.