Post by Liam O'Reilly on Aug 26, 2006 10:44:59 GMT
The spare processing power of Sony's PlayStation 3 (PS3) will be harnessed by scientists trying to understand the cause of diseases like Alzheimer's.
Sony has teamed up with US biologists who already run the distributed computing project, folding@home (FAH).
The project harnesses the capacity of thousands of PCs to examine how the shape of proteins, critical to most biological functions, affect disease.
FAH say a network of PS3's will allow performance similar to supercomputers.
With 10,000 machines joined together the researchers calculate they should be able to do a thousand trillion calculations per second.
If that was achieved it would be nearly four times as fast as the world's most powerful supercomputer, IBM's BlueGene/L System, capable of 280.6 trillion calculations per second.
Distributed computing is a way of solving large complex problems by dividing them between many computers.
Volunteers download a piece of software that uses their PC or PS3's processing power when it is idle.
In this way small packets of data can be crunched by individual machines, before being automatically fed back over the internet to a central computer where all of the results can be viewed together.
The method is already used by scientists examining millions of simulations of how malaria spreads to look for ways to control the disease.
Other groups are searching through thousands of hours of radio telescope signals for signs of extra-terrestrial intelligence.
The FAH uses distributed computing to examine protein folding and how it maybe linked to diseases. The way in which proteins contort underpins almost every biological process.
When they do not fold correctly they can cause diseases such as Huntington's, Parkinson's disease, and many cancers.
Scientists still do not entirely understand how or why this process occurs.
To try to gain a better understanding, scientists need to simulate the complex folding process.
However, although a fold may take just ten millionths of a second (10 microseconds) in the body, it takes far longer to simulate on a computer.
An average PC would take all day just to simulate just one billionth of a second (one nanosecond) of protein folding, and 10,000 days to simulate a complete fold.
Dividing the problem up allows the researchers to speed through many more simulations.
The scientists hope the arrival of the PS3 will take this research up another level.
Sony has demonstrated a piece of protein-folding software that will run on its PS3 when it is launched in November.
The PS3 has a powerful processor known as a "cell", which will run up to 10 times faster than current PC chips.
A graphical interface, also being developed between Sony and FAH, will eventually allow users and the scientists to look at the protein from different angles as it folds in real-time.
The new interface takes advantage of the PS3's graphics chip, designed for advanced gaming.
The graphics application is currently undergoing tests and is expected to be finished by September.
When the program is released to PS3 owners, the scientists say they will be able to "address questions previously considered impossible to tackle computationally".
Sony has teamed up with US biologists who already run the distributed computing project, folding@home (FAH).
The project harnesses the capacity of thousands of PCs to examine how the shape of proteins, critical to most biological functions, affect disease.
FAH say a network of PS3's will allow performance similar to supercomputers.
With 10,000 machines joined together the researchers calculate they should be able to do a thousand trillion calculations per second.
If that was achieved it would be nearly four times as fast as the world's most powerful supercomputer, IBM's BlueGene/L System, capable of 280.6 trillion calculations per second.
Distributed computing is a way of solving large complex problems by dividing them between many computers.
Volunteers download a piece of software that uses their PC or PS3's processing power when it is idle.
In this way small packets of data can be crunched by individual machines, before being automatically fed back over the internet to a central computer where all of the results can be viewed together.
The method is already used by scientists examining millions of simulations of how malaria spreads to look for ways to control the disease.
Other groups are searching through thousands of hours of radio telescope signals for signs of extra-terrestrial intelligence.
The FAH uses distributed computing to examine protein folding and how it maybe linked to diseases. The way in which proteins contort underpins almost every biological process.
When they do not fold correctly they can cause diseases such as Huntington's, Parkinson's disease, and many cancers.
Scientists still do not entirely understand how or why this process occurs.
To try to gain a better understanding, scientists need to simulate the complex folding process.
However, although a fold may take just ten millionths of a second (10 microseconds) in the body, it takes far longer to simulate on a computer.
An average PC would take all day just to simulate just one billionth of a second (one nanosecond) of protein folding, and 10,000 days to simulate a complete fold.
Dividing the problem up allows the researchers to speed through many more simulations.
The scientists hope the arrival of the PS3 will take this research up another level.
Sony has demonstrated a piece of protein-folding software that will run on its PS3 when it is launched in November.
The PS3 has a powerful processor known as a "cell", which will run up to 10 times faster than current PC chips.
A graphical interface, also being developed between Sony and FAH, will eventually allow users and the scientists to look at the protein from different angles as it folds in real-time.
The new interface takes advantage of the PS3's graphics chip, designed for advanced gaming.
The graphics application is currently undergoing tests and is expected to be finished by September.
When the program is released to PS3 owners, the scientists say they will be able to "address questions previously considered impossible to tackle computationally".