Alex Chow and His Innovation
Alex Chow is now a popular student of Manchester University. He was clever enough to develop a new way of using computer game technologies for environmental research. His research concerns the impact of ocean streams and waves on offshore wind turbines. With the help of graphic processing units (GPUs), Alex managed to create scientific simulations. His innovation uses GPUs and makes work of the computer system faster by a few notches. These simulations mainly deal with violent fluid flows.
Alex Chow could not create anything like this. But he could make use of the above mentioned graphic processing units. They are many times cheaper and don’t require too much energy in comparison with the supercomputers owned by states and large scientific enterprises. Some of the graphic processing units can even fit into a laptop. You can view this sign up offer to experience some games that have simulations as good as the one we are discussing!
Welcome to the World of Better Simulations!Really good simulations can be done only with the help of really good computers. And usually, it is not a PC or laptop. Better to say, it is never anything like that. The student used a kind of a supercomputer created by himself. What do we call a supercomputer? It is a machine made of hundreds of CPUs. They are served by hundreds (if not thousands) of computer cores. All largescale simulations in scientific research need millions of calculations to be done in seconds with the processing of billions of information units.
In any computer, all the main parameters are closely related. It's hard to imagine a universal computer that has high speed and small RAM or huge memory and a small number of disks. For this reason, supercomputers are characterized not only by maximum performance but also by the maximum amount of operational and disk memory.
Providing such technical characteristics is quite expensive - the cost of supercomputers is extremely high. You wouldn't be able to afford one. Even if you spend a chunk, you could only get a laptop with a 32 GB of RAM; a supercomputer could have a RAM size in Terabytes.
What are the important tasks that require systems worth tens and hundreds of millions of dollars?
As a rule, these are fundamental scientific or engineering computational tasks with a wide range of applications, the effective solution of which is possible only if there are powerful computing resources.
These kinds of machines are extremely powerful and very expensive. Even the smallest clusters used in these machines cost hundreds of thousands to millions of dollars. They also use large amounts of energy and only a few scientists have access to them.