London: In what could be called a major technological innovation, scientists have unveiled an ultra-fast chip which they claim could make desktop computers 20 times faster than the current ones.
Modern computers have a processor with two, four or sometimes 16 cores to carry out tasks. Now, a team, led by the University of Glasgow, has developed a central processing unit which effectively have 1,000 cores on a single microchip.
The developments could usher in a new age of high-speed computing in the next few years for home users frustrated with slow-running systems; the new “super” computer is also much greener than modern machines, despite its high speed, say its developers.
The scientists used a chip called a Field Programmable Gate Array (FPGA) which like all microchips contains millions of transistors -- tiny on-off switches that are the foundation of any electronic circuit, the Daily Mail reported.
But FPGAs can be configured into specific circuits by the user, rather than their function being set at a factory. This enabled the team to divide up the transistors within the chip into small groups and ask each to perform a task.
By creating more than 1,000 mini-circuits within the FPGA chip, the scientists effectively turned the chip into a 1,000-core processor -- each core working on its own instructions.
The chip was able to process around five gigabytes of data per second in testing - making it approximately 20 times faster than modern computers.
Team leader Wim Vanderbauwhedea said: “FPGAs are not used within standard computers because they are fairly difficult to program but their processing power is huge while their energy consumption is very small because they are so much quicker -- so they are also a greener option.”
While most computers sold today now contain more than one processing core, which allows them to carry out different processes simultaneously, traditional multi-core processors must share access to a memory source, slowing the system down.
The scientists were able to make the processor faster by giving each core a certain amount of dedicated memory.
Vanderbauwhede said: “This is very early proof-of-concept work where we’re trying to demonstrate a convenient way to program FPGAs so that their potential to provide very fast processing power could be used much more widely in future computing and electronics.”