Within the next three to four years, most PC users will see their machines morph into personal supercomputers. This change will be enabled by the emergence of multicore CPUs and, perhaps more importantly, the arrival of massively parallel cores in the graphical processing units.
In fact, ATI (a division of Advanced Micro Devices) and Nvidia are already offering multiple programmable cores in their high-end discreet graphics processing platforms. These cores can be programmed to do many parallel processing tasks, resulting in dramatically better display features and functions for video, especially for gaming. But these platforms currently come at a hefty price and often require significant amounts of power, making them impractical in many laptop designs.
But preliminary steps are being taken to make these high-end multicore and programmable components available to virtually any machine. Vendors are moving to create integrated multicore platforms, with 64 or more specialty cores that can be used in conjunction with the various multicore CPUs now taking hold in the market. Using the most advanced semiconductor processes and geometries (32nm and soon 22nm and beyond), these new classes of devices will achieve incredible processing capability. They will also morph from the primarily graphics-oriented tasks they currently perform to include many more tasks associated with business and personal productivity.
The researchers have created components that could one day be used to develop quantum computers – devices based on molecular scale technology instead of silicon chips and which would be much faster than conventional computers.
The study, by scientists at the Universities of Manchester and Edinburgh and published in the journal Nature, was funded by the European Commission.
Scientists have achieved the breakthrough by combining tiny magnets with molecular machines that can shuttle between two locations without the use of external force. These manoeuvrable magnets could one day be used as the basic component in quantum computers.
Conventional computers work by storing information in the form of bits, which can represent information in binary code – either as zero or one.
Quantum computers will use quantum binary digits, or qubits, which are far more sophisticated – they are capable of representing not only zero and one, but a range of values simultaneously. Their complexity will enable quantum computers to perform intricate calculations much more quickly than conventional computers.
Professor David Leigh, of the University of Edinburgh’s School of Chemistry, said: “This development brings super-fast, non-silicon based computing a step closer.
For those of you who want the world at your fingertips, the wait is almost over.
The future PC promises to put nearly everything you could need or want right in your palm.
Think of a souped-up version of today’s smartphone, with a monitor that unrolls into a larger screen and a biometric security system that lets you access everything in your professional and personal life from anywhere, with all the data residing in the cloud. Wave it at your car to unlock the door. Order and pay for your morning coffee with a touch of a button. Plug it into a docking station and project that big presentation to your clients. Book a weekend getaway with just a few clicks.
“PCs are going from engines or tools to portals and enablers. The vision of what they’ll be in the future is a partner. They’ll be participating in the higher cognitive tasks of what people do to get their jobs done,” says Andrew Chien, director of research at Intel Corp.
The personal computer has been a corporate workhorse for decades. And while it has evolved, becoming slimmer and more mobile, in many ways it still resembles those old terminals tethered to the mainframe. But the next decade will bring dramatic changes, as the PC evolves past the standard desktop and laptop units to amalgamations of computing devices and their peripherals.
This future PC will be smarter, too. It could discreetly remind you of the name of an acquaintance and alert you when it’s time to take your medicine. It will be your colleague, your butler — and possibly your friend.
IBM Research on Thursday is expected to uncover work it is doing to bring the brain’s processing power to computers, in an effort to make it easier for PCs to process vast amounts of data in real time.
The researchers want to put brain-related senses like perception and interaction into hardware and software so that computers are able to process and understand the data quicker while consuming less power, said Dharmendra Modha, a researcher at IBM. The researchers are bringing the neuroscience, nanotechnology, and supercomputing fields together in an effort to create the new computing platform, he said.
The goal is to create machines that are mind-like and adapt to changes, which could allow companies to find more value in their data. Right now, a majority of information’s value is lost, but relevant data can allow businesses or individuals to make rapid decisions in time to have significant impact, he said.
“If we could design computers that could be in real-world environments and sense and respond in an intelligent way, it would be a tremendous step forward,” Modha said.
There is a problem in the core philosophy of computing and a new approach is needed, Modha said. Today’s model first defines objectives to solve problems, after which algorithms are built to achieve those objectives.
“The brain is the opposite. It starts with an existing algorithm and then problems [are] second. It is a computing platform that can address a wide variety of problems,” Modha said.
For example, the new approach could help efficiently manage the world’s water supplies through real-time analysis of data that could help discover new patterns, Modha said. A network of sensors could monitor temperature, pressure, wave height and ocean tide across the oceans. “Imagine streaming this data to a global brain that discovers invariant patterns and associations that no algorithms of today can do,” Modha said.
It will also be able to sense the world’s markets, like stocks, bonds and real estate, extracting patterns and associations in the way the brain extracts information from those environments.
Also see IBM to Build “Thinking” Computers Modeled on the Brain and IBM plans ‘brain-like’ computers.
IBM looks set to join the seriously multi-core set with the Power7 chip. Internal documents seen by The Register show Power7 with eight cores per processor and also some very, very large IBM boxes based on the chip.
The IBM documents have the eight-core Power7 being arranged in dual-chip modules. So, that’s 16-cores per module. As IBM tells it, each core will show 32 gigaflops of performance, bringing each chip to 256 gigaflops. Just on the gigaflop basis, that makes Power7 twice as fast per core as today’s dual-core Power6 chips, although the actual clock rate on the Power7 chips should be well below the 5.0GHz Power6 speed demon.
In fact, according to our documents, IBM will ship Power7 at 4.0GHz in 2010 on a 45nm process. We’re also seeing four threads per core on the chip.
For some customers, IBM looks set to create 2U systems with four of the dual-chip modules, giving the server 64 cores of fun. These 2U systems will support up to 128GB of memory and hit 2 teraflops.
IBM has an architecture that will let supercomputing types combine these 2U boxes to form a massive unit with 1,024 cores, hitting 32 teraflops of performance with 2TB of memory.
And, er, if you are a seriously demanding type, boy, does IBM have the system for you.
IBM is planning to build a supercomputer that runs at 10 petaflops in 2011. A petaflop is 10^15 calculations per second. So 10 petaflop would be 10^16.
The military recently built the very first supercomputer to break the 1 petaflop barrier. A tenfold increase within 3 years is no laughing matter.
A 10 petaflop supercomputer would also be powerful enough (according to Kurzweil’s calculations, that is) to simulate a human brain in real time.