Although the chip is not compatible with Intel's current chips, the company said it has already started designing a commercial version that would essentially have dozens or even hundreds of Intel-compatible microprocessors laid out in a tiled pattern on a single chip.

    The chip's design is meant to take advantage of a new generation of manufacturing technology the company introduced last month. Intel said it had changed the basic design of transistors in such a way it would be able to continue to shrink them to smaller sizes -- offering lower power and higher speeds -- for at least a half-decade or more.

    During a briefing on Thursday in a hotel room here, Nitin Borkar, one of the chip's designers, showed an air-cooled computer based on the chip running a simple scientific calculation at speeds above one trillion mathematical calculations a second.

    Such computing power matches the performance speed of the world's fastest supercomputer of just a decade ago. However, Intel acknowledged the experimental chip was not a complete system necessary to do real computing work.

    During the demonstration, Justin R. Rattner, the company's chief technology officer, showed several futuristic computing applications he said the new chip design would help make possible. One of the applications was an automated video editing tool that would, for example, allow a computer to create a digital sports highlights video featuring a user's favorite players.

    A second demonstration showed motion capture technology -- a technique widely used by the videogame industry to reproduce human forms in action -- relying only on digital video cameras and computers. Conventional motion capture technology requires a complex array of sensors pinned to an actor's body and face to record a digital video that can be used interactively.

    In the future, Rattner said, it will be possible to blend synthesized and real-time video.

    "Imagine learning to dance with a virtual instructor," he said.

    In leaping beyond the two- and four-core microprocessors that are being manufactured by Intel and its chief PC industry competitor, Advanced Micro Devices, Intel is following a design trend that is sweeping the computing world.

    Already, computer networking companies and the makers of PC graphics cards are moving to processor designs that have hundreds of computing engines, but only for special applications.

    In addition to new kinds of computing applications, Rattner said that the so-called network-on-chip Teraflop processor would be ideal for the kind of heterogeneous computing increasingly common in the corporate world.

    Large data centers now routinely use a software technique called virtualization to run many operating systems on a single processor in order to gain computing efficiency. Having hundreds or thousands of cores available would vastly increase the power of this style of computing.

    The Teraflop chip, which consumes just 62 watts at teraflop speeds and which is air-cooled, contains an internal data packet router in each processor tile. It is able to move data among tiles in as little as 1.25 nanoseconds, making it possible to transfer 80 billion bytes a second among the internal cores.

    The chip also contains an interface capability that would make it possible for Intel, in the future, to package a memory chip stacked directly on top of the microprocessor. Such a design would make it possible to move data back and forth between memory and processor many times faster than today's chips.

    At the conference on Monday, both Intel and Advanced Micro Devices will describe new power-saving features that will make it possible for entire sections of future microprocessors to be shut down when they are not being used. The A.M.D. technology will be used in its four-core microprocessor, code-named Barcelona, which the company said would be commercially available by midyear.

    (Agencies)