Skip to main content

    HP estimates it will have a 'technologically viable' memristor by 2014

    HP estimates it will have a 'technologically viable' memristor by 2014

    /

    Stan Williams of the Memristor Research Group at HP says that the company will have a technologically viable memristor by 2014.

    Share this story

    If you buy something from a Verge link, Vox Media may earn a commission. See our ethics statement.

    memristor
    memristor

    HP originally claimed that it would be shipping memristor products by 2013, but a recent presentation by Stan Williams indicates that it could be 2014 or later until that happens. Williams, director of the Memristor Research Group at HP, was presenting at a conference in Oxnard, California when he said "[in] terms of commercialization, we'll have something technologically viable by the end of next year."

    Williams explains that the delay is due to economic forces, rather than scientific ones, saying:

    It's sad to say, but the science and technology are the easy part. The economics, investment, and market readiness are harder. Our partner, Hynix, is a major producer of flash memory, and memristors will cannibalize its existing business by replacing some flash memory with a different technology. So the way we time the introduction of memristors turns out to be important. There's a lot more money being spent on understanding and modeling the market than on any of the research.

    It was back in 2008 when HP announced it had developed a memristor — an electrical component that not only controls the stream of electrons flowing through it, like a resistor, but also "remembers" its last charge. Instead of using an on or off state to represent ones and zeroes like a transistor, is uses analogue values that scale a range of voltages. According to Williams, the analogue nature makes one memristor as computationally powerful as ten transistors.

    Despite the rapidly declining price of solid state drives, memristors can be used to create solid-state storage that is both smaller and faster. Because fewer memristors can be used in lieu of transistors, and using the same parts, these storage devices might be cheaper than DRAM type storage as well. Williams says that "[if] you know what you're doing — and there's a lot of intellectual property involved — literally any foundry could make memristors tomorrow." While economic and market forces my prevent that from happening, the idea of cheaper storage and faster computers is certainly appealing.