Browse Definitions :
Definition

3-D chip (3D chip)

A 3-D chip is an integrated circuit ( IC ) containing a three-dimensional array of interconnected devices performing digital, analog, image processing and neural-network functions, either individually or in combination.

See an image of a thinned wafer used to create a 3-D chip

3-D chip technology solves a number of issues that have been challenging chip manufacturers looking for performance increases and reductions in processor size. As chips have grown smaller and more powerful, the wires that connect the increasing numbers of transistor s have necessarily become both thinner and closer together, resulting in increased resistance and overheating. Both can cause signal delays, limiting the clock speed of central processing unit s.

In April 2007, a new version of 3-D chips was announced by a partnership of IBM and Rensselaer Polytechnic Institute (RPI) researchers at the IBM T.J. Watson Research Center, with support from the Defense Advanced Research Project Agency ( DARPA ). These 3-D chips layer one chip upon another using a technique called wafer bonding . While some companies currently package processors by layering one upon another, IBM's technique uses one base layer of silicon with active wafers layered on top. This allows engineers to place a processor on the bottom of the stack and then layer memory or other components across the top, resulting in a thousand-fold decrease in connector length, as chips are no longer organized in a two-dimensional layouts with wires connecting transistors at the periphery of chips. This reduces the distance data has to travel, resulting in much faster processing. Similarly, a hundred-fold increase in connector density dramatically reduces the size of the chip.

IBM 's engineers used a new method of manufacturing called through-silicon vias that allows multiple chip components to be stacked upon one another vertically, creating faster, smaller and lower-power CPU s (central processing units). Through-silicon vias also allow for more efficient heat dissipation up through the stack to cooling systems and, according to IBM, improve power-efficiency in silicon-germanium based products up to 40%, resulting in longer battery life.

IBM expects to begin production of 3-D chips in 2008. "Big Blue" will be applying the technology initially in mobile devices and wireless communications. Memory-on-processor technology will be available for use in servers and supercomputers in 2009. Intel used a similar 3-D chip structure in February 2007 capable of teraflop processing (a trillion calculations per second), effectively performing calculations as quickly as a complete data center while consuming a tiny fraction of the energy. Either of these improvements may allow the extension of Moore's law well into the 21st century.

This was last updated in March 2011

Continue Reading About 3-D chip (3D chip)

SearchCompliance
  • ISO 31000 Risk Management

    The ISO 31000 Risk Management framework is an international standard that provides businesses with guidelines and principles for ...

  • pure risk

    Pure risk refers to risks that are beyond human control and result in a loss or no loss with no possibility of financial gain.

  • risk reporting

    Risk reporting is a method of identifying risks tied to or potentially impacting an organization's business processes.

SearchSecurity
  • Pretty Good Privacy (PGP)

    Pretty Good Privacy or PGP was a popular program used to encrypt and decrypt email over the internet, as well as authenticate ...

  • email security

    Email security is the process of ensuring the availability, integrity and authenticity of email communications by protecting ...

  • Blowfish

    Blowfish is a variable-length, symmetric, 64-bit block cipher.

SearchHealthIT
SearchDisasterRecovery
  • What is risk mitigation?

    Risk mitigation is a strategy to prepare for and lessen the effects of threats faced by a business.

  • fault-tolerant

    Fault-tolerant technology is a capability of a computer system, electronic system or network to deliver uninterrupted service, ...

  • synchronous replication

    Synchronous replication is the process of copying data over a storage area network, local area network or wide area network so ...

SearchStorage
  • direct access

    In computer storage, direct access is the process of reading and writing data on a storage device by going directly to where the ...

  • kibi, mebi, gibi, tebi, pebi and exbi

    Kibi, mebi, gibi, tebi, pebi and exbi are binary prefix multipliers that, in 1998, were approved as a standard by the ...

  • holographic storage (holostorage)

    Holographic storage is computer storage that uses laser beams to store computer-generated data in three dimensions.

Close