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)

Start the conversation

Send me notifications when other members comment.

By submitting you agree to receive email from TechTarget and its partners. If you reside outside of the United States, you consent to having your personal data transferred to and processed in the United States. Privacy

Please create a username to comment.

-ADS BY GOOGLE

File Extensions and File Formats

SearchCompliance

SearchSecurity

  • Web application firewall (WAF)

    A Web application firewall (WAF) is a firewall that monitors, filters or blocks traffic to and from a Web application. WAFs are ...

  • MD5

    The MD5 hashing algorithm is a one-way cryptographic function that accepts a message of any length as input and returns as output...

  • identity theft

    Identity theft, also known as identity fraud, is a crime in which an imposter obtains key pieces of personally identifiable ...

SearchHealthIT

SearchDisasterRecovery

  • call tree

    A call tree -- sometimes referred to as a phone tree -- is a telecommunications chain for notifying specific individuals of an ...

  • mass notification system (MNS)

    A mass notification system is a platform that sends one-way messages to inform employees and the public of an emergency.

  • disaster recovery as a service (DRaaS)

    One approach to a strong disaster recovery plan is DRaaS, where companies offload data replication and restoration ...

SearchStorage

  • secondary storage

    Secondary storage is used to protect inactive data written from a primary storage array to a nonvolatile tier of disk, flash or ...

  • VRAM (video ram)

    VRAM (video RAM) is a reference to any type of random access memory (RAM) used to store image data for a computer display.

  • ZFS

    ZFS is a local file system and logical volume manager created by Sun Microsystems to control the placement, storage and retrieval...

SearchSolidStateStorage

  • SSD RAID (solid-state drive RAID)

    SSD RAID (solid-state drive RAID) is a methodology commonly used to protect data by distributing redundant data blocks across ...

  • Tier 0

    Tier 0 (tier zero) is a level of data storage that is faster, and perhaps more expensive, than any other level in the storage ...

  • PCIe SSD (PCIe solid-state drive)

    A PCIe SSD (PCIe solid-state drive) is a high-speed expansion card that attaches a computer to its peripherals.

SearchCloudStorage

  • RESTful API

    A RESTful application program interface breaks down a transaction to create a series of small modules, each of which addresses an...

  • cloud storage infrastructure

    Cloud storage infrastructure is the hardware and software framework that supports the computing requirements of a private or ...

  • Zadara VPSA and ZIOS

    Zadara Storage provides block, file or object storage with varying levels of compute and capacity through its ZIOS and VPSA ...

Close