November 7, 2016

Toshiba Corporation continues to build on its commitment to promoting the Internet of Things and Big Data analysis with development of a Time Domain Neural Network(1) (TDNN) that sues an extremely low power consumption neuromorphic semiconductor circuit to perform processing for Deep Learning. TDNN is composed of a massive number of tiny processing units that use Toshiba’s original analog technique, unlike conventional digital processors. TDNN was reported on November 8 at A-SSCC 2016 (Asian Solid-State Circuits Conference 2016), an IEEE-sponsored international conference on semiconductor circuit technology held in Japan.

Deep learning requires massive numbers of calculations, typically executed on high performance processors that consume a lot of power. However, bringing the power of deep learning to IoT edge devices, such as sensors and smart phones requires highly energy efficient ICs that can perform the large number of required operations while consuming extremely little energy.

In von Neumann type(2) computer architecture, most energy is consumed moving data from on-chip or off-chip memory devices to the processing unit.  The most effective way to reduce movement of a datum is to have massive numbers of processing units, each dedicated to handling only one datum that is located close by. These datum points are given a weight during conversion of an input signal (e.g. an image of a cat) to an output signal (e.g. the recognition of the image as a cat). The closer the datum point is to the desired output, the higher the weight it is given. The weight provides a parameter that automatically guides the deep learning process.

The brain has similar architecture, in that the strength of coupling between neurons (weight data) is built into synapses (processing units). In this case, synapses are connections between neurons and each has a different strength. That strength (weight) determines the signal that passes the connection. In this way, a synapse executes a kind of processing. This architecture, which can be called as fully spatially unrolled architecture, is attractive, but it has an obvious drawback—replicating it on a chip requires a massive number of arithmetic circuits that quickly becomes too large.

Toshiba’s TDNN, which employs time-domain analog and digital mixed signal processing (TDAMS(3)) techniques developed in 2013 allow miniaturization of the processing unit. In TDAMS, arithmetic operations, such as addition, are performed efficiently by using the delay time of the digital signal passing the logic gate as an analog signal. Using this technique, the processing unit for deep learning can be composed of only three logic gates and a 1-bit memory with the fully spatially unrolled architecture. Toshiba has fabricated a proof-of-concept chip that uses SRAM (static random access memory) cell as the memory and that has demonstrated recognition of handwritten figures. The energy consumption per operation is 20.6 fJ(4), which is 1/6x better than previously reported at a leading conference before(5).

Toshiba plans to develop TDNN as a resistive random access memory (ReRAM) in order to further improve energy and area efficiencies. The goal is an IC that realizes high performance deep learning technology on edge devices.

1.TDNN: Neural network using time-domain analog and digital mixed signal processing technique

2.Von Neumann type: The standard and most widely used computer architecture. The architecture loads data from memory devices to the processing unit for processing.

3.TDAMS: An analog signal processing technique that uses the delay time of a digital signal passing logic gates as an analog signal. Developed by Toshiba.

 (reference: http://www.toshiba.co.jp/about/press/2013_02/pr2101.htm)

4.20.6fJ: Equivalent to the performance of 48.6 trillion operations in 1 second with 1 W of power consumption.

5.ISSCC 2016 (International Solid-State Circuits Conference 2016) paper number 24.2

*Information in this document, including product prices and specifications, content of services and contact information, is current on the date of the announcement but is subject to change without prior notice.

Toshiba Corporation- Semiconductor and Storage Products Company　Website＞
http://toshiba.semicon-storage.com/ap-en?mm=cp161108&no=04

Visit Chip1Stop Chinese site
Visit Chip1Stop Korean site
Visit Chip1Stop English site
Visit Chip1Stop German site

Companies Website:
http://toshiba.semicon-storage.com/ap-en?mm=cp161108&no=04

Toshiba News Release

• Toshiba Starts Test-Sample Shipments of a Bare Die 1200V SiC MOSFET with Low On-Resistance and High Reliability, for Use in Automotive Traction Inverters

  2024/11/13Toshiba  Automotive

• Toshiba Starts Sample Shipments of Gate Driver IC for Three-Phase Brushless DC Motors in Diverse Automotive Applications

  2024/11/01Toshiba  Automotive

• Toshiba Releases Automotive Photorelay with Output Withstand Voltage of 900V, Housed in a Small Package

  2024/10/28Toshiba  Automotive

• Toshiba’s 1200V Additions to its Lineup of Third-Generation SiC Schottky Barrier Diodes Will Contribute to High Efficiency in Industrial Power Equipment

  2024/09/26Toshiba  Power Supply

• Toshiba Is Sampling an Automotive CXPI Responder Interface IC that Contributes to Shorter Software Development Times

  2024/09/05Toshiba  Automotive

Related News Release

• Winbond’s LPDDR4/4X: A Green Solution for the Automotive Industry

  2024/11/29  Winbond Electronics  Processor/Memory

• STMicroelectronics reveals Page EEPROM two-in-one memory to boost smart-edge performance and efficiency

  2024/10/08  STMicroelectronics  Processor/Memory

• Winbond has unveiled its latest 1Gb QspiNAND for Wearable and Low-Power IoT Devices.

  2024/08/08  Winbond Electronics  Processor/Memory

• STMicroelectronics powers up the intelligent edge with second-generation STM32 microprocessors, bringing performance boost and industrial resilience

  2024/03/18  STMicroelectronics  Processor/Memory

• Winbond Introduces Innovative CUBE Architecture for Powerful Edge AI Devices

  2023/09/27  Winbond Electronics  Processor/Memory