Electronic Devices & Storage Corporation (“Toshiba”) today
announced development of an image recognition SoC (System on Chip) for
automotive applications that implements deep learning accelerator at 10
times the speed and 4 times the power efficiency of Toshiba’s previous
product. Details of the technology were reported at the
2019 IEEE International Solid-State Circuits Conference (ISSCC) in San
Francisco on February 19.
Advanced driver assistance systems, such as autonomous emergency
braking, offer increasingly advanced capabilities, and implementing them
requires image recognition SoC that can recognize road traffic signs and
road situations at high speed with low power consumption.
Deep neural networks (DNN), algorithms modeled after the neural networks
of the brain, perform recognition processing much more accurately than
conventional pattern recognition and machine learning, and are widely
expected to find utilization in automotive applications. However,
DNN-based image recognition with conventional processors takes time, as
it relies on a huge number of multiply-accumulate (MAC) calculations.
DNN with conventional high-speed processors also consumes too much power.
Toshiba has overcome this with a DNN accelerator that implements deep
learning in hardware. It has three features.
Parallel MAC units. DNN processing requires many MAC computations.
Toshiba’s new device has four processors, each with 256 MAC units.
This boosts DNN processing speed.
Reduced DRAM access. Conventional SoC have no local memory to keep
temporal data close to the DNN execution unit and consume a lot of
power accessing local memory. Power is also consumed loading the
weight data, used for the MAC calculations. In Toshiba’s new device,
SRAM are implemented close to the DNN execution unit, and DNN
processing is divided into sub-processing blocks to keep temporal data
in the SRAM, reducing DRAM access. Additionally, Toshiba has added a
decompression unit to the accelerator. Weight data, compressed and
stored in DRAM in advance, are loaded through the decompression unit.
This reduces the power consumption involved in loading weight data
Reduced SRAM access. Conventional deep learning needs to access SRAM
after processing each layer of DNN, which consumes too much power. The
accelerator has a pipelined layer structure in the DNN execution unit
of DNN, allowing a series of DNN calculations to be executed by one
The new SoC complies with ISO26262, the global standard for functional
safety for automotive applications.
Toshiba will continue to enhance the power efficiency and processing
speed of the developed SoC and will start sample shipments of ViscontiTM5,
the next generation of Toshiba’s image-recognition processor, in
September this year.
Toshiba’s image recognition SoC in “1.9TOPS and 564GOPS/W
Heterogeneous Multicore SoC with Color-based Object Classification
Accelerator for Image-Recognition Applications,” a paper delivered
at the 2015 IEEE International Solid-State Circuits Conference
* ViscontiTM is a trademark of Toshiba Electronic Devices &
* All other company names, product names and
service names may be trademarks of their respective companies.
About Toshiba Electronic Devices & Storage Corporation
Toshiba Electronic Devices & Storage Corporation combines the vigor of a
new company with the wisdom of experience. Since becoming an independent
company in July 2017, we have taken our place among the leading general
devices companies, and offer our customers and business partners
outstanding solutions in discrete semiconductors, system LSIs and HDD.
Our 22,000 employees around the world share a determination to maximize
the value of our products, and emphasize close collaboration with
customers to promote co-creation of value and new markets. We look
forward to building on annual sales now surpassing 800-billion yen (US$7
billion) and to contributing to a better future for people everywhere.
out more about us at https://toshiba.semicon-storage.com/ap-en/top.html
Toshiba Electronic Devices & Storage
Business Planning Div. Public Relations & Investor