High-Performance, Low-Power DRAM Combines with SoC in a SiP

By Rich Nass

Executive Vice President

Embedded Computing Design

February 08, 2021


High-Performance, Low-Power DRAM Combines with SoC in a SiP
(Image Courtesy of Winbond)

What do you get when you cross high-bandwidth memory with artificial intelligence (AI)?

You get Winbond Electronics’ 1-Gbit LPDDR3 DRAM product. The feat is achieved when the memory device is combined with Tsing Micro’s TX510 AI system-on-chip (SoC). The two devices are housed in a single 14- by 14-mm TFBGA system-in-package (SiP).

The TX510 is an advanced AI Edge computing engine optimized that’s intended for functions like 3D sensing, facial recognition, object recognition, and gesture recognition. Those functions are attainable when the part is paired with Winbond’s LPDDR3 DRAM, which offers a maximum bandwidth of 1866 Mbits/s and operates from a dual 1.2/1.8-V supply. Also included are power-saving features such as deep power-down mode and a clock stop capability.

The TX510 SoC includes a 32-bit RISC processor, a reconfigurable neural network engine, a reconfigurable general computing engine, an image signal processor, and a 3D sensing engine. Achieving a computing throughput of up to 1.2 TOPS, this SiP can perform accurate face recognition (false acceptance ratio of 1 in 10 million) in less than 100 ms, and compare features with a library of 100,000 faces in less than 50 ms. Peak operating power consumption is just 450 mW, and the chip uses just 0.01 mW in quiescent mode.

The SiP is intended for use in applications which require high-speed image detection and recognition, including biometric sensing, video surveillance, smart retail operations, smart home automation and advanced industrial automation.

Richard Nass’ key responsibilities include setting the direction for all aspects of OSM’s ECD portfolio, including digital, print, and live events. Previously, Nass was the Brand Director for Design News. Prior, he led the content team for UBM’s Medical Devices Group, and all custom properties and events. Nass has been in the engineering OEM industry for more than 30 years. In prior stints, he led the Content Team at EE Times, Embedded.com, and TechOnLine. Nass holds a BSEE degree from NJIT.

More from Rich