Winbond Electronics Corporation, a leading global supplier of semiconductor memory solutions, today announced that FPGA manufacturer Gowin Semiconductor has embedded a Winbond 64Mb HyperRAM fast memory device in its new GoAI 2.0 machine learning platform.

GoAI 2.0 is a complete, new hardware and software solution for machine learning applications. Compatible with the TensorFlow machine learning development environment, GoAI 2.0 is aimed at edge computing applications such as smart door locks, smart speakers, voice-activated devices and smart toys.

The hardware component of the GoAI 2.0 platform, the GW1NSR4, is a system-in-package (SiP) featuring a FPGA and ARM Cortex M3 microcontroller for the machine learning application supported by Winbond's 64Mb HyperRAM supplied in known good die (KGD) format.

The Winbond DRAM based on HyperRAM technology is ideal for Gowin's target applications, in which the electronics circuit needs to be made as small as possible, while providing sufficient storage and data bandwidth to support compute-intensive workloads such as keyword detection or image recognition. Winbond's 64Mb HyperRAM product has just connected 11 signal pins, so its connections to the host FPGA is minimal - the entire GW1NSR4 SiP has a footprint of just 4.2mm x 4.2mm in a BGA package. The 64Mb memory capacity provided by the Winbond device is sufficient to run both an operating system and to concurrently operate as buffer memory for a TinyML model, or as a frame buffer.

The performance specifications of the Winbond's 64Mb HyperRAM include maximum data bandwidth of 500MB/s. It also offers ultra-low power consumption in operating and hybrid sleep modes.

Jason Zhu, CEO of Gowin, said: 'The problem which Gowin Semiconductor has solved with the GW1NSR4 is to pack a high-performance and low-power edge computing engine in a tiny package. The Winbond KGD format and HyperRAM memory technology are ideal for this, because the die can be embedded in the same package as the FPGA, eliminating the need for DRAM as an external component.

'Gowin is very happy that we had Winbond as our partner in the development of the GW1NSR4 because its expertise in the KGD package format and its help in integrating the die into the SiP helped us realize a very effective and reliable design in a short time.'

Winbond's HyperRAM products are available for high-volume production in densities of 512Mb, 256Mb,

128Mb, 64Mb and 32Mb. For more information, go to www.winbond.com.

About Gowin Semiconductor Corp

Founded in 2014, Gowin Semiconductor Corp., headquartered with major R&D in China, has the vision to accelerate customer innovation worldwide with our programmable solutions. We focus on optimizing our products and removing barriers for customers using programmable logic devices. Our commitment to technology and quality enables customers to reduce the total cost of ownership from using FPGA on their production boards. Our offerings include a broad portfolio of programmable logic devices, design software, intellectual property (IP) cores, reference designs, and development kits. We strive to serve customers in the consumer, industrial, communication, medical, and automotive markets worldwide.

About Winbond

Winbond Electronics Corporation is a total memory solution provider. The Company provides customer-driven memory solutions backed by the expert capabilities of product design, R&D, manufacturing, and sales services. Winbond's product portfolio, consisting of Specialty DRAM, Mobile DRAM, Code Storage Flash, and TrustME Secure Flash, is widely used by tier-1 customers in communication, consumer electronics, automotive and industrial, and computer peripheral markets. Winbond is headquartered in Central Taiwan Science Park (CTSP) and it has subsidiaries in the USA, Japan, Israel, China and Hong Kong, and Germany. Based on Taichung and new Kaohsiung 12-inch fabs in Taiwan, Winbond keeps pace to develop in-house technologies to provide high-quality memory IC products.

Contact:

Jacky Tseng

Tel: +886-3-5678168 ext 78562

Email: yctseng7@winbond.com

(C) 2021 Electronic News Publishing, source ENP Newswire