IP and Development Resources Will Provide Accelerated Time-To-Market for Customized Chip Solutions Needing Superior AI Specifications and Attributes
Gyrfalcon Technology Inc. (GTI), the chip innovator with the industry’s densest AI inference accelerators, is offering the technology powering the company’s Lightspeeur 2801 and 2803 AI accelerators for use in custom SoC designs through a new IP licensing model for companies seeking the ultimate level of chip customization.
The accelerator chips’ architecture features AI cores that are ultra-small and low-power, enabling AI Processing in Memory (APiM) with those cores configured in a proprietary Matrix Processing Engine (MPE™) architecture. The AI cores accelerate the convolutional neural network (CNN) on AI frameworks like Caffe, PyTorch, and TensorFlow. GTI’s accelerator chips combine over 28,000 cores, with the Lightspeeur 2803 capable of 16.8 TOPS in under a watt, and the Lightspeeur® 2801 using only 300mW while providing 2.8 TOPS. By offering the MPE architecture along with the company’s development and software optimization tools and technical support, SoC designers can integrate AI inference acceleration at a minimal cost in die area and just milliwatts of power consumption.
“GTI is differentiating itself at a time when the market has been saturated with companies talking about AI chips. We have been producing our three different AI Accelerator chips, now in the hands of customers designing end products, so our silicon is proven. While we intend to continue introducing and producing new AI Accelerator chips, our technology is 100% proprietary, and protected with a broad and deep portfolio of patents. We will deliver the advantages of GTI technology to companies seeking new advantages, accelerating the growth of both the global AI chip market and the monetization of our technology,” said Kimble Dong, CEO of Gyrfalcon Technology Inc.
The company introduced its first Lightspeeur® 2801 chip as an Edge AI solution in 2017, and added a second chip, the Lightspeeur® 2803 optimized for cloud AI in the data center in 2018. Both are offered in a configuration of 16 chips on a PCIe Card called GAINBOARD™ System products, packaged for upgrading data centers needing to provide AI services. Customers are designing Gyrfalcon chips inside numerous commercial products, including: smart home & office products, consumer & electronics, mobile phones & computers, baby & pet monitors, robot vacuums, defect detection equipment, edge servers and AI Data Center solutions.
GTI’s AI domain specific technology supports standard ML frameworks and tuned models in proven silicon in use by customers. Technology licensees could expect significant gains in AI performance, improvements in power dissipation and cost advantages by integrating GTI’s technology into their SOC or SOM offerings.
Gyrfalcon is one of the very few AI accelerator chip companies able to offer clients leading-edge high performing USB 3.0 dongles that can be used with Windows & Linux PCs or with hardware development kits like Raspberry Pi which are used for model creation, chip evaluation and proof-of-concept designs. Licensees will get access to the development hardware, such as the USB dongles, discrete chips or multi-chip boards, along with IP development tools and technical documentation, and the company’s AI chip design expertise.