SANTA CLARA, Calif.—Gyrfalcon Technology, Inc. (GTI) recently won a 2019 North American Best Practices Award for New Product Innovation from Frost & Sullivan for its efficient artificial intelligence (AI) accelerator chipsets that offer a high performance-to-power usage ratio. Gyrfalcon’s AI accelerator chips are reported to exhibit high reliability in extreme data-centric operations while keeping energy consumption to a minimum.
“This recognition underscores GTI’s commitment to optimizing AI-powered solutions that deliver high performance with low energy consumption,” Frost & Sullivan said in a release.
Gyrfalcon’s AI accelerator chips can be easily integrated into a variety of host processors embedded in electronic devices, such as smartphones, tablets, and industrial robots. The device sensors’ data is processed in a host processor, which undergoes further processing at the AI accelerator. Embedded with application-specific models, AI accelerator chips process the incoming data from host processors before routing back to the host device to run the dedicated application. Based on the application requirements, models can be designed and embedded in the AI accelerator chip.
“As more AI accelerator solutions are trying to pair memory and logic, GTI’s proprietary Gyrfalcon MRAM engine (GME), which is the first AI chip in the industry with integrated magnetic random access memory (MRAM), is a key advantage,” said Sushrutha Katta Sadashiva, senior research analyst at Frost & Sullivan. “With the built-in non-volatile memory of 40 megabytes (MB), this chip can run large AI models, or the memory can be partitioned to run concurrent models on a single chip.”
GTI’s Lightspeeur® portfolio comprises the 2801S accelerator chip performing at 9.3 Tera operations per second per watt (TOPs/watt); the MRAM (magnetic random access memory) based 2802M, which delivers 9.9 TOPs/watt; and the 2803S, offering 24 TOPs/watt. Compared to other AI accelerator chips, GTI’s chips are reported to offer 10 times more efficiency in performance-to-power usage, which can drastically reduce data center costs.
The release also said that the thermal footprint of GTI’s chips is smaller than other chips, thereby eliminating any need for additional cooling equipment. The 2803 chip also includes a unique cascading feature, which allows large AI models to run in data centers across a limitless number of 2803 chips that have been embedded in the data center rack.
“The launch of GTI’s 2801 chip created a new wave in the AI industry, which had been bogged down by complex GPUs and mainframe systems,” noted Sadashiva. “Compared to competing solutions, GTI’s technology offers more design flexibility because customers can mix and match the chips they want based on the end application. The chips can boost any application, such as AI thermostats, sensor hubs, drones, and robots. Regardless of the application, the core technology executes in the same way, ensuring ease of customer use and experience.”
Gyrfalcon Technology Inc. (www.gyrfalcontech.ai) is a developer of high performance AI Accelerators that use low power, packaged in low-cost and small sized chips. Founded by veteran Silicon Valley entrepreneurs and artificial intelligence scientists, GTI aims to drive adoption of AI by bringing the power of cloud AI to local devices, while improving the performance and efficiency of cloud AI.
Each year, Frost & Sullivan presents this award to the company that has developed an innovative element in a product by leveraging leading-edge technologies. The award recognizes the value-added features/benefits of the product and the increased return on investment (ROI) it gives customers.
Frost & Sullivan Best Practices awards recognize companies in a variety of regional and global markets for demonstrating outstanding achievement and superior performance in areas such as leadership, technological innovation, customer service, and strategic product development. Industry analysts compare market participants and measure performance through in-depth interviews, analysis, and extensive secondary research to identify best practices in the industry.