In fact, for AI in network edge applications for all kinds of mass markets, low power consumption, small size, and low cost semiconductor solutions are essential to enable this kind of local sensor data processing. To address this trend Lattice Semiconductor recently introduced Lattice sensAI, a complete technology suite that combines modular hardware kits, neural network IP cores, software tools, reference designs, and custom design services to accelerate machine learning. Mass market IoT applications.
According to Chen Yingren, senior business development manager of Lattice Asia Pacific, Lattice sensAI offers optimized solutions with ultra-low power consumption (less than 1mW-1W), small package size (5.5-100 mm2), and flexible interface (MIPI® CSI -2, LVDS, GigE, etc., and low volume price (about 1-10 US dollars), can accelerate the realization of network edge computing closer to the data source.
According to the microgrid, Lattice Semiconductor ranks third in the world among FPGA manufacturers worldwide, behind only Xilinx and Intel’s Altera. Unlike Alta and Xilinx, Lattice Semiconductor chose Low-power, small-size, low-cost development direction as the goal, focusing on the provision of terminal electronic product solutions.
Earlier, Glen Hawk, chief operating officer of Lattice Semiconductor, said in an interview with Gaiwei.com that since 2006, the interconnection market at the edge of the network has been gradually increasing. The network edge computing is a new market demand and will become future growth. The main driving force. At the edge of the network control, interconnection, computing three areas, Lattice can provide complete and highly advantageous solutions.
IHS Markit expects to have 40 billion IoT devices on the edge of the network from 2018 to 2025. In the next 5-10 years, the convergence of transformational technologies such as IoT, artificial intelligence-based network edge computing and cloud analysis will disrupt all industries. , And foster new business opportunities. Semico Research predicts that the number of network edge devices using artificial intelligence will explode at a compound annual growth rate of 110% over the next five years.
Deepak Boppana, director of product and marketing at Lattice Semiconductor, said: 'Lattice sensAI has for the first time fully solved the need for flexible, low cost, ultra-low power AI semiconductor solutions that can be quickly deployed to various emerging markets and the general public. Market IoT applications. Lattice sensAI will accelerate the integration of sensor data processing and analysis on network edge devices by providing a full-featured machine learning inference technology that combines flexible, ultra-low power FPGA hardware and software solutions. These new network edges The computational solution relies on our leadership in FPGA edge interconnects to enable flexible sensor interface bridging and data aggregation in high-volume IoT applications, including smart audio, surveillance cameras, industrial robots, and drones.