What is FPGA's industrial IoT solution?

In SpeedcoreeFPGAIP based on Gen4 architecture, the new machine learning processor (MLP) module for artificial intelligence/machine learning (AI/ML) is a complete AI/ML calculation engine in addition to the cost-effectiveness of eFPGA and higher bandwidth . Each MLP includes a circular register file that utilizes temporal locality to reuse stored/cached weights or data, thereby improving performance by significantly reducing data movement for various calculations. MLP is tightly coupled with its neighboring MLP and larger memory cells to maximize processing performance and provide the most operations per second with the lowest power configuration. MLP supports fixed-point and floating-point formats (Bfloat16; 16-bit, half-precision; and block floating-point numbers). Users can dynamically select the best data accuracy according to the requirements of each application, so as to balance the accuracy and performance.

In the industrial Internet of Things market, data becomes the most critical part. Sensors are naturally becoming more important as front-end data collection and processing devices. Sensor fusion has gradually become the trend.

In this regard, Alok explained that although Achronix does not provide any sensor products, Achronix's most complete full-series FPGA product portfolio in the industry can support the needs of sensor fusion and related data communication. For example, in today's factories, the demand for optical inspection of precision parts has become more and more common due to the continuous improvement of accuracy. To human staff, this is a challenging and repetitive task. Therefore, optical inspection is increasingly handled by intelligent machines, and these intelligent machines require various FPGA products, including independent FPGA chips, SiP package chips based on FPGA die, and eFPGAIP.

There are two driving forces for the demand for FPGA products, especially eFPGAIP. On the one hand, sensor fusion in some Industrial Internet of Things (IIoT) applications may require an optimized system architecture, because sensor fusion at this time requires low power consumption and higher performance. An SoC or ASIC with integrated eFPGA will have excellent power efficiency, programmability, and unit cost. On the other hand, when the data from sensors is large, such as machine vision and lidar data, and the algorithm is constantly improving, front-end data processing or sensor fusion does require FPGA devices or eFPGA logic arrays to speed up the processing process.

In today and the future, data security has always been the most concerned and sensitive issue for enterprises and users. Security and security protection capabilities are important aspects of the Industrial Internet of Things (IIoT). Because any intrusion or data leakage may cause huge losses. Therefore, it is necessary to consider safety planning from the perspective of the entire life cycle, especially for fixed assets such as equipment in smart factories. Equipment suppliers must be able to support any custom or unique security algorithms they use in different customer factories, even if they all plan to use the same manufacturing equipment products. In the entire life cycle of the device, encryption, authentication or other information security methods in industrial Internet of Things applications should have a certain degree of flexibility and scalability.

For these reasons, reprogrammable devices like FPGAs have a long history of application in information security. Achronix has supported many users in this area, covering different levels of security. Therefore, for chip suppliers who develop SoCs for industrial IoT applications, they can use eFPGAIP like Speedcore and use some of their ASIC resources to develop security modules with flexibility and scalability. In addition, SpeedcoreeFPGAIP can provide custom blocks to speed up security algorithms to achieve hardware speed level security.

At the end of the interview, regarding the current ecological construction issues of the Industrial Internet of Things and the efforts made by Achronix, Alok believes that "as the Industrial Internet of Things (IIoT) ecosystem and standards are still evolving, solution providers should choose a solution A method of moving forward at different stages of development.

Developers can initially choose Achronix's independent FPGA chip to develop algorithms and quickly start projects. Later, they can obtain FPGA chip die and system-in-package (SiP) services from Achronix for manufacturing their own SiP multi-die chips, where the FPGA device is directly connected to the processor and/or other devices. Good internal connection and performance. When the demand for devices with edge computing capabilities is increasing and they need more computing power for a set of industrial IoT functions, they can use AchronixSpeedcoreGen4eFPGA semiconductor intellectual property (IP) to develop a system-on-chip (SoC) to meet today’s and future needs.”

If you want to know more, our website has product specifications for FPGA, you can go to ALLICDATA ELECTRONICS LIMITED to get more information