The range of FPGA applications is very wide, due to the versatility and flexibility of these devices; being the main application of FPGAs digital signal processing (DSP), communications, data processing, etc. The choice of an FPGA for signal processing applications is due to its high operating frequency, its parallel processing capacity, and its low price compared to ASICs. In general, the logic of a CPLD is insufficient to perform such processing.
The following graph shows the indicative distribution of FPGA applications in 2008. This distribution changes slightly over the years, although communications and data centers are and will be, in future years (thanks to the arrival of 5G), the main application demanding FPGA, along with data acquisition and control within several industries and applications.
A wide variety of applications are derived from FPGAs, some of which are listed below:
Communications, Software Defined Radio (SDR): In order to be used in Hard Real-Time environment, Software Defined Radio/Network and others complex algorithms like FFT have to be implemented into FPGA. Traditionally, a radio consisted of an antenna, responsible for receiving and sending a signal, and hardware responsible for processing that signal, filtering it, modifying its frequency, etc. This hardware could not significantly modify the functionality for which it was designed. Today much of this functionality is transferred to an electronic device, which is often an FPGA, and the analog part can be limited to an antenna and ADC and DAC converters. The main advantage of this type of radio is that its functionality is defined by the design of the software, so that its modification or update is simple and does not require the replacement of any hardware element. In some cases, ADC y DAC are included inside of FPGA chip too.
Artificial vision systems: In today's world there are more and more devices that have an artificial vision system. Examples of this are video surveillance cameras, robots, etc. Many of these devices require a system to know their position, recognize objects in their surroundings, recognize people's faces, and be able to act and interact with them in the appropriate way. This feature requires handling very high volumes of images, treating these images to detect objects, recognize faces, etc., in the vast majority of cases in real time.
Medical imaging systems: FPGAs are being used more and more frequently for the treatment of biomedical images obtained through PET processes, CT scan, X-rays, three-dimensional images, etc. These medical vision systems increasingly require more resolution and greater processing capacity, even many need to be able to be developed in real time, so the benefits offered by frequency FPGAs and parallel processing adapt very well to these needs.
Encryption and encryption, cryptography: massive computing parallelism, capability to configure the computational units to the bit-width needed and low latency are the main reasons for which FPGAs are used in the field of both encrypting/decrypting and Post-quantum cryptography.
Radio astronomy: Radio astronomy is the science that is in charge of studying the phenomena that occur in space by capturing the electromagnetic radiation from it. Similar to previous applications, it requires the processing of a large amount of information in which the FPGA can bring its full potential.
Speech recognition: The recognition of the person who speaks is a technique used in security, information retrieval systems, etc., and it is expected that in the future its scope of application will increase. In this context, the FPGA is very efficient when it comes to comparing a person's voice with previously stored patterns.
Aeronautics and defense: In addition to those previously mentioned, there are a multitude of aeronautical and defense applications that use FPGAs due to the good characteristics they offer.
Data Center / Cloud: The internet of things (IoT), and big data in general, are generating an exponential growth of the data acquired and processed, which together with the computational analysis of the same through deep learning techniques of multiple operations parallel / concurrent, are leading to a high demand for low-latency, flexible and secure computational capacity that cannot be resolved by adding more servers / blades, due to the crazy increase in cost in space, consumption and money. Under this panorama, the doors of the world of the Data Center are being opened in a massive way to FPGAs, due to their capacity for computational acceleration, configuration flexibility and the security that the hardware guarantees against the software.
Control engineering: ability to implement FPGA-based controller as a hard Real-Time system who can react to any time critical changes in the controlling environment within a calculated deterministic time. Another aspect is the possibility to reconfigure the FPGA during run-time, which allows an adaptation to a changing environment by choosing the best fitting controller algorithm, while reducing the necessary logic resources and the deployment time.
November 30, 2020
However, FPGA-based implementations and developments are not an easy task, and you may not always have the experience, resources, or time to fulfill your planning.
Our team of engineers specialized in FPGAs and SoC / MPSoC offers you experience and services to develop your product, with the mission of helping you reduce your development cycles. At GENERA Technologies we have a long history helping our clients to convert the signal acquired by the sensor into processed, reliabilted and real-time information in the shortest latency in a wide range of applications and sectors. Contac us.