What are the characteristics and advantages of FPGA and how are they different from ASIC, DSP and ARM?

ASIC is the English abbreviation of Application Specific Integrated Circuit, which is an integrated circuit designed for a special purpose. ASIC design mainly includes full-custom (full-custom) design method and semi-custom (semi-custom) design method. Semi-custom design can be divided into gate array design, standard cell design, programmable logic design and so on. The full customization method is to design the chip independently by the designer according to the process, with the highest possible speed and the smallest possible area, and a fully satisfactory package.

1. Characteristics of ASIC, DSP and ARM

ASIC is the English abbreviation of Application Specific Integrated Circuit, which is an integrated circuit designed for a special purpose. ASIC design mainly includes full-custom (full-custom) design method and semi-custom (semi-custom) design method. Semi-custom design can be divided into gate array design, standard cell design, programmable logic design and so on. The full customization method is to design the chip independently by the designer according to the process, with the highest possible speed and the smallest possible area, and a fully satisfactory package. Although this method is highly flexible and can achieve optimal design performance, it takes a lot of time and manpower to perform manual layout and routing, and once the internal design needs to be modified, the layout of other parts will have to be affected. Therefore, its design cost is relatively high, and it is suitable for large-scale ASIC chip design, such as memory chip design and so on. In contrast, the semi-custom approach is a constrained design based on library components. The main purpose of constraints is to simplify the design, shorten the design cycle, and improve the yield of the chip. It makes more use of the EDA system to complete the work of layout and routing, which can greatly reduce the workload of design engineers, so it is more suitable for small-scale design production and experiments.

DSP (DigitalSingnalProcessor, digital signal processor) is a unique microprocessor with its own complete instruction system, a device that processes a large amount of information with digital signals. A digital signal processor chip includes a control unit, an arithmetic unit, various registers and a certain number of storage units, etc., and a number of memories can be connected to its periphery, and can communicate with a certain number of external devices, including software, The full functionality of the hardware is itself a microcomputer. The DSP adopts the Harvard structure design, that is, the data bus and the address bus are separated, so that the program and data are stored in two separate spaces, allowing the fetching and execution of instructions to overlap completely. That is to say, while executing the previous instruction, the next instruction can be fetched and decoded, which greatly improves the speed of the microprocessor. It also allows transfers between program space and data space because of increased device flexibility. Its working principle is to receive an analog signal, convert it into a digital signal of “0” or “1”, then modify, delete, strengthen the digital signal, and interpret the digital data back to analog data or actual environment format in other SoCs . It is not only programmable, but also has a real-time running speed of tens of millions of complex instruction programs per second, far exceeding that of general-purpose microprocessors, and is an increasingly important computer chip in the digital Electronic world. Its powerful data processing capability and high operating speed are the two most commendable features. Because of its strong computing power, fast speed, small size, and high flexibility in software programming, it provides an effective way to engage in various complex applications. Of course, compared with general-purpose microprocessors, other general-purpose functions of DSP Chips are relatively weak.

ARM (Advanced RISC Machines/microprocessor) embedded processor is a 32-bit high-performance, low-power RISC (Reduced Instruction Set Computing, reduced instruction set) chip, designed by the British ARM company, almost all major semiconductor manufacturers all produce general-purpose chips based on the ARM architecture, or embed ARM-related technologies in their dedicated chips, such as TI, Motorola, Intel, Atmel, Samsung, Philips, Altera, Nec, Sharp, NS and other companies have corresponding product. ARM is just a core. ARM does not produce chips by itself, and uses licensing to semiconductor manufacturers. At present, almost all semiconductor manufacturers in the world have purchased various ARM cores from ARM, equipped with a variety of different controllers (such as LCD controllers, SDRAM controllers, DMA controllers, etc.), peripherals, and interfaces to produce various ARM cores. An ARM core-based chip. At present, there are hundreds of various processor models based on the ARM core. In the domestic market, chips from ST, TI, NXP, Atmel, Samsung, OKI, Sharp, Hynix, Crystal and other manufacturers are common. Users can design their own application system by selecting the most suitable chip from many specific models according to their respective application requirements, from the aspects of performance and function. Because the ARM core adopts upward compatible instruction system, the software developed by users can be easily transplanted to higher ARM platforms. ARM microprocessors generally have the characteristics of small size, low power consumption, low cost, high performance and fast speed. At present, ARM chips are widely used in industrial control, wireless communication, network products, consumer electronic products, security products and other fields. Such as switches, routers, numerical control equipment, set-top boxes, STB and smart cards have adopted ARM technology, and in the future to achieve wider applications.

2. Features and advantages of FPGA

FPGA is the abbreviation of Field Programmable Gate Array (Field Programmable Gate Array) in English. It is the product of further development on the basis of programmable devices such as PAL, GAL, and PLD. kind. FPGA adopts a new concept of logic cell array LCA (Logic CellArray), which includes three parts: configurable logic module CLB (Configurable Logic Block), output input module IOB (InputOutputBlock) and internal connection (Interconnect). The user can reconfigure the logic modules and I/O modules inside the FPGA to implement the user’s logic. It also has the characteristics of static repeatable programming and dynamic in-system reconfiguration, so that the function of hardware can be modified by programming like software. As a semi-custom circuit in the field of application-specific integrated circuits (ASIC), FPGA not only solves the shortcomings of custom circuits, but also overcomes the shortcomings of the limited number of gate circuits of original programmable devices. It is no exaggeration to say that FPGA can complete the function of any digital device, from high-performance CPU to simple 74 circuits, all can be implemented by FPGA. FPGA is like a blank piece of paper or a stack of wood, engineers can freely design a digital system through the traditional schematic input method or hardware description language. Through software simulation, we can verify the correctness of the design in advance. After the PCB is completed, the online modification capability of the FPGA can also be used to modify the design at any time without changing the hardware circuit. Using FPGA to develop digital circuits can greatly shorten design time, reduce PCB area, and improve system reliability. FPGA is set by the program stored in the on-chip RAM to set its working state, so the on-chip RAM needs to be programmed when working. Users can use different programming methods according to different configuration modes. When powered on, the FPGA chip reads the data in the EPROM into the on-chip programming RAM. After the configuration is completed, the FPGA enters the working state. After a power failure, the FPGA recovers to a white slice, and the internal logic relationship disappears. Therefore, the FPGA can be used repeatedly. FPGA programming does not require a dedicated FPGA programmer, but only a general EPROM and PROM programmer. When you need to modify the FPGA function, you only need to change a piece of EPROM. In this way, the same piece of FPGA, with different programming data, can produce different circuit functions. Therefore, the use of FPGA is very flexible. It can be said that FPGA chips are one of the best choices for small batch systems to improve system integration and reliability. At present, there are many varieties of FPGA, including XC series of XILINX, TPC series of TI Company, FIEX series of ALTERA Company and so on.

3. What is the difference between them?

DSP is mainly used for calculation, such as encryption and decryption, modulation and demodulation, etc. The advantages are strong data processing capability and high running speed. ARM has a relatively strong transaction management function and can be used to run interfaces and applications. Its advantages are mainly reflected in control, while FPGA can be programmed with VHDL or verilogHDL, which has strong flexibility. programming and repetitive operations, so design development and verification can be fully performed. The advantages of FPGAs are even more apparent when there are minor changes to the circuit, and their field programming capabilities can extend the life of the product on the market, and this capability can be used for system upgrades or debugging.

Characterization of the performance of any signal processing device must include a measure of whether the device can perform the required function within a specified time. One of the most basic measurements of this type of evaluation is the measurement of the 1024-point Fast Fourier Transform (FFT) processing time. Consider a simple FIR filter with 16 taps. This filter requires 16 multiply-and-accumulate (MAC) operations per sample. Texas Instruments’ TMS320C6203DSP has a clock frequency of 300MHz, and in a reasonably optimized design, can complete about 400 million to 500 million MAC operations per second. This means that the FIR filtering of the C6203 family of devices has a maximum input rate of 31 million samples per second. But in the FPGA, all 16 MAC operations can be executed in parallel. For XILINX’s Virtex devices, 16-bit MAC operations require approximately 160 structurally resettable logic blocks (CLBs) to be configured, so a design implementation of 16 concurrent MAC operations would require approximately 2560 CLBs. The XCV300E easily implements the above configuration and allows the FIR filter to operate at an input sampling rate of 100 million samples per second.

At present, the development of wireless communication technology is very rapid. One of the theoretical foundations of the development of wireless communication technology is software radio technology, and digital signal processing technology is undoubtedly the basis for realizing software radio technology. On the one hand, wireless communication is developing towards the integration of voice and data. On the other hand, there is an increasing need for integrated mobile technology in handheld PDA products. This requirement presents serious challenges to FPGA chips used in wireless communications, the three most important of which are power consumption, performance and cost. In order to meet the development needs of wireless communication, the concept, technology and chip of FPGA System On a Chip (SOC) came into being. Using system-on-a-chip technology to integrate as many functions as possible on an FPGA chip, it has the characteristics of high speed and low power consumption in terms of performance, which is not only low in price, but also reduces complexity and is easy to use.

In fact, the capabilities of FPGA devices have long gone beyond traditional glue logic capabilities. With the mutual integration of various technologies, in order to meet the needs of computing speed, complexity, and reduce the difficulty of development at the same time, in the field of digital signal processing and embedded technology, the configuration mode of FPGA plus CPU has surfaced, and gradually become the standard configuration mode.

ARM has relatively strong transaction management functions, which can be used to run interfaces and applications. Its advantages are mainly reflected in control, while DSP is mainly used for calculations, such as encryption and decryption, modulation and demodulation, etc. The advantages are powerful Data processing capability and high operating speed. FPGAs can be programmed in VHDL or verilogHDL, which is highly flexible and can be fully designed for development and verification due to the ability to program, debug, reprogram, and repeat operations. The advantages of FPGAs are even more apparent when there are minor changes to the circuit, and their field programming capabilities can extend the life of the product on the market, and this capability can be used for system upgrades or debugging.

There are nothing more than a few kinds of embedded in a broad sense: the traditional 51, AVR, and PIC are called embedded microcontrollers; ARM is an embedded microprocessor; DSP; FPGA.

Objectively speaking, DSP needs more work than ARM, and ARM and FPGA are similar.

DSP has become popular due to the unprecedented development in the field of digital processing and communication. It has a wide range of applications, ranging from MP3 cameras to controllers in military products.

FPGA brothers generally do ASIC, sopc. ARM is not much stronger than a single chip, but its uniqueness lies in the declining price and improved performance.

The Links:   LQ084V3DG02 7D50D-050EHR