Embedded System Architecture
All devices with digital interfaces, such as watches, microwave ovens, VCRs, and automobiles, use embedded systems, and some embedded systems also contain operating systems, but most embedded systems implement the entire control logic by a single program. Here is what I have organized about embedded system architecture, welcome to refer to it!
Embedded system architecture:
The composition of an embedded system contains a hardware layer, an intermediate layer, a system software layer and an application software layer.
1, hardware layer: embedded microprocessor, memory, general-purpose device interface and I / O interface.
Embedded core module = microprocessor + power supply circuit + clock circuit + memory
Cache: located between the main memory and the embedded microprocessor core, stored in the recent period of time the microprocessor used the most program code and data. Its main goal is to reduce the memory access bottleneck caused by the memory to the microprocessor core and make processing faster.
2, the middle layer (also known as the hardware abstraction layer HAL or board support package BSP).
It separates the upper system software from the underlying hardware, so that the upper system software developer does not need to relate to the specifics of the underlying hardware, and develops according to the interfaces provided by the BSP layer. there are two characteristics of the BSP: hardware relevance and operating system relevance.
The design of a complete BSP requires the completion of two parts of the work:
A, the hardware initialization of the embedded system and the BSP function.
Chip-level initialization: a purely hardware initialization process that gradually sets the embedded microprocessor from the default state of power-up to the operating state required by the system.
Board-level initialization: an initialization process that includes both hardware and software components, and establishes the hardware and software operating environments for subsequent system initialization and applications.
System-level initialization: A software-based initialization process to initialize the operating system.
B. Design hardware-related device drivers.
3. System software layer: consists of RTOS, file system, GUI, network system, and general-purpose component modules.
RTOS is the foundation and development platform for embedded application software.
4. Application software: consists of applications developed based on the real-time system.
Introduction of Embedded Chip Architecture
1. Embedded Microprocessor Unit (MPU)
Embedded microprocessor is evolved from the CPU in general-purpose computers. It is characterized by a 32-bit processor or more, with high performance, and of course, its price is correspondingly high. However, unlike computer processors, in the actual embedded applications, only retain and embedded applications closely related to the functional hardware, remove other redundant functional parts, so that the lowest power consumption and resources to achieve the special requirements of embedded applications. Compared with industrial control computers, embedded microprocessors have the advantages of small size, light weight, low cost and high reliability. Currently the main types of embedded processors are Am186/88, 386EX, SC-400, Power PC, 68000, MIPS, ARM/ StrongARM series. Among them, Arm/ StrongArm is an embedded microprocessor developed specifically for handheld devices, which belongs to the mid-range price point.
Power PC:
Developed jointly by IBM, Apple, and Motorola, and manufactured a multi-processor computer based on PowerPC.The PowerPC architecture is characterized by good scalability, convenience, and flexibility. The following products mainly use Power PC microprocessors
Apple: Power Macintosh series, PowerBook series (products after 1995), iBook series, iMac series (products before 2005), eMac series products.
Nintendo: GameCube and Wii.
Sony: PlayStation 3.
MIPS:
MIPS is a RISC processor that is very popular in the world. what does MIPS mean? Microprocessor without internal interlocking pipelined stages? (Microprocessor without interlocked piped stages), its mechanism is to try to use software approaches to avoid data-related problems in the pipeline. It was first developed in the early 80's by a research group led by Prof. Hennessy of Stanford University. the R series of MIPS is the microprocessor for RISC industrial products developed on this basis. These series of products for many computer companies to form a variety of workstations and computer systems. MIPS Technologies Inc. is a well-known chip design company in the United States, which uses a compact instruction system computing structure (RISC) to design chips. MIPS is one of the earliest commercial RISC architecture chips, and the new architecture integrates all of the original MIPS instruction set and adds many more powerful features. MIPS processors were a hot topic in RISC CPU design in the mid-1980's. MIPS was the best selling RISC CPU, and MIPS products could be seen for sale anywhere from Sony and Nintendo game consoles to Cisco routers and SGI supercomputers. Currently with the RISC architecture being competed with by x86 chips, MIPS is likely to be the only one of the original RISC CPU designs to make a profit in this century. MIPS has a relatively low license fee compared to Intel, and has been adopted by most chip makers except Intel.
2. Embedded microcontroller (Microcontroller Unit, MCU)
Embedded microcontrollers are typically represented by microcontrollers, from the late 70's microcontrollers to today, although it has been more than 20 years of history, but this 8-bit electronic devices are still in the embedded devices still have a very wide range of applications. The microcontroller chip internally integrates ROM/EPROM, RAM, bus, bus logic, timer/counter, watchdog, I/O, serial port, pulse width modulation output, A/D, D/A, Flash RAM, EEPROM, and other necessary functions and peripherals. Compared with embedded microprocessors, the most important feature of microcontrollers is monolithic and greatly reduced in size, which leads to a reduction in power consumption and cost, and an increase in reliability. Microcontrollers are currently the mainstream of the embedded systems industry. Microcontrollers are generally richer in on-chip peripheral resources and are suitable for control, hence the name microcontroller. Due to the MCU low price, excellent features, so have the most varieties and number of more representative, including 8051, MCS-251, MCS-96/196/296, P51XA, C166/167, 68K series and MCU 8XC930/931, C540, C541, and there is support for I2C, CAN-Bus, LCD and many specialized MCUs and compatible series. MCU currently accounts for about 70% of the market share of embedded systems. Recently Atmel produced Avr microcontroller due to its integrated FPGA and other devices, so it has a high cost-effective, is bound to promote the microcontroller to obtain higher development.
3. Embedded DSP processor (Embedded Digital Signal Processor, EDSP)
DSP processor is a processor dedicated to signal processing, its system structure and instruction algorithms in the special design, with high compilation efficiency and instruction execution speed. In the digital filtering, FFT, spectral analysis and other instruments DSP has gained large-scale applications. the theoretical algorithms of DSP have appeared in the 70's, but due to the special DSP processor has not yet appeared, so the theoretical algorithms can only be realized through the MPU and so on by the discrete components. the MPU's lower processing speed can not meet the algorithmic requirements of the DSP, and its application areas are only limited to some of the cutting-edge high-tech fields. Its application areas are only limited to some cutting-edge high-tech fields. With the development of large-scale integrated circuit technology, the world's first DSP chip was born in 1982. Its operation speed is dozens of times faster than MPU, and it is widely used in speech synthesis and coding decoder. To the mid-80s, with the progress and development of CMOS technology, the second generation of DSP chips based on CMOS process came into being, its storage capacity and computing speed have been exponentially improved, and become the basis of voice processing, image hardware processing technology. By the late 80's, the DSP computing speed is further improved, the application field is also expanded from the above scope to communications and computers. 90's, the DSP development to the fifth generation of products, integration is higher, the use of the scope is also more extensive. Currently the most widely used is TI's TMS320C2000/C5000 series, in addition, such as Intel's MCS-296 and Siemens' TriCore also has its own scope of application. Depending on the chip manufacturer using different IP cores, they can be divided into the following categories:
StarCore
Freescale
Freescale digital signal processors with StarCore technology are the industry's highest-performance programmable devices for the baseband, aerospace, defense, medical, and test and measurement markets. We have designed the StarCore DSP family to provide a comprehensive, flexible and scalable solution to help our customers accelerate time-to-market. the StarCore DSPs feature low power consumption and low cost, making them an ideal solution for next-generation designs. Enabling a smarter world through next-generation innovation. The main multi-core chips include: MSC8122: Quad-core 16-bit DSP with Ethernet, MSC8126: Quad-core 16-bit DSP with Ethernet, TCOP and VCOP, MSC8144: Quad-core DSP, MSC8152: High-performance Dual-core DSP, MSC8154: High-performance Quad-core DSP, MSC8154E: High-performance Quad-core DSP with security, MSC8154E: High-performance Quad-core DSP with security, MSC8154E: High-performance Quad-core DSP with security, and MSC8155: High-performance DSP with security. High-Performance Quad-Core DSP, MSC8156: High-Performance Hexa-Core DSP, MSC8156E: High-Performance Hexa-Core DSP with Security, MSC8157: MSC8157 Broadband Wireless Access DSP, MSC8158: MSC8158 Broadband Wireless Access DSP, MSC8252: High-Performance Dual-Core DSP, MSC8254: High-Performance MSC8254: High-performance quad-core DSP, MSC8256: High-performance hexa-core DSP. Single-core chips include: MSC8151: high-performance single-core DSP, MSC8251: high-performance single-core DSP.
4. Embedded System On Chip (System On Chip)
SoC pursues the integration of the product system of the largest inclusive device, is currently one of the hot topics in the field of embedded applications. The biggest feature of SOC is that it successfully realizes the seamless combination of hardware and software, and directly embeds the code module of operating system in the processor chip. Moreover, SOCs are highly comprehensive, utilizing hardware description languages such as VHDL to realize a complex system within a silicon chip. Users do not need to draw huge and complex circuit boards like the traditional system design, a little bit of connection soldering, only need to use the precise language, integrated timing design directly in the device library to call a variety of general-purpose processor standards, and then through the simulation can be directly delivered to the chip manufacturer for production. As the vast majority of system components are within the system, the entire system is particularly concise, not only reduces the size of the system and power consumption, but also improves the reliability of the system, and improve the design and production efficiency. Since SOCs are often specialized, most of them are not known to users, and a typical SOC product is Philips' Smart XA. A few general-purpose series, such as Siemens' TriCore, Motorola's M-Core, certain ARM series devices, and the Neuron chip jointly developed by Echelon and Motorola, are also available. etc. It is expected that in the near future, some big chip companies will launch mature SOC chips that can occupy most of the market, and knock out competitors in one fell swoop. SOC chips will also play an important role in the application areas of sound, image, video, network and system logic.
;