Initially, Acorn intended to use Motorola’s 16-bit chips but found them too slow and expensive. “A machine costing £500 cannot use a CPU priced at £100!” They turned to Intel for the design of the 80286 chip but were refused, forcing them to develop their own.

In 1985, Roger Wilson and Steve Furber designed their first generation 32-bit, 6M Hz processor, which they used to create a computer based on the RISC instruction set, abbreviated as ARM (Acorn RISC Machine). This is how the name ARM came about.

The full name of RISC is “Reduced Instruction Set Computer,” which supports simpler instructions, resulting in low power consumption and low cost, making it particularly suitable for mobile devices. A typical early device using ARM chips was Apple’s Newton PDA.

By the late 1980s, ARM quickly developed into Acorn’s desktop products, forming the foundation of computer education in the UK.

On November 27, 1990, Acorn officially restructured into ARM Computer Company. Apple invested £1.5 million, chip manufacturer VLSI invested £250,000, and Acorn itself contributed £1.5 million in intellectual property and 12 engineers. The company’s office was very simple, just a barn. In the 1990s, ARM’s 32-bit embedded RISC processors expanded globally, occupying a leading position in low-power, low-cost, and high-performance embedded system applications. ARM does not produce or sell chips; it only sells chip technology licenses.

MCU is essentially a microcontroller, integrating the CPU, RAM, ROM, timer, and various I/O interfaces on a single chip, forming a chip-level computer.

Leading manufacturers of MCUs include Renesas, NXP, Nuvoton, Microchip, STMicroelectronics, Atmel, Infineon, Texas Instruments, Toshiba, Samsung, Cypress, ADI, Qualcomm, Fujitsu, AMD, Holtek, and many others.

DSP (Digital Signal Processing) is the theory and technology of processing signals through numerical computation. It also refers to Digital Signal Processor, a chip that is an integrated dedicated computer, about the size of a coin.

FPGA (Field-Programmable Gate Array) is a product developed further based on PAL, GAL, CPLD, and other programmable devices. It appears as a semi-custom circuit in the ASIC field, solving the shortcomings of custom circuits and overcoming the limitations of existing programmable devices.

Leading manufacturers of FPGAs include Altera (acquired by Intel), Xilinx, Lattice (acquired by CanyonBridge), Microsemi, Cypress, TI, Shanghai Fudan Microelectronics, Guangdong Gaoyun, Tongfang Guoxin, Xi’an Zhiduo Crystal, China Electronics, Chengdu Huamai, Shenzhen Guowei, Aogexin, and others.

The definition of SoC varies widely, making it difficult to provide an accurate definition due to its rich connotation and broad application range. Generally speaking, SoC stands for System on Chip, meaning it is a product, a dedicated integrated circuit containing a complete system with embedded software. It is also a technology used to implement the entire process from defining system functions to software/hardware partitioning and design completion.

1. Architecture

ARM: The architecture uses a 32-bit RISC processor architecture. Since ARM9, ARM has adopted the Harvard architecture, which separates instructions and data into their own independent memory structures, significantly improving processing capability.

ARM often uses pipelining technology, which shortens program execution time by allowing multiple power components to work in parallel, enabling instructions to flow through multiple pipelines, thus improving processor efficiency and throughput. Currently, ARM7 uses a typical three-stage pipeline, ARM9 employs a five-stage pipeline, while ARM11 utilizes a seven-stage pipeline, and ARM Cortex-A9 even uses a variable pipeline structure (supporting 8-11 stages). ARM Cortex-A9 supports up to four cores, marking the first time multi-core technology is supported in the ARM series processors. The diagram below illustrates the internal structure of ARM Cortex-A9.

MCU: Most are based on the Von Neumann architecture, which clearly defines the four essential components of embedded systems: a central processing core, program memory (ROM or flash), data memory (RAM), one or more timers/counters, and input/output ports for communication with peripheral devices and extended resources—all integrated into a single integrated circuit chip. Early MCUs used CISC instruction sets, later replaced by RISC. In terms of bus width, MCUs cover 4-bit, 8-bit, 16-bit, and 32-bit architectures, widely applied.

DSP: Also known as Digital Signal Processor, it is a microprocessor specifically designed for real-time digital signal processing. It adopts a Harvard architecture and also uses pipelining technology. Additionally, DSP can operate as a direct memory access device within a host environment and supports data from analog-to-digital converters (ADC), ultimately outputting data converted to analog signals by digital-to-analog converters (DAC), supporting a certain level of parallel processing.

FPGA: FPGA stands for Field Programmable Gate Array, which is a product developed further based on PAL, GAL, PLD, and other programmable devices, and is the highest integrated type in ASIC. FPGA employs a new concept of Logic Cell Array (LCA) that includes configurable logic blocks (CLB), input/output blocks (IOB), and interconnects. Users can reconfigure the internal logic and I/O modules of the FPGA to implement their logic. It also features static reprogrammability and dynamic in-system reconfiguration, allowing hardware functions to be modified through programming like software. FPGA differs from DSP, ARM, and MCU primarily in its parallel processing capability, which allows for significant speed improvements in complex calculations.

SoC: A system on chip integrates a computer or other electronic systems into a single chip integrated circuit. SoCs can process digital, analog, mixed signals, or even higher frequency signals. SoCs are often applied in embedded systems. The integration scale of SoCs is large, typically reaching millions to tens of millions of gates. SoCs are relatively flexible, allowing integration of ARM architecture processors with dedicated peripheral chips to form a system. Some ARM processors like Hisi-3507, hisi3516, etc., are SoC systems, especially application processors that integrate many peripheral devices, providing strong support for executing more complex tasks and applications.

2. Power Consumption

ARM: The primary reason for ARM’s great success in the mobile market is its low power consumption. It is well known that electronic products in the mobile market are very sensitive to processor power consumption. In the past, processor power consumption on PC platforms ranged from tens to hundreds of watts, which is unimaginable on mobile platforms. ARM consumes only a few hundred mW at a frequency of 1GHz, making it well-suited for mobile electronic products.

DSP: DSP holds a significant market share in digital signal processing, competing with FPGA. One advantage of DSP over FPGA is its relatively low power consumption. DSP manufacturers improve processor frequency and work to reduce power consumption to maintain market share, as FPGA seems to have an advantage in high-performance digital processing markets. From the DSP perspective, TI’s DSP processors are the best in terms of power consumption and performance, as they are lower in cost and power consumption compared to other DSP manufacturers.

MCU: MCUs have the longest history, with various manufacturers having their own architectures and instruction sets. In terms of low power consumption, TI’s MSP430 series MCUs perform relatively well.

FPGA: Due to its internal structure, FPGA has relatively high power consumption and generates significant heat, which is a disadvantage. However, this is unavoidable as it supports high-performance concurrent computing digital circuits, and the logic gates are mostly designed with standard width-to-length ratios, making it impossible to compete with ASICs and other dedicated processors in terms of power consumption.

SoC: Due to the flexibility of SoCs, which integrate multiple components into a tiny chip to form a system, SoC systems have power consumption advantages over systems made up of MCUs and other processors. Additionally, SoC chips can optimize system power consumption by combining technology and circuit design factors at the layout level, resulting in lower power consumption and smaller footprint compared to systems built with current peripheral PCB layouts.

3. Speed

As market application demands increase, ARM manufacturers have optimized to enhance their frequency and performance, advancing from 100MHz to an astonishing 2.3GHz.

The fastest current DSP can reach a frequency of 1.2GHz. However, it is not solely the frequency that determines performance; DSP can complete one multiplication and one addition in a single clock cycle, a capability that general ARM processors typically lack, making the DSP’s advantages particularly evident in computation. As a result, TI has combined the strengths of ARM and DSP to produce the Da Vinci heterogeneous chip, which falls under the SoC category.

MCUs, as low-end application processors, have frequencies ranging from several MHz to tens of MHz.

FPGAs can reach clock frequencies of several GHz, even exceeding 10GHz, though at a high cost. Comparing FPGA with ARM, DSP, etc., solely on frequency is not very meaningful, as the parallel computing capability far exceeds that of general-purpose processors using serial computation by dozens of times. For instance, implementing the same filtering algorithm on a 100MHz FPGA is much faster than on a 1GHz ARM.

4. Applications and Market

ARM processors are mainly divided into three series: A series, R series, M series, where the A series focuses on consumer electronics applications and is widely used.

• Computing: Netbooks, smart books, input devices, e-readers, thin clients

• Mobile: Smartphones, feature phones

• Digital Appliances: Set-top boxes, digital TVs, Blu-ray players, game consoles

• Automotive: Infotainment, navigation

• Enterprise: Laser printers, routers, wireless base stations, VOIP phones and devices

• Wireless Infrastructure: Web 2.0, wireless base stations, switches, servers

The R series processors mainly target applications requiring high real-time performance, such as aerospace and automotive electronics, with advantages in reliability, availability, fault tolerance, and real-time response.

The M series processors mainly target lower-end applications, initially aimed at replacing existing MCUs on the market:

ARM Cortex-M0

ARM Cortex-M0+

ARM Cortex-M3

ARM Cortex-M4

“8/16 bit” applications

“16/32 bit” applications

Low cost and simplicity

Low cost, optimal energy efficiency

High performance, general-purpose

Effective digital signal control

DSP primarily targets applications requiring high computational power, such as video image processing, intelligent robotics, digital wireless, broadband access, digital audio, high-resolution imaging, and digital motor control.

MCUs are the most widely used, benefiting from cost control, enabling them to establish themselves in many applications that do not require high computational power. It is believed that key growth drivers for the MCU market in the coming years will come from green energy, smart electronic devices, smart grids, and upgrades of electronic products such as automotive electronics.

SoC applications are also very broad, mainly because the architecture adopted by existing mainstream ARM chips is a form of SoC architecture, and SoC is a relatively broad concept. Currently, many ARM and DSP chips are beginning to adopt SoC methods to integrate multiple devices into processors to form complex systems.

5. Development Costs

• ARM primarily runs on operating systems like LINUX, ANDROID, WINCE, and is relatively more challenging to get started with compared to MCUs and DSPs, requiring developers to have a deep understanding of operating systems; from a cost perspective, ARM’s single-chip cost is higher than that of MCUs, primarily applied in more complex systems.

• MCUs are the easiest to get started with, quick to learn, and have low development costs, making them widely used in low-end markets.

• DSPs are relatively easy to get started with but have higher single-chip costs, mainly applied in applications requiring high computational power. DSPs can also run operating systems, making them suitable for multitasking applications.

• FPGA development is more challenging and has a longer development cycle, and its single-chip cost is also high.

Example: SOBEL Operator (Horizontal Edge)

Normally, performing such an operator requires 9 multiplications and 8 additions. This computation is straightforward for FPGA and DSP but can be challenging for ARM and MCU due to their weaker parallel capabilities, especially when processing larger images, such as 1280P.

However, this operator is quite easy to optimize. For example, the pixel points at positions 1 and -1 can be directly added, and similarly for the last row, while the points 2 and -2 in the middle row can also be added and then shifted to complete the operation. This reduces the original 9 multiplications and 8 additions to three additions and one shift (the shift operation can usually be completed in a single clock cycle on most processors).

1. An electronic magazine, why not get a copy!

2. Baidu’s IoT chip claims to be free for licensing; is this possible?

3. Book recommendation | March is full of great books~

4. Four levels and six principles analyzing IoT security architecture, everything you thought and didn’t think of is here!

5. These basic knowledge of embedded Linux systems you should know!

6. This is how ARM appears in the eyes of finance professionals!

Disclaimer: This article is a network reprint, and the copyright belongs to the original author. If there are copyright issues, please contact us, and we will confirm the copyright based on the copyright certificate you provide and pay the remuneration or delete the content.