RISC (Reduced Instruction Set Computer) is a microprocessor that executes a small number of instruction types, originating from the MIPS mainframe in the 1980s (i.e., RISC machines), collectively referred to as RISC processors. This allows it to execute operations at a faster speed (millions of instructions per second, or MIPS). Each type of instruction executed by a computer requires additional transistors and circuit components; the larger the instruction set, the more complex the microprocessor becomes, and the slower the execution of operations.

• Performance Feature One: With a simplified instruction set, pipelining, and frequently used instructions can be executed with hardware;

• Performance Feature Two: A large number of registers are used, allowing most instruction operations to be performed between registers, improving processing speed;

• Performance Feature Three: A three-level storage structure consisting of cache, main memory, and external storage separates the execution of data retrieval and storage instructions, enabling the processor to complete as much work as possible without slowing down due to memory access.

Among them, ARM/MIPS/PowerPC are all based on RISC architecture; x86 is based on Complex Instruction Set architecture, with Atom being a simplified version of the x86 instruction set. According to various news reports, the current support for various processors by Android is as follows:

• ARM+Android has the earliest and most complete support, mainly in the smartphone, netbook, and smart device markets;
• X86+Android has relatively complete development, with Atom+Android netbooks;
• Atom+Android and Atom+Windows 7 dual systems;
• MIPS+Android is currently in the process of porting and improvement;
• PowerPC+Android is also currently in the process of porting and improvement.

ARM Series Processors

ARM architecture, formerly known as Advanced RISC Machine (earlier known as Acorn RISC Machine), is a 32-bit RISC processor architecture widely used in many embedded system designs. Due to its energy-saving characteristics, ARM processors are very suitable for mobile communications, aligning with its primary design goal of low power consumption.

Today, the ARM family accounts for 75% of all 32-bit embedded processors, making it one of the most widely used 32-bit architectures worldwide. ARM processors can be found in many consumer electronic products, from portable devices (PDAs, mobile phones, multimedia players, handheld gaming consoles, and computers) to computer peripherals (hard drives, desktop routers), and even in military facilities such as missile onboard computers. Additionally, there are several derivative products based on ARM design, including Marvell’s XScale architecture and Texas Instruments’ OMAP series.

• Advantages: Low cost; low power consumption;
• ARM Licensing Model: ARM does not manufacture or sell CPUs based on its own designs but licenses its processor architecture to interested manufacturers.
• Manufacturers: TI (Texas Instruments)/Samsung/Freescale/Marvell/Nvidia

ARM offers a variety of licensing terms, including pricing and distribution. For licensees, ARM provides integration hardware descriptions of ARM cores, complete software development tools (compilers, debuggers, SDKs), and sales rights for silicon chips containing ARM CPUs. For fabless licensees, they typically aim to integrate ARM cores into their own chip designs, usually only requiring a production-ready intellectual property (IP Core) certification.

For these customers, ARM releases the gate-level schematics of the selected ARM cores, along with abstract simulation models and testing programs to assist with design integration and verification. More demanding customers, including integrated device manufacturers (IDMs) and foundries, opt for synthesizable RTL (Register Transfer Level, such as Verilog) forms to obtain processor IP rights.

With synthesizable RTL, customers can perform architectural optimizations and enhancements. This method allows designers to achieve additional design goals (such as high oscillation frequency, low power consumption, instruction set extensions, etc.) without being limited by unmodifiable schematics. Although ARM does not grant licensees the right to resell the ARM architecture itself, licensees can freely sell products (such as chip components, evaluation boards, complete systems, etc.).

Commercial foundries are a special case because they not only grant the right to sell silicon products containing ARM cores but also typically retain the right to reproduce ARM cores for other customers.

x86 Series/Atom Processors

x86 or 80×86 is a generic term for a microprocessor architecture initially developed and manufactured by Intel. The x86 architecture is significantly variable in instruction length and is categorized as CISC (Complex Instruction Set Computer).

Intel Atom (Chinese: 凌动, codename: Silverthorne) is a series of ultra-low-voltage processors from Intel. The processors are manufactured using a 45nm process and integrate 47 million transistors. The L2 cache is 512KB and supports the SSE3 instruction set and VT virtualization technology (on some models).

Currently, the Atom processor series includes six models, all belonging to the Z500 series: Z500, Z510, Z520, Z530, Z540, and Z550. The lowest-end Z500 has a core frequency of 800MHz and an FSB of 400MHz, while the highest-speed Z550 has a core frequency of 2.0GHz and an FSB of 533MHz.

Starting from the Z520, all processors support hyper-threading technology, but only increase power consumption by less than 10%. The dual-core version is the N series, still using the 945GC chipset. The dual-core version will still support hyper-threading technology, so the system will display four logical processors. The two cores in this version are not locally designed but simply encapsulate two single cores together.

MIPS Series Processors

MIPS is a very popular RISC processor worldwide. MIPS stands for “Microprocessor without interlocked piped stages,” and its mechanism aims to avoid data dependency issues in the pipeline as much as possible using software methods.

It was originally developed in the early 1980s by a research group led by Professor Hennessy at Stanford University. The R series of MIPS Corporation was developed based on this RISC industrial product microprocessor. These series products have been adopted by many computer companies to form various workstations and computer systems.

MIPS Technology Company is a well-known chip design company in the United States, which designs chips using the RISC architecture. Compared to the complex instruction set architecture (CISC) used by Intel, RISC has advantages such as simpler design, shorter design cycles, and the ability to apply more advanced technologies to develop faster next-generation processors.

MIPS was one of the earliest commercial RISC architecture chips, and the new architecture integrates all original MIPS instruction sets and adds many more powerful features. MIPS itself only designs CPUs and then licenses the design to clients, allowing them to manufacture high-performance CPUs.

• 1984: MIPS Computer Company was established and began designing RISC processors;
• 1986: Launched the R2000 processor.
• 1992: SGI acquired MIPS Computer Company.
• 1988: Launched the R3000 processor.
• 1991: Launched the first commercial 64-bit microprocessor, the R4000; subsequently launched the R8000 (in 1994), R10000 (in 1996), and R12000 (in 1997).
• 1998: MIPS separated from SGI, becoming MIPS Technology Company; thereafter, MIPS shifted its focus to embedded systems; in 1998, MIPS Technology went public on the NASDAQ.
• 1999: MIPS announced the MIPS32 and MIPS64 architecture standards, laying the foundation for future MIPS processor development. The new architecture integrated all original MIPS instruction sets and added many more powerful features. MIPS subsequently developed high-performance, low-power 32-bit processor cores (core) MIPS324Kc and high-performance 64-bit processor cores MIPS64 5Kc.
• 2000: MIPS announced versions for MIPS32 4Kc and 64-bit MIPS 64 20Kc processor cores.
• August 16, 2007: MIPS Technology announced that the Loongson processor from the Institute of Computing Technology, Chinese Academy of Sciences, obtained all patents and bus/instruction set licenses for its processor IP.
• December 20, 2007: MIPS Technology announced that Yangzhi Technology had obtained authorization for its customizable system-on-chip (SoC) core “MIPS32 24KEc Pro” designed for advanced multimedia.

PowerPC Series Processors

PowerPC is a central processing unit (CPU) based on a RISC architecture, with its basic design originating from IBM’s IBM PowerPC 601 microprocessor POWER architecture. In the 1990s, IBM, Apple, and Motorola successfully developed PowerPC chips and manufactured multiprocessor computers based on PowerPC.PowerPC architecture is characterized by good scalability and flexibility.

PowerPC processors have a wide range of implementations, from high-end server CPUs like Power4 to the embedded CPU market (Nintendo Gamecube uses PowerPC).

PowerPC processors exhibit very strong embedded performance due to their excellent performance, low energy consumption, and low heat generation. Besides integrated I/O such as serial and Ethernet controllers, these embedded processors are significantly different from desktop CPUs.

Real-Time DSP Architecture

DSP is a type of microprocessor that has extremely high processing speed because the applications of such processors require very high real-time performance. For example, when making a phone call via mobile phones, if the processing speed is not fast enough, one must wait for the other party to stop talking before being able to speak. If both parties talk simultaneously, due to insufficient digital signal processing speed, the signal connection must be terminated. Before the emergence of DSP, digital signal processing could only rely on MPUs (microprocessors). However, the lower processing speed of MPUs could not meet the demands of high-speed real-time performance.

Thus, it was not until the 1970s that the theory and algorithmic foundation for DSP were proposed. At that time, DSP merely existed in textbooks, and even the DSP systems developed were composed of discrete components, with their application limited to military and aerospace sectors.

The 1990s saw the fastest development of DSP, with the emergence of fourth and fifth-generation DSP devices. Today’s DSP belongs to the fifth generation, which has higher system integration, integrating the DSP core and peripheral components onto a single chip.This highly integrated DSP chip not only excels in communications and computing fields but is also gradually penetrating into everyday consumer domains.

Source: CSDN

Scan to Subscribe to the “Military-Civil Fusion” Magazine↓↓↓

Important Notice: Scan to subscribe to the magazine, invoices are issued by the handling post office.