In today’s era of electronic products flooding the market, relying solely on brand or appearance is no longer sufficient to distinguish the quality of products. The built-in processors have naturally become one of the standards for determining whether a product is high-end. So today, let’s take a closer look at the mainstream RAM processors in electronic products in recent years.
Before that, let’s briefly familiarize ourselves with processor architecture. The so-called processor architecture is a specification set by CPU manufacturers for CPU products belonging to the same series, mainly aimed at distinguishing important labels of different types of CPUs. Currently, the classification of CPU instruction sets on the market is mainly divided into two camps: one led by Intel and AMD, which is the complex instruction set CPUs, and the other led by IBM and ARM, which is the reduced instruction set CPUs. Different brands of CPUs have different architectures; for example, Intel and AMD CPUs use the X86 architecture, while IBM’s CPUs use the PowerPC architecture, and ARM’s architecture is ARM architecture. Below, we will take a detailed look at several A-series processors released by ARM in recent years. ARM’s Cortex-A series processors are suitable for applications with high computational requirements, running rich operating systems, and providing interactive media and graphical experiences.
Cortex-A73
This is the latest A-series processor released by ARM in 2016. Cortex-A73 supports the full-size ARMv8-A architecture, which is ARM’s first processor architecture to support a 64-bit instruction set, including ARM TrustZone technology, NEON, virtualization, and encryption technology. Therefore, whether it is 32-bit or 64-bit, Cortex-A73 can provide the most adaptable mobile application ecosystem development environment. Cortex-A73 includes a 128-bit AMBR 4 ACE interface and ARM’s big.LITTLE system integrated interface, manufactured using the most advanced 10nm technology, providing 30% higher sustained processing capability than Cortex-A72, making it very suitable for mobile devices and consumer-grade devices. It is expected that later this year to 2017, the Cortex-A73 processor will gradually cover a series of consumer electronic devices such as high-end smartphones, tablets, clamshell mobile devices, and digital TVs.
Cortex-A72
Cortex-A72 was first released in early 2015 and is also based on the ARMv8-A architecture, utilizing TSMC’s 16nm FinFET manufacturing process. Cortex-A72 can achieve performance independently on the chip or be paired with Cortex-A53 processors and ARMCoreLinkTMCCI high-speed cache coherence interconnect (CacheCoherentInterconnect) to form an ARM big.LITTLETM configuration, further improving energy efficiency. Under the same mobile device battery life constraints, Cortex-A72 can provide 3.5 times the performance compared to devices based on Cortex-A15, and has about 1.8 times the performance improvement compared to Cortex-A57, demonstrating excellent overall power efficiency. Cortex-A72 is currently one of the most widely used processors based on the ARMv8-A architecture, with its main application markets including high-end smartphones, large-screen mobile devices, enterprise networking devices, servers, wireless base stations, and digital TVs.
Cortex-A57
Cortex-A57 is the flagship CPU product line designed by ARM for the 2013, 2014, and 2015 design points. It is also ARM’s first CPU to adopt the 64-bit ARMv8-A architecture, while maintaining complete backward compatibility with the ARMv7 architecture through the Aarch32 execution state. In addition to the architectural advantages of ARMv8, Cortex-A57 also improves single-clock cycle performance, outperforming high-performance Cortex-A15 CPUs by 20% to 40%. It also improves the design of the secondary cache and other components of the memory system, greatly enhancing energy efficiency. Cortex-A57 will provide ultra-high performance for mobile systems, and with the help of big.LITTLE, SoC can achieve this with very low average power consumption. It mainly targets mid-to-high-end computers, tablets, and server products.
Cortex-A53
Cortex-A53 also adopts the ARMv8-A architecture, capable of supporting both 32-bit ARMv7 code and 64-bit code in AArch64 execution state. The A53 architecture is characterized by reduced power consumption and improved energy efficiency. Its target is to achieve a power consumption of no more than 0.13W per core when running SPECint2000 tests under 28nm HPM manufacturing process. It provides higher performance than the Cortex-A7 processor’s power efficiency and can serve as a standalone primary application processor or be paired with the Cortex-A57 processor to form a big.LITTLE configuration. At the same frequency, Cortex-A53 can provide better performance than Cortex-A9. Its main targets are mid-to-high-end computers, tablets, set-top boxes, and digital TVs.
Cortex-A35
Cortex-A35 is a low-power CPU designed based on the ARMv8-A 64-bit architecture, aimed at replacing the previous 32-bit Cortex-A7 and Cortex-A5 cores. It adopts a similar in-order limited dual-issue design as A53/A7 while incorporating some new features from A72 and redesigning the instruction prefetch unit in the frontend to improve branch prediction accuracy. Additionally, A35 also uses A53’s cache and memory architecture, configurable with 8-64KB of level 1 instruction and data cache, 128KB-1MB of level 2 cache, integrates NEON/FP units, improves storage performance, supports full pipeline double-precision multiplication, and is equipped with hardware state retention (independent power domains) for both the CPU core and NEON pipeline to enhance power management efficiency. At the same process and frequency, A35’s power consumption is about 10% lower than that of A7, while performance is improved by 6-40%. Compared to A53, it can retain 80-100% of performance while reducing power consumption by 32% and area by 25%, achieving a 25% improvement in energy efficiency. A35 can also be paired with A53, A57, A72, and other large cores to form a big.LITTLE heterogeneous architecture system, further enhancing system energy efficiency. Its main positioning is in low-power low-end mobile phones, wearables, and IoT fields.
Cortex-A32
This is the only 32-bit (ARMv7-A) architecture processor in ARM’s new generation architecture, but A32 is like a 32-bit version of A35, with a clear goal of further controlling power consumption based on the already impressive performance of A35. The A32 architecture focuses on chip area, power consumption control, and energy efficiency, remaining at 32-bit (ARMv7-A instruction set). The instruction prefetch unit has been redesigned for efficiency, and the performance of level 1, level 2 caches, floating-point, and DSP operations has been improved for speed, introducing new power management features. It supports TrustZone security encryption, NEON SIMD instruction set, DSP/SIMD extensions, VFPv4 floating-point computation, and virtual hardware. A32 can provide the same performance as A35 in 32-bit mode. However, with lower power consumption, its energy efficiency (performance per unit of energy) is 10% higher than A35, 30% higher than A5, and 25% higher than A7. A35 can achieve 80-100% performance of A53 by increasing frequency, meaning A32 can also reach the same performance level in 32-bit mode, with a chip area only 68% of A53, while power consumption is only 61% of A53.
Under 64-bit, A35 has the strength to replace A53 architecture, while in 32-bit, A32 has already surpassed everyone, and compared to the 64-bit A35 architecture, the 32-bit A32 is more suitable for wearables and IoT products.
Cortex-A17
A17 is still based on the 32-bit ARMv7-A instruction set, initially adopting a 28nm process, later evolving to 20nm. Its essential architecture is the same as A12, which is dual-width and out-of-order issuing, only improving external interconnects by introducing a new consistency bus AMBA4 ACE for faster connections to memory controllers, thus improving performance and energy efficiency. Thanks to this new bus, A17 can support complete memory consistency operations for multi-core SoCs and can participate in big.LITTLE dual architecture hybrid schemes. Under specific frequency, process, and memory conditions, A17’s performance is approximately 40% higher than A12. In certain specific environments, A17’s performance can already match that of A15, but with lower power consumption and higher energy efficiency. Although it is named above Cortex-A15, its positioning is mid-range, not high-end.
Cortex-A15
Cortex-A15 was first released in 2010, based on the 32-bit ARMv7-A architecture. A15, like A9, supports out-of-order execution, but Cortex-A15 has (twice) the instruction issue ports and execution resources, with instruction decoding ability 50% higher, and dynamic branch prediction capability is stronger (using a multi-level branch table cache), and instruction fetching bandwidth is stronger (128 bit vs 64 bit), all of which can provide higher efficiency for A15’s pipeline execution. In addition, A15 uses the VFPv4 floating-point unit design, capable of executing FMA instructions and hardware division instructions, while A9’s peak vector floating-point performance is basically only half of A15’s. Cortex-A15 processors can be applied in smartphones, tablets, mobile computing, high-end digital appliances, servers, and wireless infrastructure devices.
Cortex-A9
ARM Cortex-A9 adopts the ARMv7-A architecture, and most of the quad-core processors we see today belong to the Cortex-A9 series. The design of Cortex-A9 processors aims to create the most advanced, efficient, dynamically variable-length, multi-instruction execution superscalar architecture, providing an 8-stage pipeline processor that executes using out-of-order speculation, with the required functionality for cutting-edge products in a wide range of consumer, networking, enterprise, and mobile applications, achieving both high performance and high energy efficiency. The Cortex-A9 microarchitecture can be used for scalable multi-core processors (Cortex-A9 MPCore multi-core processors) as well as more traditional processors (Cortex-A9 single-core processors). Scalable multi-core processors and single-core processors support 16, 32, or 64KB 4-way associative L1 cache configurations, and for optional L2 cache controllers, support up to 8MB of L2 cache configurations, offering high flexibility suitable for specific application areas and markets.
Cortex-A8
ARM Cortex-A8 processor, based on the ARMv7-A architecture, is currently the most common product among single-core smartphones. The Cortex-A8 processor is the first product based on the ARMv7 architecture, capable of increasing speed from 600MHz to over 1GHz. The Cortex-A8 processor can meet the power optimization requirements for mobile devices that need to operate below 300mW, as well as the performance optimization requirements for consumer applications that need 2000 Dhrystone MIPS. The Cortex-A8 high-performance processor is now very mature, providing reliable high-performance solutions from smartphones to netbooks, DTVs, printers, and automotive infotainment.
Cortex-A7
Cortex-A7 adopts the ARMv7-A architecture, characterized by excellent low-power performance while ensuring performance. The Cortex-A7 processor’s architecture and functionality are identical to those of the Cortex-A15 processor, with the difference being that the Cortex-A7 processor’s microarchitecture focuses on providing optimal energy efficiency. Therefore, these two processors can work together in a big.LITTLE (big core/little core companion structure) configuration, providing the ultimate combination of high performance and ultra-low power consumption. A single Cortex-A7 processor’s energy efficiency is five times that of the Cortex-A8 processor, with a performance improvement of 50%, while its size is only one-fifth of the latter.
Cortex-A5
Cortex-A5 processor is also based on the ARMv7-A architecture, known for being the most energy-efficient and cost-effective processor, providing the most basic Internet access to the widest range of devices. The Cortex-A5 processor is completely compatible in terms of instructions and functions with higher-performance Cortex-A8, Cortex-A9, and Cortex-A15 processors – all the way to the operating system level. The Cortex-A5 processor also maintains backward application compatibility with classic ARM processors (including ARM926EJ-S, ARM1176JZ-S, and ARM7TDMI?). It is positioned for entry-level smartphones, low-cost phones, smart mobile devices, and basic industrial devices.
To give everyone a more intuitive feel, please see the image below
As shown in the figure, the green parts are all v7-A architecture, the blue ones are v8-A architecture, basically, the green ones can support both 32 and 64 bits, except for A32, which only supports 32 bits. On the right side of each part, for example, the top A15-A73 part that requires high efficiency is the most efficient, followed by the part that focuses more on overall efficiency, the middle part is quite efficient, and the bottom bar is the best in terms of battery efficiency, achieving the best standards.
If one must rank them, from high to low, it can generally be sorted as: Cortex-A73 processor, Cortex-A72 processor, Cortex-A57 processor, Cortex-A53 processor, Cortex-A35 processor, Cortex-A32 processor, Cortex-A17 processor, Cortex-A15 processor, Cortex-A7 processor, Cortex-A9 processor, Cortex-A8 processor, Cortex-A5 processor.
| Architecture | Processor Family |
|---|---|
| ARMv1 | ARM1 |
| ARMv2 | ARM2, ARM3 |
| ARMv3 | ARM6, ARM7 |
| ARMv4 | StrongARM, ARM7TDMI, ARM9TDMI |
| ARMv5 | ARM7EJ, ARM9E, ARM10E, XScale |
| ARMv6 | ARM11, ARM Cortex-M |
| ARMv7 | ARM Cortex-A, ARM Cortex-M, ARM Cortex-R |
| ARMv8 | Cortex-A50[9] |
Previous Recommendations
SoC Design: Bus Interfaces
SoC Design: Low Power Consumption
Application of Perl in IC
EDA Tutorials
Chip Design
UVM Chip Verification
FPGA Series
Vivado Advanced
Formal Verification
Digital C Written Test
Digital IC Interview Experience
Excellent IC/FPGA Open Source Projects
Synthesis and Timing Analysis
Statement: Unauthorized reproduction is prohibited