Trending News
Home / Technology / Electronics & EW / Race for faster, high performance System on Chip (SoC) for 5G, mobile computing, Smartphones, and IoT

Race for faster, high performance System on Chip (SoC) for 5G, mobile computing, Smartphones, and IoT

A system on a chip or system on chip (SoC) is an integrated circuit (also known as a “chip”) that integrates all components of a computer or other electronic system on a single circuit die. Similar to how a microcontroller integrates a microprocessor with peripheral circuits and memory, an SoC can be seen as integrating a microcontroller with even more advanced peripherals like graphics processing unit (GPU), Wi-Fi module, modems or one or more coprocessors– all on a single substrate.   It may also contain digital, analog, mixed-signal, and often radio frequency signal processing functions, depending on the application. SoCs connect to other components too, such as cameras, a display, RAM, flash storage, and much more.

 

As they are integrated on a single electronic substrate, SoCs consume much less power and take up much less area than multi-chip designs with equivalent functionality. Finally, SoCs are much cheaper to design and utilize when compared to multi-chip systems. They are fabricated using a metal-oxide-semiconductor process that is cheaper at volume, and the reduced assembly costs and cabling drives cost down further still. Because of this, SoCs are very common in the mobile computing such as tablets, smartphones, smartwatches , netbooks, edge computing markets and the Internet of Things.

 

SoCs are characterised using manufacturing processes, a number in nanometers (nm), which is measurement of the internal wiring of the SoC. The chips and transistors, which form the brains of our smartphones and devices, have been shrinking each year and current flagship SoCs are as tiny as 7 nanometers or 7 billionths of a meter. That’s how small the overall frame of the chipset has become. In the microelectronics space, Intel was once the champion. Apple, Google, Facebook and others are designing their own chips because they have recognised this is a vital opportunity. “The basic microelectronic architecture is going to be key,” said Vincentelli. And so, the race is on for the company that can build the machinery that can do these essential AI computations the best and the fastest.

 

In the smartphone space, Qualcomm, Samsung Semiconductor, Huawei’s HiSilicon, and MediaTek are the four biggest names in the business.   Qualcomm is largest provider of smartphone SoCs, shipping chips for the majority of flagship, mid-tier, and even low-end smartphone releases each year. Qualcomm’s SoCs fall under the Snapdragon branding. Premium chips boasting the company’s best technology come under the Snapdragon 800 series banner, such as the latest Snapdragon 868. Mid and super-mid tier products are branded with Snapdragon 600 and 700 series names respectively. Such as the Snapdragon 765 which sports 5G connectivity. Entry level products are named under the 400 series.

 

Motorola could soon launch its next flagship device with Snapdragon 888 SoC. As per reports, Chen Jing, general manager of Lenovo, had teased the launch of the smartphone on Twitter’s Chinese counterpart Weibo. In his post, Chen revealed that the smartphone would arrive with a set of interesting features. However, no details about its specifications and launch date were confirmed by the company.

 

Samsung’s Exynos SoCs operate on a similar premium, mid, and entry tier scale. These were previously listed as the Exynos 9900, 9800, and 9600 series, with Exynos 7000 series products propping up the budget end of the portfolio. However, Samsung’s latest high-end chip is the Exynos 990, while the Exynos 980 is a 5G mid-tier chipset. Fittingly, Samsung has previously confirmed that they’ll be (back to) using Arm’s cores in future designs, particularly the the Cortex-X1, Arm’s big effort to double-down on overall CPU performance. So it’s pretty much guaranteed that Cortex-X1 will show up in Samsung’s next-gen SoC – especially if they want to compete with Qualcomm’s X1-equipped next-gen Snapdragon.

 

The Kirin 990 is Huawei’s latest flagship chip, which comes in 4G and 5G variants. The Kirin 600 series is much like the Snapdragon 600 range, offering mid-tier specifications for more affordable smartphones. The Chinese tech giant Huawei Technologies showcased its  Kirin 990 chipset as the first all-in-one 5G system on a chip, describing it as superior to alternatives from Qualcomm (QCOM.O) and Samsung (005930.KS) that, it says, graft 5G modems on to 4G chips. Finally, MediaTek’s Helio range spans affordable P series products up to the gaming focused G series, and latest flagship Dimensity 1000 with 5G.

 

The race for faster chips is getting hotter. Apple’s recently released M1 chip computers,  based on TSMC’s 5nm technology node process. Tesla only recently announced an expansion to its partnership with Samsung to develop 5nm chips for its FSD technology. Intel currently uses 10nm and 14nm chips, though the company typically has greater transistor density than its competitors, meaning it’s not a like-for-like comparison.

 

In May 2019 , Samsung has announced a breakthrough  in chip manufacturing that will help foundries pursue miniaturization to 3nm. And the Korean giant has a head start as it is two to three years ahead of Intel and around 12 months of TSMC, said Handel Jones, chief executive of consulting firm International Business Strategies.

 

In May 2021, IBM announced a “breakthrough in semiconductor design and process” today, with the world’s first 2-nanometer (nm) chip using nanosheet technology. The chip is expected to achieve 45 percent higher performance than today’s most advanced 7nm node chips, IBM explained in a press statement.

SOC are  based on ARM Architecture

Central Processing Unit (CPU) is the “brains” of the SoC running most of the code for the Android OS and most of your apps. SoCs use one or more processor cores based on the Arm CPU architecture.  An ARM processor is one of a family of CPUs based on the RISC (reduced instruction set computer) architecture developed by Advanced RISC Machines (ARM). RISC processors are designed to perform a smaller number of types of computer instructions so that they can operate at a higher speed, performing more millions of instructions per second (MIPS).  By stripping out unneeded instructions and optimizing pathways, RISC processors provide outstanding performance at a fraction of the power demand of CISC (complex instruction set computing) devices.

 

ARM processors are extensively used in consumer electronic devices such as smartphones, tablets, multimedia players and other mobile devices, such as wearables. Because of their reduced instruction set, they require fewer transistors, which enables a smaller die size for the integrated circuitry (IC). The ARM processor’s smaller size, reduced complexity and lower power consumption makes them suitable for increasingly miniaturized devices.

 

The simplified design of ARM processors enables more efficient multi-core processing and easier coding for developers. While they don’t have the same raw compute throughput as the products of x86 market leader Intel, ARM processors sometimes exceed the performance of Intel processors for applications that exist on both architectures. Many of today’s best integrated circuits maximize power efficiency using asynchronous symmetric multi-processing (aSMP). This allows a chip to only utilize the cores that are necessary to perform a given operation.

 

Other peripherals in SoC

The days of the central processing unit (CPU) being the primary component in a computer system are long gone. Today, the CPU is only a small part of the constantly growing equation that adds up to be a system-on-chip (SoC).

Apart fom CPUs SoC contain other peripherals like:

  • Graphics Processing Unit (GPU) — The graphics processing unit (GPU) is  number-crunching hardware  that handles most graphics-related tasks, such as visualizing an app’s user interface and 2D/3D gaming.These operations are are repeated over and over again to fill all the pixels on your screen and as such, GPUs are designed to run lots of math all at once on big batches of data. Unlike CPUs that execute one or two operations each cycle, GPUs execute tens, hundreds, and even thousands of parallel operations each cycle. This depends on the size and performance of the GPU design. The two major GPUs in the mobile SoC space are Arm’s Mali and Qualcomm’s Adreno. Both offer bigger and smaller versions of the GPU technology, with flagship chips packing in their most powerful hardware for 3D gaming.
  • Digital Signal Processor (DSP) — Handles more mathematically intensive functions than a CPU. Includes decompressing music files and analyzing gyroscope sensor data.
  • Image Processing Unit (ISP) — Converts data from the phone’s camera into image and video files. An ISP is a specialized DSP that handles common imaging tasks like Bayer transformations, focusing, demosaicing, sharpening, and noise reduction. In other words, it turns digital information from a camera sensor into a nice looking picture. Huawei’s Kirin 990 is the first SoC with DSLR-grade block-matching and 3D filtering (BM3D) noise reduction. This produces great results in the Huawei Mate 30 Pro.
  • Neural Processing Unit (NPU) — Used in high-end smartphones to accelerate machine learning (AI) tasks. These include voice recognition and camera processing. NPUs are processors specifically designed to run neural networks and machine learning tasks more quickly and efficiently than CPUs. NPUs feature their own local memory caches too, to speed up execution without having to use slower RAM. Neural networks often require operations that take multiple pieces of input data to generate just a single output. The multiple-accumulate operation is particularly popular, often operating on a variety of data sizes from 16 bits down to 8 and even 4 bits of data. This is very different from the math and data types used by CPUs, although some operations can be accelerated on flexible GPUs.
  • Video encoder/decoder — Handles the power-efficient conversion of video files and formats.
  • Modems — Converts wireless signals into data your phone understands. Components include 4G LTE, 5G, WiFi, and Bluetooth modems. Different modems also determine the speed and quality of your data connection. The most powerful modems hit speeds above 1Gbps. The first SoCs with integrated 5G modems and capabilities are already here. Huawei has a 5G version of its Kirin 990 and Qualcomm’s Snapdragon 765 offers integrated 5G. However, the most powerful 5G modems are still external. Qualcomm’s Snapdragon X55 and Samsung’s Exynos 5123 modems provide faster speeds than their integrated counterparts as well as mmWave support. 2020’s flagship 5G phones will be sticking with external modems for a little while longer.

 

Smartphone SoCs are increasingly less about any one single capability and more about a heterogeneous compute approach to solving processing problems. Today’s handsets handle a wider range of workloads than ever before. As a result, the number of dedicated processors inside each chip continues to increase. From basic CPU and GPU components a few years ago, to DSPs, advanced ISPs, and NPUs today. These less-talked-about parts are only becoming more important with advances in security, machine learning, and 5G.

Qualcomm announces latest Snapdragon

Qualcomm Technologies, Inc. announced the Qualcomm® Snapdragon™ 678 Mobile Platform in Dec 2020, a follow-on to the Snapdragon 675, to deliver overall performance upgrades, high-speed connections for sophisticated photo and video capture, and immersive entertainment experiences.

 

Snapdragon 678 offers the following performance enhancements over Snapdragon 675:

Qualcomm® Kryo™ 460 CPU core clock speed up to 2.2GHz
Qualcomm® Adreno™ 612 GPU performance increase
In addition to these performance upgrades, Snapdragon 678 supports dynamic photography and videography abilities, and immersive entertainment experiences with long battery life over fast, reliable connectivity.

Qualcomm earlier  announced the Snapdragon 675, a mid-range smartphone SoC with some high-end features. The Snapdragon 675 has two performance-focused cores at 2.0GHz alongside six 1.78GHz cores designed for power efficiency. Cores aside, the Snapdragon 675 appears to have designed for the reality that high-end features are no longer the exclusive preserve of flagship phones. The new image signal processor has been built with triple-camera setups in mind, while there are gaming enhancements for specific titles that sound similar to Huawei’s GPU Turbo optimizations. The 675 also includes Quick Charge 4+ support and a faster AI engine.

 

 

Apple advances to 5nm node

In Sep 2020, Apple introduced what it called its most advanced processor yet, a custom-designed mobile chip based on the 5-nm node that will power its upcoming generation of hardware, including its iPhone. Apple said the new chip pumps out more performance by integrating 11.8 billion transistors on the silicon die, a generational leap of around 40% compared to the A13, which incorporates 8.5 billion, and the A12, which packs 6.9 billion.

 

Apple has continuously rolled out more advanced chips in its flagship iPhone over the last decade, boasting of major improvements in performance and energy efficiency. The A14, the latest in its family of A-series processors, contains a new central processing unit (CPU) with a pair of large, high-performance cores and four smaller, more energy-efficient cores to bolster battery life. Apple said the improvements add up to 40% more performance than the A12 processor in the last-generation iPad. Apple released the A12 based on TSMC’s 7-nm node in the 2018 iPhone.

 

It had a six-core CPU (with two “performance” cores and four “efficiency” cores), a four-core GPU (which is up to 50 percent faster than the A11’s), and an updated Neural Engine, a special part of the chip designed to handle AI tasks. While last year’s chip had a two-core Neural Engine, the A12 Bionic bumps that up to eight cores. And while the old Neural Engine could crunch through 600 billion operations per second, the new version can handle 5 trillion operations per second.

 

2021 iPhones will use enhanced 5nm chips; 2022 ones move to 4nm(ish)

Market intelligence firm TrendForce is out with a new report, in which it predicts that the A15 chip in Apple’s 2021 iPhones will stick with a 5nm process, but will move to an enhanced ‘5nm+’ version. The A16 chip for the 2022 iPhones are expected to move to a 4nm process, though the company does add a rider to this …

TrendForce notes that Apple’s iPhone 12 models are so far the only smartphones to use TSMC’s advanced 5nm process capabilitie

Looking ahead to 2021, in addition to Apple’s 5nm+ wafer input for the A15 Bionic SoC, trial production will also kick off for a small batch of AMD 5nm Zen 4 CPUs […] Furthermore, based on current data, Apple is highly likely to continue manufacturing its A16 SoCs with the 4nm process technology (a process shrink of the 5nm node).

TSMC refers to 5nm+ as N5P, and describes it as a performance-enhanced version which will combine greater power with improved power efficiency to improve battery-life (or, as might be more likely with Apple, permit smaller-capacity batteries).

 

 

Huawei’s SOC  launches

Chinese tech giant Huawei launched the most powerful flagship Mate 40 series carrying its 5-nanometer Kirin 9000 chips during a global online event in Oct 2020. The phones, which are likely to be Huawei’s last equipped with its proprietary Kirin chips, are hitting the market at a time when the US crackdown on the firm is intensifying, and more countries are excluding it from their 5G network rollouts under US government pressure. Among the very first group of smartphones to carry the cutting-edge 5nm chip, and probably the last to carry its “out-of-print” chips, the launch of the Mate 40 series is impressive and “solemn,” Jiang Junmu, chief writer at Chinese telecom industry news website c114.com.cn, told the Global Times.

 

“Among the highlights of the phones will certainly be its self-developed 5nm Kirin 9000 chips,” Jiang said. Richard Yu Chengdong, CEO of Huawei Consumer Business, said during the launch event on Thursday that the Kirin 9000 chipset, also the world’s first 5G System on Chip (SOC), will have more powerful 5G capabilities, artificial intelligence capabilities, and stronger CPU and GPU capabilities than its rivals. While some companies are just launching their first-generation 5G phones, the Mate 40 series is Huawei’s third-generation 5G phone, with the third-generation 5G technology, Yu said.

Huawei has unveiled a new ARM-based CPU called Kunpeng 920, designed to capitalise on the growing euphoria building around big data, artificial intelligence and edge-computing. The CPU was independently designed by Huawei based on ARMv8 architecture license, with the team claiming it improves processor performance by optimizing branch prediction algorithms, increasing the number of OP units, and improving the memory subsystem architecture. The Kunpeng 920  built using the cutting edge 7-nanometer process and uses the semiconductor architecture of ARM Holdings, Shenzhen-based Huawei said in a statement on Monday. The new chips would compete with the dominant x86 server architecture used by US giants Intel and Advanced Micro Devices Inc.

 

 

IBM Makes ‘Semiconductor Design Breakthrough’ With the World’s First 2nm Chip

“The IBM innovation reflected in this new 2 nm chip is essential to the entire semiconductor and IT industry,” said Darío Gil, SVP and Director of IBM Research. “It is the product of IBM’s approach of taking on hard tech challenges and a demonstration of how breakthroughs can result from sustained investments and a collaborative R&D ecosystem approach.” The 2nm chip will allow processor makers to either deliver a 45 percent performance boost using the same amount of power, or the same performance using 75 percent technology.

 

IBM said that mobile devices using 2nm-based processors could have up to four times more battery life “only requiring users to charge their devices every four days.” The chips would also faster internet access and quicker processing in applications for laptops, as well as faster object detection and reaction time for self-driving cars. The company also said its new 2nm chip would enable data centers, which currently “account for one percent of global energy use,” to greatly reduce their carbon footprint.

 

SOC Market

System-on-chip market is expected to reach USD 256.87 billion by 2027 witnessing market growth at a rate of 9.55% in the forecast period of 2020 to 2027.

 

Major factors such as the increasing demand for smart, compact and power-efficient electronic device and rise in adoption of IoT based technologies is spurring the growth of system-on-chip market globally. However, high initial cost of design & development and maintenance is expected to hinder the growth of this market. The requirement for compact and scalable ICs in the global electronic industry is expected to bring numerous opportunities, thereby supporting the growth of the system-on-chip market during the forecast period.

 

The market for system-on-chip has seen considerable growth due to rising applications in end-user industries, with smartphones application having the largest market share. Industries such as telecommunication, consumer electronics, and healthcare are also leading verticals in adopting system-on-chip technology so as to improve the performance of networking devices and biomedical devices.

 

The growing demand for IoT devices will foster the growth of the system-on-chip (SoC) market in the forthcoming years. The spending on the IoT by several market vendors grows, the demand for connected devices will also increase. In the generation of large volumes of data, various connected devices are being used. Therefore, several vendors in the market are introducing SoCs for IoT applications, as it offers reliable, secure, fast, scalable, and cost-efficient solutions. And it is increasingly being deployed across complex business environments to support the processing of large volumes of data at high speeds and reduced error rates. Thus, the adoption of the IoT is driving the demand for connected devices, which is creating the demand for SoCs. Our analysts have predicted that the system-on-chip (SoC) market will register a CAGR of over 6% by 2023.

 

System-on-chip is an integrated circuit on which several electronic components are combined together such as transistors, control units, memory units, peripherals, and others, depending on the type of its application. It contains both hardware and software that results in better response time and efficient power consumption. SoC is an efficient way to enhance the performance of the device and helps to meet the ever-increasing computational demand. Also, due to the advancement in manufacturing process and availability of cost-effective silicon chip is expected to create better opportunities for many players in the semiconductor market.

 

Top System on Chip (SoC) Manufacturers

The major players in the system-on-chip market are Intel Corporation, Qualcomm Incorporated, Samsung Electronics Ltd, NXP Semiconductors N.V., Toshiba Corporation, Broadcom Limited, STMicroelectronics N.V., Apple Inc, MediaTek Inc, and Taiwan Semiconductor Manufacturing Company Limited.

STMicroelectronics:  STMicroelectronics, one of the renowned names in top 10 SoC Manufacturers has varieties of SoC. SoC from ST embedding the most advanced innovations today catering to vast applications. Panning from LoRa SoCs to automotive infotainment SoCs, ST has been ground-breaking new markets with the use of SoCs. SoC combines ST’s expertise in ultra-low-power STM32 microcontroller(MCU) design.

Analog Devices : Apart from analog, mixed-signal and digital signal processing (DSP) integrated circuits (ICs), Analog Devices manufacture the greatest SoC which is used in the modern electronic equipments.  Analog Devices SoC FPGA Development Boards are of great demand and the company plans to keep on innovating this space.

Texas Instruments : Texas Instruments has been advancing its focus into the wireless infrastructure space.  Focusing on the portable and mobile multimedia applications, TI has leading proprietary OMAP which is advanced SoC.

Dialog Semiconductor: DFor years, Dialog Semiconductor has been innovating the SoC market, fuelling into the Internet of Things and Industry 4.0 applications, Dialog’s proven expertise in SoC is already propelling next generation devices. Delivering performance and capability to act in this new digital world, Dialog Semiconductors deliver highly-integrated, world’s smallest and most energy efficient Bluetooth low energy SoCs. Also, the company has world’s first Wi-Fi SoC.

Microchip Technology:  Ranging from Dual Core Metering SoC to Smart Energy SoC, Microchip could speed development of portable products with its advanced SoC technology. Microchip also flaunts the company’s Newest RF System on a Chip.

GHI Electronics: GHI Electronics has been providing consulting, manufacturing huge range of SoC. It’s SoC has made the name of GHI Electronics in electronics engineering and manufacturing. The company is planning on continuing its cutting-edge innovation with best products and services in the SoC space. Also, the company has been focusing vitally into the embedded product market.

Cypress Semiconductor: With its plan to make Cypress 3.0, Cypress Semiconductor has manufactured high range of SoC in the world. It is planning to target markets growing faster than the broader semiconductor industry with embedded systems solutions: combinations of MCUs, wireless connectivity, analog, USB and memory products plus the software to enable them to work together flawlessly. Also, Cypress is a leading player for PSoC® (Programmable System-on-Chip) technology.

Silicon Labs:  Silicon Labs today offers Low Energy SoC, Series 2 Multiprotocol Wireless SoC also puts leadership in Bluetooth SoC for Bluetooth 5.2. The work of Silicon Labs is to create the silicon, software, and solutions that enable the connection of things, information, and people. Silicon Labs wireless solutions today comprises the widest technology and product portfolio advancing its SoC capabilities.

Nordic Semiconductor: Nordic chips are routinely found in wireless PC peripherals, game controllers, sports and fitness sensors, toys, advanced multi-media controllers, and digital/satellite TV (set-top box) remotes, to mention a few.

 

 

ARM’s DynamIQ is the future of multi-core SoCs

The latest CPU cores from Arm are the big Cortex-A77 and little Cortex-A55. Smartphone CPUs often appear in eight-core configurations, with big powerful cores for more demanding applications and smaller power-efficient cores to ensure long battery life.

 

In March 2017, ARM unveiled its next-generation multi-core micro-architecture designed to boost the performance and efficiency of multi-core Cortex-A processors, which form the basis of many mobile and server SoCs. Known as DynamIQ, the new technology will be heading to automotive, smart home, smartphone, and other connected device markets in the near feature. The Arm Cortex-A76 CPU is the second generation premium core built on DynamIQ technology. DynamIQ is an evolution of ARM’s existing big.LITTLE technology, the heterogeneous computing architecture that connects together and manages dual ARM CPU core clusters in multi-core configurations. DynamIQ takes this a step further by enabling big.LITTLE configurations of up to eight different CPU cores on a single compute cluster for the first time. This offers SoC designers much greater flexibility than ever before.

 

Paired with a Cortex-A55 CPU in a scalable DynamIQ big.LITTLE configuration, the Cortex-A76 delivers laptop-class performance with mobile efficiency, bringing the mobile experience (fast responsiveness, always on, always connected) into all classes of intelligent mobile compute devices. With superior energy efficiency and far greater single-threaded performance, the Cortex-A76 CPU extends battery life and improves user experience for sustained high performance across even the most complex compute tasks.

MediaTek Announces Dimensity 1000 ARM Chip With Integrated 5G Modem

The company has announced its new Dimensity 1000 system-on-a-chip (SoC) with the latest ARM CPU cores and an integrated 5G modem. The company’s previous high-end chip was the Helio G90, which had two high-power CPU cores and six low-power cores. That put it on a different, more modest level than the chips from Qualcomm, HiSilicon, and Samsung. The Dimensity 1000 doesn’t just bring new branding; it’s also sporting four Cortex A77 CPU cores and four Cortex A55 CPU cores, all built on a 7nm process node. There’s also a 9-core Mali GPU, a 5-core ISP, and a 6-core AI processor.

 

The Dimensity 1000 modem has a maximum theoretical download speed of 4,800Mbps, but that’s on “sub-6” 5G networks. Those networks, operating below 6GHz, are still very rare in the US. Most carriers have started their 5G rollouts in higher millimeter wave spectrum, which has higher throughput and less coverage. Sprint is the only US carrier with a large swath of sub-6 spectrum suitable for 5G, so millimeter wave will continue being an important part of the US 5G landscape into the future. The Dimensity 1000 won’t support that spectrum at all.

 

The Dimensity 1000 will support QHD+ resolutions with refresh rates up to 90Hz. At 1080p, the Dimensity can go as high as 120Hz. It also supports camera resolutions as high as 80MP or a 32+16MP dual arrangement with 4k60 video. That’s all in the same ballpark as the 800-series Snapdragon chips from Qualcomm.

 

References and Resources also include:

https://www.engadget.com/2018/08/31/huawei-kirin-980-mobile-chip-7nm/

https://www.theverge.com/circuitbreaker/2018/10/22/18012568/qualcomm-snapdragon-675-announced-specs-features

https://www.androidauthority.com/arm-unveils-dynamiq-758182/

https://www.androidauthority.com/what-is-an-soc-smartphone-chipsets-explained-1051600/

https://www.bisinfotech.com/top-10-system-on-chip-soc-manufacturers-of-2020/

About Rajesh Uppal

Check Also

Edge Computing is multiplier for IoT infrastructure and military missions

Humanity is now generating more data than it can handle; more sensors, smartphones, and devices …

Leave a Reply

Your email address will not be published. Required fields are marked *

error: Content is protected !!