Fusion Design platform enables first-pass silicon for Armv9-based SoCs

Multiple SoC tape-outs at early adopters of the Arm Cortex-X2, Cortex-A710, and Cortex-A510 CPUs based on Arm’s Armv9 architecture, Arm Mali-G710 GPUs and Arm DynamIQ Shared Unit-110, have been announced. They were achieved using Synopsys’ EDA and IP, including Fusion Design Verification Continuum and DesignWare Interface IP.

The latest SoCs, developed for high end consumer devices, use Armv9’s performance and power efficiency enhancements and jointly developed flows and methodologies targeting the latest 5nm, 4nm and 3nm process technologies.

The EDA tools and IP provide designers with the leading, SoC-centric, and power-first software-to-silicon solution, says Synopsys, to hasten the achievement of the maximum performance per Watt across various use cases, including specialised artificial intelligence (AI), digital signal processing (DSP) and virtual and augmented reality (XR) workloads which are expected to be broadly deployed in next generation consumer devices.

“Based on the Armv9 architecture, the Arm Total Compute solution is designed to deliver a step-change in compute performance and efficiency while providing the levels of native security and trust needed in an increasingly data-centric and connected world,” said Paul Williamson, senior vice president and general manager, Client Line of Business, Arm.

Designers creating Armv9-based SoCs for a range of markets, including smartphones, laptops, PCs, digital TVs, wearables, and augmented- and virtual-reality applications, select Synopsys’ portfolio of integrated digital, verification and interface IP solutions to achieve optimum differentiation and the fastest time-to-market, says the company.

“Data is becoming an ever-increasing and important currency in this knowledge-driven world, and its timely, efficient and secure processing is paramount in shaping a safe, information-leveraged future,” said Shankar Krishnamoorthy, general manager of the Digital Design Group at Synopsys. “Our broad portfolio of optimised design, verification, IP, software security and software quality solutions have been aggressively co-optimised with Arm to enable a new wave of high-value applications based on the Armv9 architecture, establishing the new benchmark for trustworthy, power-centric performance.”

According to Synopsys, the Fusion Design Platform delivers unprecedented full-flow quality-of-results and time-to-results. Fusion Technology redefines conventional EDA tool boundaries – test, synthesis, place-and-route, and signoff – by sharing common, best-in-class engines, enabling broad-flow optimisations and wide-ranging margin reduction for performance per Watt and time to results.

Early adopters of Arm’s Armv9 mobile solution are using Synopsys’ Verification Continuum Platform solutions optimised for Arm, including Virtualizer Development Kit (VDK) with Arm Fast Models for Cortex-X2, Cortex-A710, Cortex-A510 CPUs and Mali-G710 GPUs, VCS simulation, Verdi for hardware and software debug, Verification IP for the latest Arm AMBA interconnect, ZeBu Server and HAPS hardware to accelerate hardware-software development and power and performance validation to reduce time-to-market.

The DesignWare Interface IP portfolio provides the performance, power efficiency, security and real-time connectivity for Arm-based systems implementing the latest Cortex CPUs and Mali GPUs. Synopsys’ IP portfolio of controllers and PHYs supporting the latest protocols such as PCI Express, DDR, MIPI and USB, is optimised for the rapid development of Arm-based SoCs.

Synopsys QuickStart Implementation Kits (QiKs) include implementation scripts and reference guides and enable early adopters to accelerate time-to-market and achieve their demanding performance per Watt targets.

http://www.synopsys.com

> Read More

Mali GPUs complement Armv9 CPUs

To complement a raft of Arm v9 CPUs, Arm has introduced GPUs for the architecture. The highest performing GPU, the Mali-G710 targets premium smartphones and Chromebooks, with 20 per cent performance improvements for compute intensive experiences, such as AAA high-fidelity gaming.

Mali-G710 also raises machine learning performance by 35 per cent, for tasks such as image enhancement for new camera and video modes.

There is also a sub-premium GPU, the Arm Mali-G610. This GPU has the same features as the Mali-G710 but at a lower price point.

Another introduction is the Arm Mali-G510, which has performance and low energy operation to extend battery life as well as machine learning for mid-range smartphones, premium smart TVs and set top boxes.

Finally, there is the Arm Mali-G310, claimed to deliver the highest performance at the smallest area cost. Mali-G310 now brings the Valhall architecture and high-quality graphics technologies to lower cost devices such as entry-level smartphones, augmented reality (AR) devices and wearables.

For more technical details on the new suite of Mali GPUs, visit our blog.

Arm believes that digital experiences have been shaped and defined by the premium smartphone, its software ecosystem and almost universal connectivity. This is now defining the standard for all consumer interactions.

Arm has introduced Total Compute, an holistic approach with IP to deliver richer gaming experiences with higher fidelity graphics and gameplay performance.

Arm’s Total Compute will also transform the way we interact, work and learn, says Dr Kevin Jou, CTO, MediaTek.  “Arm’s Total Compute solutions bring exciting new advances to the mobile landscape with more compute performance, increased system efficiency, and stronger security for future devices,” he said.

“Smart devices have become digital extensions of our lives that rely on performance, efficiency and security. With Arm’s Total Compute solution based on its latest Armv9 architecture and enhanced lead partnership, Samsung’s System LSI Business and Arm will open new possibilities for next-generation mobile platforms and we are excited about the transformation this will bring to the user experiences through our future technologies,” added Joonseok Kim, vice president of SoC design team, Samsung Electronics

“The new Armv9 based Total Compute solution with enhanced security features and increased performance will enable a more seamless immersive experience for the next-generation of smartphone and laptop devices using Arm technology, said” Eric Yu, head of hardware partnership at Zoom.

http://www.arm.com

> Read More

IP suite and Armv9 Cortex CPUs are part of Arm’s Total Compute

Arm has created Total Compute solutions, assembling hardware IP, physical IP, software, tools and standards based the recently introduced Armv9 architecture.

There are Armv9 CPU cores designed for consumer devices, including laptops, smart TVs, and mobile gaming. Arm Cortex-X2 is Arm’s most powerful CPU to date, delivering 30 per cent performance improvements compared with today’s flagship Android smartphones, says the company. It is also scalable across smartphones and laptops.

Arm Cortex-A710 is also based on Armv9 and has a 30 per cent energy efficiency gain and 10 per cent uplift in performance compared to the Cortex-A78.

Another announcement is the Arm Cortex-A510, which delivers 35 per cent performance improvements and increases machine learning (ML) performance, for use in smartphone, home and wearable devices.

Described as the backbone of the Armv9-A CPU cluster is a new DynamIQ Shared Unit, the DSU-110, which is scalable and supports up to eight Cortex-X2 CPUs, together with security and ML features.

Arm also announced that all cores for mobile applications will be 64-bit only by 2023, with support for all apps from Arm’s partners worldwide.

The latest CoreLink CI-700 Coherent Interconnect and CoreLink NI-700 Network-on-Chip Interconnect work seamlessly with Arm CPU, GPU and NPU IP to enable system enhancements. CoreLink CI-700 and CoreLink NI-700 have hardware level support for Armv9-A features, such as memory tagging extension (MTE), and support increased security, improved bandwidth and latency.

http://www.arm.com

> Read More

Reference IP accelerates creation of signal and data processing SoCs

Power signal and data processing SoCs can be created faster and for lower costs, says Sondrel, using its latest reference IP platform.

The SFA 300 reference IP is the latest addition to the. It is a semi-custom SoC design to which a customer’s IP can be added to create a bespoke solution for high performance data processing.

Each SFA 300 reference design has four CPU clusters. Several SFA 300s can be ganged together and synchronised via the PCIe interface to scale the processing performance. There is also the option to integrate accelerators and/or custom logic to further increase performance and minimise power requirements. Developers can use the SFA 300 to tailor designs for processing-intense applications such as 8K video, artificial intelligence (AI), facial recognition for surveillance, smart factories, blockchain servers and medical data analysis.

An ASIC with four CPU clusters is complex to design,” explained Rowan Naylor, a principal engineering consultant at Sondrel. “Moving data around the chip without bottlenecks needs a network on chip, a multi-width data path, internal RAM, scaled and distributed across the design for optimal performance, and data conflict arbitration”. He also went on to explain that data security aspects are required in the Arm-based security sub-system, such as activity/intrusion detection. These function are in the SFA 300 IP platform, which allows engineers to reduce the design time and costs by up to 30 per cent, declared Naylor.

The SFA 300 framework design enables it to be scaled to suit the application as well as be the basis for different solutions of varied processing power capabilities. The four CPUs can be chosen to suit the processing power need by each of the four channels of the chip because the interconnects on and off the CPUs are standardised. This standardisation of interconnects on the boundaries of IP blocks and the rest of chip enables most other IP blocks such as memory to be also exchanged as required.

If the processing power required is greater than can be achieved by upgrading the processors, then several chips can be ganged together to form a cluster to achieve the processing power required with the limiting factor being the speed of inter-chip communications dropping as more chips are ganged together.

According to Sondrel, this is an inexpensive means of achieving a high-performance solution as it requires just one chip repeated several times rather than a more expensive, single chip solution. Typical performance figures are 4 tera operations per second (TOPS) for each channel for AI and 400 giga operations per second for each channel for DSP.

The SFA 300 can be used for image and video analysis, for example. For a static image, it could find a face or count the number of blood cells on a sample slide and a neural net could provide more sophisticated recognition for data analysis, explained the company. Treating a video as a series of images, it could deduce the direction and speed of an object of interest.

Another use case could be heavy duty number crunching such as for block chains and cryptocurrency mining.

The SPA 300 has low power consumption, making it suitable for battery powered applications, such as a drone. The powerful image processing capabilities and AI enable it to be used as an autonomous drone controller to fly the drone.

The SPA 300 is the third in the company’s Architecting the future IP platforms.

Sondrel offers a full turnkey service that turns designs into fully tested, shipping silicon.

http://www.sondrel.com

> Read More

About Smart Cities

This news story is brought to you by smartcitieselectronics.com, the specialist site dedicated to delivering information about what’s new in the Smart City Electronics industry, with daily news updates, new products and industry news. To stay up-to-date, register to receive our weekly newsletters and keep yourself informed on the latest technology news and new products from around the globe. Simply click this link to register here: Smart Cities Registration