Vendor: Sondrel Ltd Category: Edge AI Accelerator

IP platform for intelligence gathering chips at the Edge

Designed to be the solution for an AI compute device right at the Edge, Sondrel’s new SFA 100 IP reference platform makes creatin…

Contact Provider Request Datasheet

Overview

Designed to be the solution for an AI compute device right at the Edge, Sondrel’s new SFA 100 IP reference platform makes creating high-performance, battery-powered IoT devices easy and fast. The design has an onboard Arm® CPU to locally process data gathered from its associated sensors for onward transmission via wire or wireless connection for further analysis. Naturally, security is built in using standard secure/encrypted protocols.

Key features

  • The SFA 100 provides the ability to integrate a machine-learning engine onto a low cost, low power edge device and is based on the Arm® Corstone™-300 subsystem that ensures a very high level of security. It consists of an Arm Cortex®-M55 with secure boot with cryptographic algorithm accelerators and supports TrustZone® and CryptoCell™ for additional security for the onward processed data. Also included is the Arm Ethos™-U55 Machine Learning (ML) processor that provides a 480x uplift in ML performance. This powerful, combined processing capability enables the endpoint device to perform a variety of ‘smarts’ such as voice activation, image classification, gesture recognition, filtering, inference and tracking depending on the application. If these need more memory, it can easily be scaled up via the DRAM interface.
  • The design has GPIO, I2C, UART and QSPI peripheral interfaces to capture sensor data, such as video, image, sound and both static and dynamic data, along with a 12-bit audio DAC for voice commands. The low overall power requirement of the SFA 100 design enables it to operate on battery power for long periods which is complemented by low power, wireless connectivity using either Bluetooth BT5.1-LE or ZigBee.

Block Diagram

SFA 100 block diagram

Benefits

  • High performance IoT solutions for AI at the Edge can now be created up to 30% faster

Applications

  • High performance IoT solutions for AI at the Edge

Files

Product Sheet Download

Note: some files may require an NDA depending on provider policy.

Specifications

Identity

Part Number
SFA 100
Vendor
Sondrel Ltd

Provider

Sondrel Ltd
HQ: United Kingdom
Sondrel was founded in 2002, and is a privately held UK company, providing silicon chip design services. With design centres in China, Europe and Morocco, Sondrel provides engineering consultancy supporting an international client base, designing the technology products and infrastructure that we now all take for granted, for example in our cars, consumer products and communications networks. In association with industry partners we are also leading the creation of a new eco-system to support the growth of the connected world through the Internet of Things. Our engineers have substantial expertise and relationships with IP providers, EDA tool suppliers and foundries. We work with large multi-national companies and SMEs to achieve the quality, reliability and time to market targets required for today's increasingly complex technology applications. In 2021, we launched a pioneering new approach to ASIC design that can reduce design costs by up to 30% and bring products to market much faster. Called Architecting the Future, it is a family of IP platforms each designed for specific application areas. The platform is pre-designed to have the relevant IP and interconnects already designed, rather than starting from scratch for each new project, such that the customer's IP can be easily integrated to create the final bespoke ASIC.
Contact Sondrel Ltd

Learn more about Edge AI Accelerator IP core

RISC-V Based TinyML Accelerator for Depthwise Separable Convolutions in Edge AI

While lightweight architectures like MobileNetV2 employ Depthwise Separable Convolutions (DSC) to reduce computational complexity, their multi-stage design introduces a critical performance bottleneck inherent to layer-by-layer execution: the high energy and latency cost of transferring intermediate feature maps to either large on-chip buffers or off-chip DRAM. To address this memory wall, this paper introduces a novel hardware accelerator architecture that utilizes a fused pixel-wise dataflow.

Accelerating Your Development: Simplify SoC I/O with a Single Multi-Protocol SerDes IP

Enter the Multi-Protocol SerDes (Serializer/Deserializer)—a flexible, reusable IP block that allows a single PHY to support multiple serial communication protocols, such as PCIe, SATA, Ethernet, USB, and more. This approach enables SoC vendors to meet diverse customer requirements and application needs without redesigning I/O for each target market.

Frequently asked questions about Edge AI Accelerator IP cores

What is IP platform for intelligence gathering chips at the Edge?

IP platform for intelligence gathering chips at the Edge is a Edge AI Accelerator IP core from Sondrel Ltd listed on Semi IP Hub.

How should engineers evaluate this Edge AI Accelerator?

Engineers should review the overview, key features, supported foundries and nodes, maturity, deliverables, and provider information before shortlisting this Edge AI Accelerator IP.

Can this semiconductor IP be compared with similar products?

Yes. Buyers can compare this product with similar semiconductor IP cores or IP families based on category, provider, process options, and structured technical specifications.

×
Semiconductor IP