industry news
Subscribe Now

High AI performance in a tiny, rugged housing

SolidRun launches new Bedrock R7000 - a Fanless Edge-AI IPC with AMD Ryzen 7840HS processor and 3 Hailo-8 AI Accelerators

Acre, Israel, 26 July 2023 – SolidRun has announced the world’s first rugged system design that combines 8-core AMD Ryzen 7040 series processors with multiple Hailo-8 AI accelerators to create its Bedrock R7000 Edge AI for artificial intelligence (AI) applications. This new member in SolidRun’s Bedrock family of fanless modular industrial PCs is specifically designed to meet demanding vision-based situational awareness in harsh environments.

The new system integrates with the AMD Ryzen 7840HS processor, a state-of-the-art 4nm APU with 8C/16T Zen4 CPU and integrated RDNA 3 Radeon 780M GPU. The 20 native PCIe Gen4 lanes and up to three Hailo-8 AI accelerators can be fully utilized together with NVME Gen4x4 storage, dual 2.5 Gbit Ethernet and 4x4K displays. The CPU and all devices are passively cooled by the innovative fanless cooling system of the Bedrock R7000 in an industrial temperature range of -40ºC to 85ºC.

Demand for such high-performance Edge AI box-PCs is growing in all segments of the embedded market, including Industry 4.0, robotics, autonomous guided vehicles, healthcare, transportation, smart cities, retail, agriculture, defense, and utility.

“Efficiency and scalability are key factors in advanced edge AI,” said Irad Stavi, IPC Product Line Manager at SolidRun. “Bedrock R7000 stands out as the first fanless IPC based on the ultra-efficient AMD Ryzen 7040 processor and the innovative modular design which enables out-of-the-box integration of 3 Hailo-8 AI accelerators, each with 26 Tera Operations per Second (TOPS), or even more with a simple customization.”

“An important feature of Hailo-8 AI accelerator and Hailo AI Software Suite is linear scaling of the inference performance simply by adding modules,” said Dima Caplan, Product Manager at Hailo. “SolidRun’s new Edge AI platform exhibits ample system resources which enable high AI performance at perfect scaling.”

Bedrock R7000 features
The Bedrock R7000 is equipped with an AMD Ryzen 7 7840HS / 7840U processor, featuring 8 cores and 16 threads running at up to 5.1 GHz based on the AMD Zen4 4nm microarchitecture that also integrates the AMD Radeon 780M GPU with up to 12 CUs @ 2700 MHz. CPU power can be precisely adjusted in BIOS in an extremely wide range between 8W – 54W.
For Edge AI workloads, up to 3 Hailo-8 AI accelerators can be installed with combined inferencing performance of up to 78 TOPS.

RAM and storage are modular with 2x SODIMMs supporting 64 GB DDR5 ECC/non-ECC, and 3 NVME 2280 PCIE Gen4x4 devices, including enterprise-grade NVME with power loss protection (PLP). RAM and storage are conduction-cooled for reliable operation at extreme temperatures.

I/O includes 4 displays comprising HDMI 2.1 + 3x DP 2.1, dual 2.5 Gbit Ethernet (Intel I226), optional WiFi 6E + BT 5.3, 5G or LTE modem, 4 USB 3.2 ports and a console port. All I/O is conveniently organized on a single face to simplify integration.

Bedrock R7000 supports all major PC operating systems, including most Linux distributions, Windows Desktop, Server and IoT.

Power, mechanical and thermal design
Bedrock R7000 electronic design is modular, SoM based. Power input is by a dedicated interchangeable module for supporting various deployment use cases. The default PM 1260 supports a wide voltage range of 12V to 60V

The enclosure is made of heavy-duty machined aluminum with an anodized finish. It is offered in 3 variants – 1.0 liter enclosure for dissipating up to 30W by convection, 1.6 liter for 60W and an 0.6 liter “Tile” variant for conduction cooling. The enclosure is ideal for DIN-Rail mounting with a specially designed zero-force locking bracket.

Bedrock R7000 fanless design can handle up to 60W, which is over 3 times the cooling capacity of typical fanless PCs of similar size. Cooling innovations include liquid metal TIM, 360º stacked heat pipes, dual-layer chimney effect heat exchanger and thermal coupling of all internal devices. The system operates reliably at a temperature range of -40ºC to 85ºC.

Specifications

CPU: AMD Ryzen 7840HS/U with Radeon 780M GPU
RAM: Dual channel DDR5 up to 64 GB ECC / non-ECC
Display: 1x HDMI 2.1 + 3x Display Port 2.1
Storage: Up to 3x NVMe PCIe Gen4 x 4
AI Acceleration: Up to 3x Hailo-8 M.2 AI Acceleration Module
LAN: 2x 2.5 GbE (Intel I226)
WLAN: WiFi 6E (Intel AX210)
Modem: 4G / 5G (Quectel)
USB: 1x USB 3.2 10 Gb/s + 3x USB 3.2 5 Gb/s
Console: Serial over USB
BIOS: AMI Aptio V
Operating systems: Windows 10/11/IoT, Linux
Power: DC 12V-60V
Temperature range: Up to -40ºC to 85ºC
Enclosure: All aluminum enclosure, fanless cooling
Dimensions:
30W model: 45 mm (W) x 160 mm (H) x 130 mm (D) –  0.9 liter
60W model: 73 mm (W) x 160 mm (H) x 130 mm (D) – 1.5 liter
Tile model: 29 mm (W) x 160 mm (H) x 130 mm (D) –  0.6 liter
Mounting: DIN-rail, wall, table top

For more information about the SolidRun Bedrock R7000 and its feature set please visit www.solid-run.com/fanless-computers/bedrock-r7000/

About SolidRun
SolidRun is a global leading developer of embedded systems and network solutions based on x86 and ARM architecture, in a variety of form factors including industrial mini PCs, gateways, SBCs (Single Board Computer) and SOMs (System-on-Module). The companies’ mission is to streamline application development, shorten time-to-market and simplify life-cycle management for its customers. For more information, please visit www.solid-run.com

Leave a Reply

featured blogs
Dec 8, 2023
Read the technical brief to learn about Mixed-Order Mesh Curving using Cadence Fidelity Pointwise. When performing numerical simulations on complex systems, discretization schemes are necessary for the governing equations and geometry. In computational fluid dynamics (CFD) si...
Dec 7, 2023
Explore the different memory technologies at the heart of AI SoC memory architecture and learn about the advantages of SRAM, ReRAM, MRAM, and beyond.The post The Importance of Memory Architecture for AI SoCs appeared first on Chip Design....
Nov 6, 2023
Suffice it to say that everyone and everything in these images was shot in-camera underwater, and that the results truly are haunting....

featured video

Dramatically Improve PPA and Productivity with Generative AI

Sponsored by Cadence Design Systems

Discover how you can quickly optimize flows for many blocks concurrently and use that knowledge for your next design. The Cadence Cerebrus Intelligent Chip Explorer is a revolutionary, AI-driven, automated approach to chip design flow optimization. Block engineers specify the design goals, and generative AI features within Cadence Cerebrus Explorer will intelligently optimize the design to meet the power, performance, and area (PPA) goals in a completely automated way.

Click here for more information

featured paper

Power and Performance Analysis of FIR Filters and FFTs on Intel Agilex® 7 FPGAs

Sponsored by Intel

Learn about the Future of Intel Programmable Solutions Group at intel.com/leap. The power and performance efficiency of digital signal processing (DSP) workloads play a significant role in the evolution of modern-day technology. Compare benchmarks of finite impulse response (FIR) filters and fast Fourier transform (FFT) designs on Intel Agilex® 7 FPGAs to publicly available results from AMD’s Versal* FPGAs and artificial intelligence engines.

Read more

featured chalk talk

Shift Left with Calibre
In this episode of Chalk Talk, Amelia Dalton and David Abercrombie from Siemens investigate the details of Calibre’s shift-left strategy. They take a closer look at how the tools and techniques in this design tool suite can help reduce signoff iterations and time to tapeout while also increasing design quality.
Nov 27, 2023
1,624 views