AI inference server optimized for the edge

March 02, 2020 //By Rich Pell
AI inference server optimized for the edge
High-performance edge computing solution developer SolidRun and AI processor provider Gyrfalcon Technology have introduced a co-developed Arm-based artificial intelligence (AI) inference server optimized for the edge.

Offered as being highly scalable and modular, the Janux GS31 supports leading neural network frameworks and can be configured with up to 128 Gyrfalcon Lightspeeur SPR2803 AI acceleration chips. The server, say the companies, allows for accelerated and cost-effective scaling of AI inference and is tailor made to meet the future challenges of mass deployment of AI applications at the edge, including energy consumption, cost effectiveness, and server real estate.

Janux GS31 supports ultra-low latency decoding and video analytics of up to 128 channels of 1080p/60Hz video, and is well suited for monitoring smart cities and infrastructure, intelligent enterprise/industrial video surveillance applications, tagging photos, and videos for text-based searching and more.

"Powerful, new AI models are being brought to market every minute, and demand for AI inference solutions to deploy these AI models is growing massively," says Dr. Atai Ziv, CEO at SolidRun. "While GPU-based inference servers have seen significant traction for cloud-based applications, there is a growing need for edge-optimized solutions that offer powerful AI inference with less latency than cloud-based solutions. Working with Gyrfalcon and utilizing their industry-proven ASICs has allowed us to create a powerful, cost-effective solution for deploying AI at the Edge that offers seamless scalability."

The server, says the company, outperforms SoC and GPU based systems by orders of magnitude, while using a fraction of the energy required by systems with equivalent computational power. It also requires less of an upfront investment than competing inference servers, say the companies.

"SolidRun's Janux GS31 inference server is a perfect implementation of GTI's AI accelerator technology and the Lightspeeur 2803S," says Bin Lei, senior vice president of sales and marketing for GTI. "The design and implementation of this server supports extremely high-performance inference with low energy use for high capacity live HD streaming video encoding and decoding to address demand in surveillance, broadcasting and a wide range of service provider market segments."

The Janux GS31 server is available


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.