SolidRun, Gyrfalcon Develop First Edge Optimized AI Inference Server That Bests GPU Performance

February 25, 2020 Perry Cohen

SolidRun, a developer and manufacturer of edge computing solutions, and ASIC solutions provider Gyrfalcon Technology,  introduced Janux GS31, a co-developed Arm-based AI inference server optimized for the edge (SRGT-AI31).

Highly scalable and modular, Janux GS31 can be configured with up to 128 Gyrfalcon Lightspeeur SPR2803 AI acceleration chips for unrivaled inference performance for today’s most complex video AI models.

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

It is equipped with 2803S Neural Accelerator chips for energy efficiency and delivers up to 24TOPS per Watt. Its Edge AI Inference Server outperforms SoC and GPU based systems by orders of magnitude, while using a fraction of the energy required by systems with equivalent computational power, according to the company. While lower energy consumption will help the Janux GS31 server deliver long-term cost savings, it also requires less of an upfront investment than competing inference servers.

For more information, visit

About the Author

Perry Cohen

Perry Cohen, associate editor for Embedded Computing Design, is responsible for web content editing and creation in addition to podcast production. He also assists with the publication’s social media efforts which include strategic posting, follower engagement, and social media analysis. Before joining the ECD editorial team, Perry has been published on both local and national news platforms including (Phoenix), (Phoenix),, Cronkite News, and MLB/MiLB among others. Perry received a BA in Journalism from the Walter Cronkite School of Journalism and Mass Communications at Arizona State university. He can be reached by email at <a href=""></a>. Follow Perry’s work and ECD content on his twitter account @pcohen21.

Follow on Twitter Follow on Linkedin More Content by Perry Cohen
Previous Article
Eta Compute Announces Production Silicon of the Energy-Efficient Edge AI Processor

Eta Compute’s ECM3532 family brings AI to edge devices for sensor data into actionable information for voic...

Next Article
embedded world 2020: DACOM West Presents IIoT Solutions from Established Manufacturers
embedded world 2020: DACOM West Presents IIoT Solutions from Established Manufacturers

Focus on industry 4.0