SolidRun, Gyrfalcon Develop First Edge Optimized AI Inference Server That Bests GPU Performance
February 25, 2020
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.
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 https://www.solid-run.com/nxp-lx2160a-family/ai-inference-server/.