Janux GS31 AI Server

Cost-Performance Optimized Edge

AI Inference Server

Janux GS31 AI Inference Server

Cost Performance Optimized LX2160A & i.MX8M Based AI Inference Server

Edge Optimized Machine Learning Inference

Janux GS31 AI Inference Server was tailor made to meet the future challenges of mass deployment of machine learning applications at the edge, including energy consumption, cost effectiveness and server real estate. This powerful server foundation allows for accelerated and cost-effective scaling of AI inference.

Supporting ultra-low latency transcoding and video analytics of up to 128 channels of 1080p/60Hz video, Janux GS31 is well suited for monitoring smart cities, infrastructure, intelligent enterprise/industrial video surveillance applications, object detection, recognition & classification, deep leaning inference, smart visual analysis, and much more.

See Specifications

Cost-Performance Optimized

The Janux GS31 server offers high-end processing with extreme energy efficiency and best cost-performance in its class. Janux GS31 achieves x3 the performance of other devices on the market, for half the cost, half the size and half the power consumption – it can simply do much more – for much less.

128 Acceleration Chips

Janux GS31 packs the ultimate punch with the CEx7 LX2160A COM Express type 7 module at the center, harnessing NXP’s Layerscape LX2160A 16-core Arm Cortex A72 processor. The server includes up to 4 x Snowball modules, each featuring 8 x NXP i.MX8M processors decoding 32 x Gyrfalcon Lightspeeur® SPR2803 AI accelerators – bringing the total AI inference power to 128 x acceleration chips.

Variety of Applications

Smart City & Buildings

Artificial Intelligence of Things

Machine Vision

Public Saftey

Specifications Resources Buy

AI Inference

TOPs	2150 tera operations per second @ 300MHz
AI Accelerators	Gyrfalcon Lightspeeur® SPR2803S (Up to x128 chips)
AI Networks	VGG ResNet MobileNet
Decoders	Up to 32 i.MX8M with 2D/3D engine and HW video decoders supporting 1080p60
No. of Channels	Up to 128 channels of 1080p60

Processor & Memory

Processor	CEx7 LX2160A 16-core Arm® Cortex® A72 (up to 2GHz)
Socket	1
Memory Type	Dual channel SO-DIMM DDR4, up to 64GB

Network & Connectivity

Network	2 x 10GbE SFP+ 1 x 1GbE RJ45
USB	2 x USB Type A 1 x USB Type B

Power & Mechanical

Power Consumption	Max 650W (single phase)
Power Input	IEC60320 connector 100V~240V
Form Factor	1U, 445mm X 43.5mm X 500mm (WxHxD)

Software

OS Support	Linux
Supported Framework	TensorFlow Caffe PyTorch

Environmental

Operating Temperature	10°C to 35°C
Storage & Transport Temperature	-40°C to 60°C
Operating Humidity	20% to 80% relative, non-condensing
Storage & Transport Humidity	20% to 93% relative, non-condensing

Developer Center

AI Inference
TOPs	2150 tera operations per second @ 300MHz
AI Accelerators	Gyrfalcon Lightspeeur® SPR2803 (Up to x128 chips)
AI Networks	VGG ResNet MobileNet
Decoders	Up to 32 i.MX8M with 2D/3D engine and HW video decoders supporting 1080p60
No. of Channels	Up to 128 channels of 1080p60
Processor & Memory
Processor	CEx7 LX2160A 16-core Arm® Cortex® A72 (up to 2GHz)
Socket	1
Memory Type	SO-DIMM DDR4, up to 64GB
Memory Slots	2
Network & Connectivity
Network	2 x 10GbE SFP+ 1 x 1GbE RJ45
USB	2 x USB Type A 1 x USB Type B
Power & Mechanical
Power Consumption	Max 900W (single phase)
Power Input	IEC60320 connector 100V~240V
Form Factor	1U 445mm X 43.5mm X 500mm (WxHxD)
Software
OS Support	Linux
Supported Framework	TensorFlow Caffe PyTorch
Environmental
Operating Temperature	10°C to 35°C
Storage & Transport Temperature	-40°C to 60°C
Operating Humidity	20% to 80% relative, non-condensing
Storage & Transport Humidity	20% to 93% relative, non-condensing
	Contact Us