UAGX2U

AGX Orin Inference Server with 12x AGX Orin

Brand :

Deep Learning Servers

Description
Specifications
Ordering Guide

GPU-Accelerated Machine Learning and Inferencing Servers Bring Flexibility and Cost Efficiency to High-Powered Computing.
The AGX Orin Inference Server is an extremely low wattage, high performance AI workstation powered by the NVIDIA Jetson AGX Orin 64GB module. Running NVIDIA’s most powerful deep-learning software libraries, this inference server solves the challenge of deploying edge solutions at scale. The on-board 12x Jetson AGX Orin modules are all connected by a Gigabit Ethernet fabric through a specialized Managed Ethernet Switch with 10G uplink capability.

Processing Module	• 12x NVIDIA® Jetson AGX Orin™ • GPU: 2048-core CUDA GPU with 64 Tensor Cores, 11 TFLOPS (FP16), 275 TOPS (INT8) • CPU: 12-core Cortex ARM v8.2 64-bit CPU, 3MB L2 + 6MB L3 • Memory: 64GB 256-bit LPDDR5, 204.8 GB/s • Storage: 64 GB eMMC 5.1
Out-of-band Management Module	• ARM based OOBM • Enabling Serial console access, power status monitoring, and power control (ON/OFF) to all 12x AGX Orin modules • OOBM accessible via Ethernet or via its own integrated USB-to-Serial console
Processor Module Carriers	• Each module carrier will allow up to 4x NVIDIA Jetson AGX Orin modules to be installed • 3x module carriers can be installed in the system for a total of 12 modules
Internal Embedded Ethernet Switch	• Vitesse/Microsemi SparX-5i VSC7558TSN-V/5CC Managed Ethernet Switch Engine (XDG205) • CPU: 1 GHz Vcore • Memory: 8Gb DDR4 SDRAM • Storage: 1Gbit Serial NOR Flash • Multi 10G uplinks, with 12x 1G downstream • Complete TSN feature set (Time-Sensitive Networking)
Internal Array Communication	• 12x Gigabit Ethernet / 1000BASE-T / IEEE 802.3ab channels • All AGX Orin modules can communicate to all other AGX Orin modules
External Uplink Connections	• 4x SFP+ 10G uplink
Misc / Additional IO	1x 1GbE OOB management port via RJ-45; 1x USB UART management port; status LEDs
Input Power	100~240 VAC (dual redundant) with 1000W output each
Internal Storage	Each AGX Orin module has its own M.2 NVMe interface
Operating Temperature	0°C to +50°C (+32°F to +122°F)
Dimensions	• Standard 2U rackmount 88.9mm (H), 635mm (D) • With Mounting Bracket: 163.6 x 146.1mm x 99.4mm • Without Mounting Bracket: 163.6 x 108.0mm x 96.3mm

Model	Description
UAGX2U-13	NVIDIA Orin AGX 2U Inference Server with 12x AGX Orin 64GB Modules, 12x 1TB NVMe
UAGX2U-16	NVIDIA Orin AGX 2U Inference Server with 12x AGX Orin 64GB Modules, 12x 2TB NVMe