AV800-X1A
AI Inference GPU System, Tesla T4 (Turning Tensor Cores 320) & Intel® Xeon® D-2183IT (16 Cores), up to 256GB DDR4 ECC RDIMM, MIL-DTL-38999 , MIL-STD 461 Compliant
- Ultra-High Performance Intel® Xeon® Skaylake DE D2183IT (16 Cores, , 32 Threads, Frequency 2.20GHz, Turbo Boost Frequency up to 3.00GHz)
- NVIDIA TELSA T4 GPU Integrated (2560 CUDA, 16GB GDDR6)
- 128GB DDR4 ECC RDIMM
- NVMe for Fast & Mass Storage
- Design for reliability under demanding MIL-STD-810 Temperature, Shock, Vibration, MIL-STD 461 EMI/EMC
- Extended Temperature -20 to +55 Degree
- Technical Profile
- Specifications
AV800-X1A is 7STARLAKE ruggedized AI inference platform specifically designed for NVIDIA® Tesla T4 and supports Intel® Xeon® Skylake DE D-2183IT Processor. Utilizing 7STARLAKE' Open, Modular, Scalable Architecture, AV800-X1A provide optimized cooling solution for Tesla T4, ensure the stable system operation in harsh environments. In addition to Tesla T4, AV800-X1A provides one M.2 NVMe slot for fast storage access. Combining stunning inference performance, powerful CPU and expansion capability, it is the perfect ruggedized platform for versatile edge AI applications.
AV800-X1A ruggedized AI inference platforms designed for advanced inference acceleration applications such as voice, video, image and recommendation services. It supports NVIDIA® Tesla T4 GPU, featuring 8.1 TFLOPS in FP32 and 130 TOPs in INT8 for real-time inference based on trained neural network model.
- Advanced thermal solution
-
From internal conduction cooling system with copper heat pipes dissipating the CPU GPU main heat to external dual-sided aluminum heat sink, furthermore with system fan of active cooling control and power fan for turbo operation, are all the solution designed to guarantee superior system performance and stable operation under critical environment.
- Edge AI Inference, NVIDIA Tesla T4 & INTEL XEON D2183IT
-
AV800-X1A is 7STARLAKE ruggedized AI inference platform specifically designed for NVIDIA® Tesla T4 and supports Intel® XEON Skylake DE processor. Utilizing 7STARLAKE' Open, Modular, Scalable Architecture, AV800-X1A provide optimized cooling solution for Tesla T4, ensure the stable system operation in harsh environments. In addition to Tesla T4, AV800-X1A provides one M.2 NVMe slot for fast storage access. Combining stunning inference performance, powerful CPU and expansion capability, it is the perfect ruggedized platform for versatile edge AI applications.
AV800-X1A ruggedized AI inference platforms designed for advanced inference acceleration applications such as voice, video, image and recommendation services. It supports NVIDIA® Tesla T4 GPU, featuring 8.1 TFLOPS in FP32 and 130 TOPs in INT8 for real-time inference based on trained neural network model.
- Ultra-High Performance Intel® Xeon® Performance with VMware Support
-
Skylake DE: The Intel® Xeon® processor D-2183IT product family is Intel’s 64-bit system on a chip (SOC) and the first Intel® Xeon® SoC based on Intel® 14 nm silicon technology. This lineup offers hardware and software scalability from two up to sixteen cores, making it the perfect choice for a broad range of high-performing, low-power solutions that will bring intelligence and Intel® Xeon® reliability, availability, and serviceability (RAS) to the edge. For applications where space is a premium, an integrated Platform Controller Hub (PCH) technology and Intel® Ethernet in a ball grid array (BGA) package offer an inspiring level of design simplicity. The Intel® Xeon® processor Skylake DE product family is offered with a seven-year extended supply life and 10-year reliability for Internet of Things designs.
- Design to Meet MIL-STD 810, MIL-STD461
-
AV800-X1A is designed to meet strict size, weight, and power (SWaP) requirements and to withstand harsh environments, including temperature extremes, shock/vibe, sand/dust, and salt/fog.
AV800-X1A is MIL-461/1275 EMI/EMC compliant rugged Edge AI Inference server. It passes numerous environmental tests including Temperature, Altitude, Shock, Vibration, Voltage Spikes, Electrostatic Discharge and more. The sealed compact chassis shields circuit cards from external environmental conditions such as sand, dust, and humidity.
- 7STARLAKE Inference Optimized GPU Server
|
System |
|
|---|---|
|
Processor |
Intel® Xeon® Processor D-2183IT (Frequency 2.20GHz, Turbo Boost Frequency up to 3.00GHz), 16-Core, 32 Thread Support, 22MB Smart Cache.
|
| Memory type
|
4 x DIMMs Up to 256GB ECC RDIMM DDR4 2133MHz |
|
Chipset |
SoC, integrated with CPU |
|
GPU |
|
|
NVIDIA |
TESLA T4 |
|
Turning Tensor Cores |
320 |
|
CUDA Cores |
2560 |
|
Memory |
16 GB GDDR6, 300 GB/sec |
|
Graphics Output |
|
|
1x VGA |
ASPEED AST2500 |
|
Resolution |
Up to 1920x1200@60Hz 32bpp |
|
Storage |
|
|
HDD/SSD |
1x M.2 2280 M key NVMe socket (PCIe Gen3 x4) for NVMe SSD installation 2 x 2.5" SSD (Easy Swappable) |
|
Side I/O |
|
|
X1 ( 2 x 10GbE Ethernet)) |
1x Amphenol TV07RW-13-35S (22PIN) |
|
X3(VGA) |
1 x Amphenol TV07RW-13-35S (22PIN) |
|
X4(USB3.0x2) |
1 x Amphenol TV07RW-13-35S (22PIN |
|
X5 (DC-IN) |
1 x Amphenol TV07RW-13-04P (4PIN) |
|
Button |
1 x Power Switch with Dedicated LED |
|
SSD Tray |
2 x Dual 2.5" HDD/SSD Easy Swap Tray |
|
Dedicated LED |
1 x Red LED(OVHT),1 x Green LEDs(SSD) |
|
Power Requirement |
|
|
Power Input |
DC-DC 18 to 36V (300W max) Mil-STD 461 |
| Applications, Operating System | |||||||
|---|---|---|---|---|---|---|---|
| Applications | Commercial and Military Platforms Requiring Compliance to MIL-STD-810 Process Control, where Harsh Temperature, Shock, Vibration, Altitude, Dust and EMI Conditions. | ||||||
| Operating System | Windows 10 64Bit, Windows Server 2008 R2, Windows Server 2012 R2, Windows Server 2016, Ubuntu14.04, Fedora 20/23, RedHat Linux EL 7.1/7.2, VMware ESXi 6.0, ESXi 6.5 | ||||||
| Physical | |||||||
| Dimension(W x D x H) | 400 x 284 x 180mm (15.74" x 11.18" x 7.08") | ||||||
| Weight | 15Kg (33.06lbs)> | ||||||
| Chassis | Aluminum Alloy, Corrosion Resistant | ||||||
| Finish | Anodic aluminum oxide | ||||||
| Cooling | Natural Passive Convection/Conduction. No Moving Parts | ||||||
| Ingress Protection | IP65 | ||||||
| Environmental | |||||||
| Operating Test | MIL-STD-810G Test | ||||||
| Method 502.5, Procedure II ( Operation/Low Temperature ) | |||||||
| Method 501.5, Procedure II ( Operation/High Temperature ) | |||||||
| Method 507.5, Procedure II ( Temperature & Humidity ) | |||||||
| Method 514.6 Vibration Category 24/Non-Operating ( Category 20 & 24, Vibration ) | |||||||
| Method 516.6 Shock-Procedure V Non-Operating ( Mechanical Shock ) | |||||||
| Method 516.6 Shock-Procedure I Operating ( Mechanical Shock ) | |||||||
|
Non-Operating Test |
|||||||
|
|
|||||||
| Method 502.5, Procedure I ( Storage/Low Temperature ) | |||||||
| Method 502.5, Procedure II ( Operation/Low Temperature ) | |||||||
| Method 501.5, Procedure I ( Storage/High Temperature ) | |||||||
| Method 514.6 Vibration Category 24/Non-Operating ( Category 20 & 24, Vibration ) | |||||||
| Method 514.6 Vibration Category 20/Operating ( Category 20 & 24, Vibration ) | |||||||
| Method 516.6 Shock-Procedure V Non-Operating ( Mechanical Shock ) | |||||||
| Method 516.6 Shock-Procedure I Operating ( Mechanical Shock ) | |||||||
| Method 509.7 Salt Spray (50±5)g/L | |||||||
| EMC compliance | |||||||
|
MIL-STD-461 : CE102 basic curve, 10kHz - 30 MHz RE102-4, (1.5 MHz) -30 MHz - 5 GHz RS103, 1.5MHz to 18GHz, 50V/m equal for all frequencies EN 61000-4-2: Air discharge: 8 kV, Contact discharge: 6kV EN 61000-4-4: Signal and DC-Net: 1 kV EN 61000-4-5: Leads vs. ground potential 1kV, Signal und DC-Net: 0.5 EN 55022, class A EN 61000-4-3: 10V/m Designed to Meet the following testing methods(Options for testing with additional cost):CS101, CS114, CS115,CS116CE106, RE103,RS101MIL-STD-1275:Steady State – 20V~33VSurge Low – 18V/500msSurge High – 100V/500ms |
|||||||
| Operating Temperature | -20°C to 55°C | ||||||
| Storage Temperature | -40°C to 85°C | ||||||