VPX3U-AD2000E-FGX2-IO (WOLF-1570)

• NVIDIA RTX™ 2000 (AD107) GPU with 3072 CUDA Cores, 96 Tensor Cores, 24 RT Cores
• 8 GB GDDR6 128-bit memory, up to 256 GB/s
• Four 12G-SDI or ARINC 818 outputs
• Optional DP/DVI/HDMI output
• Two 12G-SDI or ARINC 818 inputs, two CVBS inputs
• Module power: TBD-120W, configurable

Overview

The VPX3U-AD2000E-FGX2-IO module includes an NVIDIA RTX™2000 Ada embedded GPU and a WOLF FGX2 in a rugged 3U VPX module. The NVIDIA Ada architecture includes CUDA cores for parallel processing, Tensor cores for dedicated AI accelerated compute, and Ray Tracing cores for superior rendering speeds. The WOLF FGX2 provides video conversion for formats which are not native to the GPU, such as SDI, ARINC 818, and CVBS formats.

The NVIDIA Ada GPU uses a new TSMC 4N NVIDIA Custom Manufacturing Process which produces a denser chip with increased power efficiency. The denser Ada GPUs have more CUDA and Tensor cores operating at higher clock frequencies at the same power, delivering significantly more performance per watt compared to WOLF’s previous generation product. The Ada AD107 GPUs can achieve up to two times the GFLOPS/W compared to the Ampere GA107 (depending on power and GPU temperature).

Unlocking the best performance requires the best cooling capability. WOLF’s advanced cooling technology is designed to move heat using a low weight, high efficiency path from the GPU die to the wedgelocks.

GPU & FGX FEATURES

• Video inputs/outputs:
  • 2x 12G-SDI or ARINC 818 Inputs
  • 2x CVBS inputs
  • 4x 12G-SDI or ARINC 818 outputs
  • Optional DP 1.4 output with support for 4K at 120Hz or 8K at 60Hz with 10-bit color depth
  • Optional DVI or HDMI output
• Ada GPGPU parallel processing:
  • CUDA Toolkit 12, CUDA Compute capability 8.9
  • CUDA-X AI and CUDA-X HPEC libraires
  • OpenCL™ 3.0, DirectX® 12 Ultimate, OpenGL 4.6, OpenGL ES 3.2, Vulkan™ 1.2
• 96 Tensor Cores (4th Gen)
• 24 Ray Tracing cores (3rd Gen)
• NVENC (8th Gen) and NVDEC (5th Gen) with up to 8K video encoding and hardware decoding support

CONNECTIVITY / SYSTEM MANAGEMENT

• IPMI system management
• NVIDIA GPUDirect RDMA support
• Configurable PCIe Gen4 switch
• Windows and Linux drivers
•  Ada GPU support requires one of the following host CPUs: Intel H/HX/P/PX/S/U Class, AMD H/HS/U Class

MECHANICAL / OPEN SYSTEMS ARCHITECTURE

• High level of ruggedization:
  • Rugged Conduction cooled 
  • Operating temperature: -40° to +85°C
  • Vibration (sine wave): 10G peak, 5 - 2000Hz
  • Shock: 40G peak 
• Dimensions: 160mm x 100mm x 25.4mm
• Weight (approximately): 1.5kg
• ANSI/VITA 48, 65 (VPX-REDI, OpenVPX)
• SOSA Aligned profile support for the Legacy payload slot profile 14.2.3

Datasheet

Open the product datasheet - includes block diagram, order codes, etc.

Learn More