WOLF-1471
Overview
Embedded AI and Video Conversion with NVIDIA RTX A2000
The VPX3U-A2000E-FGX2-COAX module includes an NVIDIA RTX A2000 embedded GPU and a WOLF FGX2 in a rugged 3U VPX module. The NVIDIA Ampere 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 that are not native to the GPU, such as 12G-SDI and analog formats.
The NVIDIA Ampere architecture has introduced many significant improvements to the performance and efficiency of the GPU, with more flexible CUDA FP32/INT core use, more efficient third generation Tensor cores, and second generation RT cores. The Ampere GPU fabrication uses an 8nm manufacturing process providing significant power improvements which, along with other Ampere architecture improvements, can provide up to 103 GFLOPS/W, providing almost twice the performance compared to the previous Turing generation’s 60 GFLOPS/W or the Pascal generation’s 46 GFLOPS/W.
Unlocking the best performance requires the best cooling capability. WOLF’s advanced cooling technology moves heat away from the hot components using an efficient conduction cooled or air flow through design.
Block Diagram
The block diagram illustrates the RTX A2000 (Ampere) GPU paired with FGX2, highlighting coax-based video I/O paths (e.g., 12G-SDI and analog over coax) that are not native to the GPU. It shows the conversion/capture path into GPU processing and the outbound converted video routes, alongside the module’s PCIe connectivity to the VPX system.
Features
WOLF-1471 is a rugged 3U VPX module that combines an NVIDIA RTX A2000 embedded GPU with WOLF FGX2 video conversion to support embedded AI/HPEC processing alongside converted video I/O over 75 Ohm coax. It supports two 12G-SDI inputs, two CVBS inputs, and four 12G-SDI outputs, and includes 8 GB GDDR6 memory. The design provides a configurable PCIe Gen4 switch, and has a default 90W power configuration (configurable). The module aligns to SOSA slot profile support 14.6.11-16.
GPU Features
- Video inputs/outputs:
- Two 12G-SDI inputs
- Two CVBS inputs
- Four 12G-SDI outputs
- Ampere GPU parallel processing:
- CUDA Toolkit 12, CUDA Compute capability 8.6
- OpenCL 3.0, DirectX 12 Ultimate, OpenGL 4.6, OpenGL ES 3.2, Vulkan 1.2
- 80 Tensor Cores (3rd Gen), 34/66 TOPS (dense/sparse)
- 20 Ray Tracing cores (2nd Gen)
- 8 GB GDDR6 128-bit memory, up to 256 GB/s
- NVENC (7th Gen) and NVDEC (5th Gen) video encoding and hardware decoding support
Connectivity / System Management
- IPMI system management
- NVIDIA GPUDirect RDMA support
- Configurable PCIe Gen4 switch
- Linux and Windows drivers
- NVIDIA Ampere GPU support requires the following host CPUs: Intel E, S/H/H35 or AMD H/HS Class
Mechanical / Open Systems Architecture
- High level of ruggedization:
- Conduction cooled (CC) or Air flow through (AFT)
- Operating temp: CC: - 40°C to +70°C standard, operational to +85°C AFT: - 40°C to +71°C
- Random Vibration: VITA 47.1 Class V3
- Shock: VITA 47.1 OS2
- Two 75 Ohm coaxial connector type C, VITA 67.3
- Dimensions: 160 x 100 x 25.4/3.81 mm
- Weight: 1.3 kg
- ANSI/VITA 48, 65 (VPX- REDI, OpenVPX)
- SOSA Aligned support for slot profile 14.6.11- 16
Specifications
Key configuration and performance parameters for WOLF-1471 are summarized below for quick comparison. Values shown reflect the standard module configuration; contact WOLF if you need a tailored build or a specific payload profile.
Configuration Guide
The following table defines series of common order codes for the VPX3U-A2000E-FGX2-COAX module. The asterisks denote characters of the part number that are defined based on common configuration options.
Some configuration options for this module include:
- Display Interfaces
- Conformal Coatings
- Variant Locked
- Default Power Threshold
- PCIe Configuration Options
Contact Sales for the latest Ordering Numbers and available options.
Representative ordering numbers
| Ordering Number | Description |
|---|---|
| 147133-F**-***VPX3vA0 | 3U VPX, Conduction Cooled, 1”, NVIDIA Ampere RTX A2000 and WOLF FGX2, 80W, 1x 12G-SDI output, 1x 12G SDI input, 4x 3G SDI output, 4x 3G SDI input |
| 147133-F**-***VPX3vA0 | 3U VPX, Conduction Cooled, 1”, NVIDIA Ampere RTX A2000 and WOLF FGX2, 80W, 1x 12G-SDI output, 1x 12G SDI input, no 3G SDI output, no 3G SDI input |
Related Products
- NVIDIA RTX 2000 Ada (AD107)
- 3072 CUDA Cores, 96 Tensor Cores
- 8 GB GDDR6 VRAM
- PCIe Gen 4
- SOSA Payload, SOSA Legacy, OpenVPX
- Module power 45–120 W
- NVIDIA RTX 2000 Ada (AD107)
- 3072 CUDA Cores, 96 Tensor Cores
- 8 GB GDDR6 VRAM
- PCIe Gen 4
- SOSA Payload, SOSA Legacy
- Module power 45–100 W
FAQ
Choose WOLF-1471 when your platform uses coax-based video transport and you need SDI/CVBS-class I/O integrated with GPU processing.
This module is typically selected for:
- The system uses 75Ω coax I/O (VITA 67.3)
- You need 12G-SDI ingest and/or egress in a rugged VPX system
- You want GPU compute tightly coupled to the coax video workflow
If your ecosystem is DP/HDMI/DVI, a display-output module is usually simpler.
Coax integration is primarily a mechanical + signal-integrity planning exercise.
Confirm early:
- Your chassis/backplane and cabling plan supports VITA 67.3 Type C coax connectivity
- Connector count and routing align with how you plan to use the I/O (inputs vs outputs)
- Downstream equipment expects the selected SDI/CVBS formats
These checks typically prevent late-stage surprises in rear I/O design and harnessing.
Lock the required I/O mix early to avoid rework.
WOLF-1471 supports:
- Inputs: two 12G-SDI inputs and two CVBS inputs
- Outputs: four 12G-SDI outputs
If the program may change between variants (e.g., more ingest vs more egress), treat I/O planning as a configuration-management item, not a “later” detail.
Key ordering-time decisions are typically:
- Slot profile alignment: SOSA 14.6.11-16
- Power threshold: confirm the default/configured power aligns with chassis cooling
- Program controls: conformal coating and variant locking where required
Contact Sales for the latest ordering numbers and available configuration options.