WOLF-1538
Overview
HPEC with NVIDIA Ada RTX 5000 and PCIe Gen4 Switch
The VPX3U-AD5000E-VO module includes an NVIDIA RTX 5000 Ada embedded GPU and a PCIe Gen4 switch in a rugged 3U VPX module. The NVIDIA RTX 5000 embedded GPU provides the advanced processing capabilities for high performance embedded computing (HPEC) and artificial intelligence (AI) processing.
The NVIDIA Ada architecture includes CUDA cores for HPEC, 4th generation Tensor cores for AI and data science computations, and 3rd generation Ray Tracing (RT) cores for visually accurate rendering. The Ada GPU uses a new TSMC 4N NVIDIA Custom Manufacturing Process which increases 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. For example, comparing the 1448 to the 1538, the 1538 can achieve two to three times the GFLOPS/W (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.
Block Diagram
The block diagram depicts the RTX 5000 Ada GPU connected through an onboard PCIe Gen4 switch, providing the primary compute node with scalable uplinks to the VPX backplane. It highlights GPU-to-switch peer paths and the display output routing (front/rear, configuration dependent) used for visualization and mission display workloads.
Features
WOLF-1538 is a rugged 3U VPX module built around an NVIDIA RTX 5000 Ada embedded GPU and a configurable PCIe Gen4 switch to support embedded AI and HPEC processing with flexible VPX backplane integration. It includes 16 GB GDDR6 256-bit VRAM with ECC support and provides up to 4 DisplayPort outputs with options for DVI or HDMI by configuration. Module power is configurable from 60W to 140W, and the design supports SOSA aligned profile 14.6.11 (with P2 depopulated) or SOSA Legacy payload slot profile 14.2.3.
GPU Features
- Ada GPU parallel processing:
- CUDA Toolkit 12, CUDA Compute capability 8.9
- CUDA-X AI and CUDA-X HPEC libraries
- OpenCL 3.0, DirectX 12 Ultimate, OpenGL 4.6, OpenGL ES 3.2, Vulkan 1.2
- 304 Tensor Cores (4th Gen)
- 76 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
- Linux and Windows drivers
- AD103 GPU support requires one of the following host CPUs: Intel H/HX/P/PX/S or AMD H/HS Class
Mechanical / Open Systems Architecture
- High level of ruggedization:
- Rugged conduction cooled
- Operating temp: CC: - 40°C to +70°C standard, operational to +85°C
- Vibration (sine wave): 10G peak, 5 - * Shock: 40G peak
- Dimensions: 160mm x 100mm x 25.4mm
- Weight (approximately): 1.3kg
- ANSI/VITA 48, 65 (VPX- REDI, OpenVPX)
- SOSA Aligned profile support: 14.6.11 (with P2 depopulated) or SOSA Legacy payload slot profile 14.2.3
Specifications
Key configuration and performance parameters for WOLF-1538 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-AD5000E-VO 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
- SOSA or OpenVPX profiles
Contact Sales for the latest Ordering Numbers and available options.
Representative ordering numbers
| Ordering Number | Description |
|---|---|
| 153833-F***-***VPX3vA0 | 3U VPX, Conduction Cooled, 1", NVIDIA Ada RTX5000, OpenVPX 14.4.4 Profile, PCIe P1 x16 and P2 x4, Display Outputs 4 x DP |
| 153833-F***-***VPX3vA0 | 3U VPX, Conduction Cooled, 1", 14.6.11 payload profile with P2 depopulated, NVIDIA Ada RTX5000, PCIe P1 x16, Display Output 1 x DP |
Related Products
- NVIDIA RTX 5000 Ada (AD103)
- 9728 CUDA Cores, 304 Tensor Cores
- 16 GB GDDR6 VRAM
- PCIe Gen 4
- OpenVPX
- Module power 80–140 W
- NVIDIA RTX 5000 Ada (AD103)
- 9728 CUDA Cores, 304 Tensor Cores
- 16 GB GDDR6 VRAM
- PCIe Gen 4
- OpenVPX
- Module power 70–140 W
- NVIDIA RTX 5000 Ada (AD103)
- 9728 CUDA Cores, 304 Tensor Cores
- 16 GB GDDR6 VRAM
- PCIe Gen 4, 100GbE
- SOSA Payload
- Module power 100–140 W
FAQ
Choose WOLF-1538 when your system needs GPU compute plus native display outputs (DisplayPort, with HDMI/DVI options by configuration) and you do not need conversion to SDI/ARINC-class formats.
WOLF-1538 is typically the right fit when:
- Your downstream displays accept DP/HDMI/DVI
- You want flexible VPX integration via the onboard PCIe Gen4 switch
- You are optimizing for compute + visualization rather than non-native video transport
If your program requires SDI/ARINC 818 or other converted interfaces, a module with FGX/FGX2 is usually the better architectural match.
It gives you flexibility in how PCIe is presented to the backplane and how traffic is routed between the host, GPU, and peers.
Practically, that means:
- Easier alignment to different chassis/backplane PCIe topologies
- More options for lane routing and fan-out (platform/profile dependent)
- A cleaner path to peer-to-peer or multi-endpoint architectures without redesigning the module
If your backplane PCIe topology is fixed and simple, you may not need the additional flexibility; if you expect topology constraints or growth, the switch often reduces integration risk.
Confirm these items early to avoid profile/routing surprises:
- Slot profile support: SOSA-aligned 14.6.11 (P2 depopulated) or SOSA legacy 14.2.3 (and OpenVPX builds by configuration)
- Video output expectations: up to 4x DisplayPort outputs (with HDMI/DVI options by configuration)
- Rear I/O vs other routing: ensure the chosen profile and chassis support the display routing you intend to use
Treat the profile decision as an I/O routing decision, not just a mechanical compliance decision.
Most tradeoffs are system-level integration decisions:
- Slot profile selection: determines VPX backplane compatibility and which connector resources are available
- PCIe configuration: influences lane presentation and how you feed the GPU from the host/fabric
- Display interface configuration: DP-only vs DP with HDMI/DVI options, and how many outputs are enabled
- Power threshold (60W-140W envelope): must match chassis cooling for sustained performance
Contact Sales for the latest ordering numbers and available configuration options.