PRODUCT OF THE WEEK: WOLF Advanced Technology’s WOLF-153L HPEC module with NVIDIA Ada RTX5000 GPU

This week’s product, the WOLF Advanced Technology VPX3U-AD5000E-CX7 (WOLF-153L) high-performance embedded computing (HPEC) module, leverages the NVIDIA RTX 5000 (AD103) GPU and also the NVIDIA ConnectX-7, which provides the module with up to 100 GbE Ethernet and a PCIe Gen4 switch. The VPX3U-AD5000E-CX7 module uses a WOLF chip-down design to provide NVIDIA’s technology on a rugged board for aerospace and defense applications. such as sensor processing and C5ISR [command, control, communications, computers, cyber, intelligence, surveillance, and reconnaissance] systems.

NVIDIA Advantage

The VPX3U-AD5000E-CX7 HPEC module’s NVIDIA RTX 5000 Ada embedded GPU provides the advanced processing capabilities for HPEC and artificial intelligence (AI) processing. The ConnectX-7 provides the Ethernet and PCIe connectivity needed to move large data sets efficiently.

Included with the NVIDIA Ada architecture are 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. Tensor cores are designed to speed up the tensor/matrix computations used for deep learning neural network training and inferencing operations. NVIDIA Ada architecture GPUs include the 4th-generation Tensor core design which supports many data types for improved performance, efficiency, and programming flexibility, including a sparsity feature, a Tensor Float 32 (TF32) precision mode, and a new FP8 precision mode.

The Ada GPU uses a new TSMC 4N NVIDIA Custom Manufacturing Process which to increased efficiency. Ada GPUs are denser and have more CUDA and Tensor cores operating at higher clock frequencies at the same power, delivering more performance per watt compared to WOLF’s previous-generation product. For example, comparing the 144L to the 153L, the 153L can achieve two to three times the GFLOPS/W (depending on power and temperature limits).

The NVIDIA ConnectX-7 SmartNIC provides PCIe and Ethernet connectivity. ConnectX-7 is ideal for the high-speed, secure, data-transfer capabilities required for data-heavy tasks such as sensor data processing and other C5ISR tasks. The ConnectX-7 also provides support for RDMA over Converged Ethernet (RoCE), enabling the fastest method for transferring data across the network to the GPU.

GPU Features

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
184 Tensor cores (4th-Gen)
46 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

Onboard IPMI controller for system management
PCIe Gen4 configurable switch
Switching is offloaded from the CPU to the ConnectX with NVIDIA ASAP2 technology
Daisy Chain options
Support for 40/100 GBASE-KR4 protocols
10GBASE-KR Data and Control planes
GPUDirect RDMA and RoCE support
Block-level hardware encryption and the use of dedicated encryption keys per user
Windows and Linux drivers

SOSA Slot Profile support

This module’s configurable switch provides support for slot profiles aligned to the Sensor Open Systems Architecture, or SOSA, Technical Standard. The module can be configured with pin mappings that are compatible with older generation WOLF-144L modules, which allows the WOLF-153L to be a plug-in upgrade for previous WOLF products. The following SOSA aligned profiles are supported: 14.6.11-0 Payload Slot Profile, P2 depopulated and 14.6.13-0 Payload Slot Profile, P2B depopulated.

Other Features

Conduction cooled
Operating temperature: -40°C to +70°C standard, operational to +85°C
Vibration (sine wave): 10G peak, 5 - 2000Hz
Shock: 40G peak
Dimensions: 160mm x 100mm x 25.4mm
Weight (approximately): 1.5kg
WOLF designs and manufactures modules in North America with full component traceability.