Stouffville, Ontario, July 5, 2018 - WOLF announces a new WMXM-P2000E-VO (WOLF-9176) module which uses a WOLF chip-down design to provide advanced NVIDIA® Quadro® Pascal™-based GPU technology on an extremely rugged small form factor module, making it an excellent choice for aerospace and defense applications. These modules, manufactured in North America with full component traceability, have been designed specifically for use in harsh environments with mission critical reliability requirements.
The WOLF Pack is growing at a phenomenal rate and it is time for us to upgrade to a much larger facility to meet our customers' future needs. The new location triples our space and has been designed to maximize our collaboration, innovation, technology development and production capabilities.
WOLF Advanced Technology announces two new 3U VPX models which combine NVIDIA Pascal P5000, 6.2 TFLOP GPUs with high-density features, ruggedized for harsh aerospace and defense environments. These new modules meet MIL-STD-810 and MIL-HDBK-217 and are manufactured to IPC A 610 and IPC 6012 Class 3. The processing performance provided by these modules is the highest currently available to aerospace and defense, with an unprecedented 62 GFLOPS/Watt.
Aerospace and defense applications demand products that are sensitive to their SWaP (size, weight and power) restrictions. In the past this put some of the highest performing GPU products out of reach because their power requirements, acceptable for a desktop computer or a data center, were too high for a device intended for an embedded application. This led embedded solution providers to use GPUs that were targeted mainly at the mobile and laptop market. While these mobile GPUs had lower power requirements they also were not as high performing as the same generation’s desktop GPUs.
WOLF’s Frame Grabber eXtreme powers the XMC-FGX-SDI-4IO providing Video Capture, Conversion and Display.
The versatile WOLF XMC-FGX-SDI-4IO (WOLF-3080) module accepts multiple simultaneous inputs and can convert to multiple output formats, including 3G-SDI, HD-SDI and analog (CVBS, STANAG 3350 or VGA). The module is powered by a WOLF Frame Grabber eXtreme (FGX) capture engine which leverages Xilinx® FPGAs to provide capture and conversion of video data from one standard to another. The module can also accept video sources from a GPU DisplayPort output or from a PCIe DMA stream for real-time conversion to SDI or analog output. The raw data from each channel can be streamed with sub-frame latency to the host system or to a GPU for analysis, enhancement, encode or display.
WOLF Pascal-Based XMC Video Boards bring Tremendous Processing/Watt Advantages to Aerospace and Defense.
WOLF Advanced Technology announces new XMC boards which integrate Pascal GP107, 2.3 TFLOP GPUs, designed to operate in harsh aerospace and defense environments. These new, chip-down XMC boards are tested to meet MIL-STD-810 and MIL-HDBK-217, and meet the quality standards of IPC-A-610 Class 3 and IPC 6012 Class 3. The NVIDIA Pascal GP107 provides excellent performance per watt with an extremely impressive 46 GFLOPS/Watt.
The latest generation of NVIDIA® PascalTM and AMD Polaris GPUs are providing enormous increases in processing speed. However, these new GPUs have dropped native support for legacy analog formats. While this may be an obvious move for a GPU chip designer, whose primary market no longer requires analog support, it does present a challenge to customers who do still require legacy analog support. WOLF’s solution is a new FIT module, a Flexible Interface Technology module, which can be used to provide analog format support to new VPX products.
This document describes WOLF’s VPX PCI-Express port configuration options as it applies to both the VPX3U and VPX6U system architectures.
WOLF’s VPX 3U/6U modular solutions have been designed to facilitate rapid module integration into today’s highly configurable rugged system designs. WOLF’s VPX solutions combine advanced technology graphics and compute modules, legacy analog and high speed digital capture, process and display, and VPX interface configurability supporting multiple host interface options.
Advances in graphics processors offer extremely powerful computing capabilities for image capture and processing suited to aerospace and defense applications, while addressing past concerns regarding both heat dissipation and power consumption that arise when implementing GPUs in constrained, rugged embedded environments. The NVIDIA Tegra K1 GPU architecture offers a performance/power combination ideally suited for high-performance embedded applications, especially those where there is a desire to offload the graphics processing from the main computing engine yet still facilitate data transfers between the two, typically over a PCI Express-based switched fabric connection such as XMC or VPX.
The VNX VITA 74 specification, ratified on December 13, 2017, is a response to an industry demand for a smaller form factor module that maintains many of the advantages of VPX. The VNX specification defines the:
The small form factor MXC modules can be combined to make extremely powerful video capture, display and encoding solutions on VPX, VME, CompactPCI, COMExpress designs and OEM products. The envelope size for MXC is equal to the board outline, due to the interface connector used and its position on the bottom of the board, giving it a size advantage over MXM modules with similar functionality.
Modular COTS building blocks for aerospace and defense requirements enable WOLF to provide analog/digital video capture, CUDA/OpenCL GPGPU processing, H.264/H.265 encoding and display solutions for VPX, XMC and other SFF architectures.
The aerospace and defense industries are experiencing an ever-increasing demand for situational awareness capabilities for applications such as surveillance and autonomous navigation. The majority of new military and aerospace projects will require some degree of image capture, video processing, encoding and display capabilities as a part of the system.
The VPX architecture is designed around the concept of a “system-in-a-chassis” topology. Each card performs a single function that adds to an overall system, connected through a backplane. In that model, too much functionality on any single card would quickly saturate the available bandwidth.
However, advancements in bandwidth speed and inter-connectors have greatly increased the data transfer rates between discrete cards. For instance, a 16-lane PCIe link using the ubiquitous v2.x serial fabric is capable of transmitting eight gigabytes of data per second, and the newer v3.0 can attain transfer rates of sixteen gigabytes per second.