GPU, Graphics, & Video Cards

CHAMP-XD3
The CHAMP-XD3/VPX3-484 3U OpenVPX Intel Ice Lake Xeon D-1700 DSP Processor Card features high-speed DDR4 memory, 10 Gb Ethernet, 40 Gb Ethernet Data Plane, AMD MPSoc FPGA for enhanced security.
CHAMP-XD3
The CHAMP-XD3/VPX3-484 3U OpenVPX Intel Ice Lake Xeon D-1700 DSP Processor Card features high-speed DDR4 memory, 10 Gb Ethernet, 40 Gb Ethernet Data Plane, AMD MPSoc FPGA for enhanced security.
Learn More
GPU, graphics and video cards provide extensive capabilities, from video capture to graphics rendering and display to processing high-resolution sensor data to enable quick response and other massive parallel computing needs. Some solutions are avionics safety certifiable with artifacts to document objectives are met. Lastly, processors with integrated graphics are also available in our 3U VPX processor cards selection, including VPX3-1260, VPX3-1262, and VPX3-1220. GPU co-processor cards can harness to the enormous floating point processing power of the GPU device for applications requiring massive parallel computing capability, such as algorithmic vector processing and deep learning frameworks for AI/ML applications. Our GPU co-processing engines leverage the latest NVIDIA technologies supporting CUDA software frameworks and include integrated Tensor Cores for machine learning applications. These cards are critical components of our high-performance embedded computing (HPEC) ecosystem that delivers data center capability at the tactical edge.

3U VPX GPU Cards

Equipped with NVIDIA CUDA and Tensor cores, the 3U VPX GPU cards offer TFLOPS processing capability alongside maximum memory bandwidth for the most compute-intensive tasks like situational awareness, deep learning, artificial intelligence (AI), and high-performance processing.

Product Image Product Name Description Profile Processor / FPGA Performance Data Sheet
VPX3-1711 3U VPX AI/ML Processor Card with NVIDIA Jetson AGX Orin Industrial SoM N/A NVIDIA N/A
VPX3-730 3U VPX NVIDIA RTX PRO 5000 Blackwell GPU SOSA Payload 14.6.11 or 14.6.13, OpenVPX NVIDIA 50 TFLOPS
VPX3-4940 3U VPX NVIDIA RTX GPU Card with 3072 CUDA, 96 Tensor, & 24 RT cores 3U SOSA Payload, 3U OpenVPX NVIDIA 12.9 TFLOPS
VPX3-4938 3U VPX NVIDIA RTX 5000 Ada GPU Card with 9728 CUDA, 304 Tensor, & 76 RT cores 3U SOSA Payload 14.6.11-0 or 14.6.13-0, 3U OpenVPX NVIDIA 27.7 TFLOPS
VPX3-4937 3U VPX NVIDIA Ada GPU Card with 9728 CUDA, 304 Tensor, & 76 RT cores 3U SOSA Payload 14.6.11-0 or 14.2.3, 3U OpenVPX NVIDIA 27.7 TFLOPS
VPX3-4935 3U VPX NVIDIA Quadro Turing (TU104) GPU Card with 3072 CUDA, 384 Tensor, & 48 RT Cores 3U SOSA Payload 14.6.11 or 14.6.13, 3U OpenVPX NVIDIA 11.2 TFLOPS
VPX3-719 3U VPX AMD E8860 Graphics and Video Capture Card 3U OpenVPX MOD3-PAY-1D, MOD-PAY-2F, and MOD-PER-2F AMD 768 GFLOPS
VPX3-717 & V3-717 DO-254 Safety-Certifiable 3U VPX AMD E8860 Graphics Board 3U OpenVPX 1D-14.2.6 or 2F-14.2.7 AMD 768 GFLOPS
VPX3-716 3U VPX/OpenVPX AMD E8860 Graphics Processor 3U OpenVPX MOD3-PAY-1D, MOD-PAY-2F, and MOD-PER-2F AMD 768 GFLOPS
Graphics Software Suite Graphics & Video Drivers with Artifacts for RTOS and Safety-Critical Systems Support 3U OpenVPX and XMC AMD N/A
VPX3-493 3U VPX NVIDIA Turing T1000 GPU Card with 896 CUDA cores 3U OpenVPX NVIDIA 2.6 TFLOPS

6U VPX GPU Cards

For systems requiring compute-intensive capability or using deep learning frameworks for AI applications, these 6U OpenVPX highly engineered processing powerhouse cards provide a field-proven hardware foundation for machine learning, AI, and high-performance embedded computing applications.

Product Image Product Name Description Profile Processor / FPGA Performance Data Sheet
VPX6-731 6U VPX NVIDIA RTX PRO 5000 Blackwell GPU SOSA Payload 14.6.11 or 14.6.13, OpenVPX NVIDIA N/A
VPX6-4939 6U OpenVPX Single or Dual NVIDIA RTX5000 Ada GPU Card with 9728 CUDA, 304 Tensor, and 76 RT Cores 6U SOSA Payload 10.6.4, 6U OpenVPX NVIDIA 27.7 TFLOPS per GPU
VPX6-4955 6U OpenVPX Dual NVIDIA Quadro Turing (TU104) RTX5000E GPU Card with 6144 CUDA, 768 Tensor, & 96 RT cores 6U OpenVPX NVIDIA 11.2 TFLOPS per GPU

XMC Graphics & Video Cards

Delivering powerful capability in a minimalistic footprint, these XMC cards add GPU processing without occupying an extra system slot.

Product Image Product Name Description Processor / FPGA PCIe Configuration Data Sheet
XMC-4701 XMC Capture Card with SDI and Analog Interfaces N/A x4 Gen 2, 4-lane PCIe2
XMC-715 & X-715 N/A N/A N/A
Graphics Software Suite Graphics & Video Drivers with Artifacts for RTOS and Safety-Critical Systems AMD N/A
XMC-4906 NVIDIA Ampere GPU XMC with 2560 CUDA, 80 Tensor, and 20 RT cores NVIDIA 8-lane PCIe3

6U VME Video Windowing Card

Video windowing solutions designed for high-performance, multi-input video window processing.

Product Image Product Name Description Standard Function Inputs Outputs Data Sheet
Cobra2 Video Windowing VME Video Composite, DVI, RGB/VGA, S-Video DVI, RGB/VGA
White Paper
How Can I Teach My Machine to Learn

Like humans, machines learn from experience. They make observations from inputs of images, text, or other data, and then look for patterns. After the machine runs through the mathematical layers, it learns to make better decisions based on the examples it was given.

How Can I Teach My Machine to Learn?
White Paper
How Can I Teach My Machine to Learn

Like humans, machines learn from experience. They make observations from inputs of images, text, or other data, and then look for patterns. After the machine runs through the mathematical layers, it learns to make better decisions based on the examples it was given.

Learn More
White Paper
Enabling AI & Machine Learning: The Role of Tensor Cores

Tensor cores are indispensable for performing the types of calculations needed for artificial intelligence (AI) and machine learning. The role of AI and machine learning in defense applications is on the rise, making tensor cores critical for defense.

wp-fifty-enabling-ai-machine-learning-the-role-of-tensor-cores.png
White Paper
Enabling AI & Machine Learning: The Role of Tensor Cores

Tensor cores are indispensable for performing the types of calculations needed for artificial intelligence (AI) and machine learning. The role of AI and machine learning in defense applications is on the rise, making tensor cores critical for defense.

Learn More
White Paper
Meeting DAL A Challenges with Dissimilar Redundant Architecture

This white paper examines how building a system with a dissimilar redundant architecture can help overcome the challenges of meeting DO-254/178 DAL A requirements.

Meeting DAL A Challenges with Dissimilar Redundant Architecture
White Paper
Meeting DAL A Challenges with Dissimilar Redundant Architecture

This white paper examines how building a system with a dissimilar redundant architecture can help overcome the challenges of meeting DO-254/178 DAL A requirements.

Learn More
White Paper
Enabling AI at the Network Edge of the Battlefield

This white paper describes how modern AI technology can benefit the warfighter as embedded solutions at the network edge are deployed for military and aerospace platforms. Edge computing brings data storage and computation closer to where it's needed.

Enabling AI at the Network Edge of the Battlefield
White Paper
Enabling AI at the Network Edge of the Battlefield

This white paper describes how modern AI technology can benefit the warfighter as embedded solutions at the network edge are deployed for military and aerospace platforms. Edge computing brings data storage and computation closer to where it's needed.

Learn More
Case Study
Airborne Signal Processing and Display Computer

An extended-service marine patrol aircraft required a signal processing and display computer to provide an upgrade in capability and performance. Learn about the solution Curtiss-Wright provided.

Airborne Signal Processing and Display Computer
Case Study
Airborne Signal Processing and Display Computer

An extended-service marine patrol aircraft required a signal processing and display computer to provide an upgrade in capability and performance. Learn about the solution Curtiss-Wright provided.

Learn More
White Paper
Simplifying Sensor Data Processing With Advanced GPGPU Technology and COTS Building Blocks

This white paper looks at how standards-based, pre-integrated, and prevalidated Commercial-Off-The-Shelf (COTS) building blocks can reduce program risk, expedite development-to-deployment, and create quality, affordable High-Performance Embedded Computing

Simplifying Sensor Data Processing With Advanced GPGPU Technology and COTS Building Blocks
White Paper
Simplifying Sensor Data Processing With Advanced GPGPU Technology and COTS Building Blocks

This white paper looks at how standards-based, pre-integrated, and prevalidated Commercial-Off-The-Shelf (COTS) building blocks can reduce program risk, expedite development-to-deployment, and create quality, affordable High-Performance Embedded Computing

Learn More