Certifying Multi-Core Processing Following AMC 20-193/AC 20-193 Objectives
This white paper examines the key challenges multi-core processors present in safety-certifiable systems, and the traditional and newer, more effective techniques for alleviating them to ensure MCP-based systems will safely perform their intended functions.
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.
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.
Comparing CPUs and GPUs for Deep Learning and Artificial Intelligence
Which is better for machine learning applications, 2nd Generation Intel Xeon Scalable Processors or NVIDIA’s T4? A head-to-head comparison helps explain whether you should choose a CPU or a GPU for your high-performance machine learning solution.
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.
Optimizing PCIe Communications through Device Lending and Multicast with Dolphin PCIe Fabric Library
In the third paper in our series, we cover additional features of the Dolphin PCIe Fabric Communications Library that help minimizes latency, maximize system bandwidth, and optimize configuration flexibility.
Minimizing Latency in Peer-to-Peer Communications with Dolphin PCIe Fabric Library
In this second white paper in our two-part series, we present several different software interfaces provided for applications development, comparing their advantages and tradeoffs. Finally, we present performance benchmarks using a variety of Curtiss-Wright.