AI Inference at the Rugged Edge: Meeting Performance with M.2 Accelerators
September 29, 2022
The world of computing technology maintains a high bar for innovation, with systems continually becoming faster and more efficient. Think Moore’s Law and the steadfast expectation that CPU capabilities will naturally improve at a structured pace. And so they have…a reality amplified through smart design strategies developed to accommodate specific workloads. Developers and designers have found ways for systems to do more, pairing CPUs with floating point processors or adding GPUs to offload graphics-intensive processing applications like deep neural networks.
Today, groundbreaking applications like artificial intelligence (AI) and machine learning are bringing a new dose of reality to these design strategies. It’s not just the data-intensive nature of automation that is causing change – it’s where it is being implemented. As applications move out of the data center and into the world, more and more industrial and non-traditional computing settings are seeking greater competitive value from data in real-time. This can be defined as the rugged edge, and it is here that performance acceleration requires a new path.