SAN FRANCISCO, Oct. 25, 2019 — Micron Technology, today announced a powerful new set of high-performance hardware and software tools for deep learning applications with the acquisition of FWDNXT, a software and hardware startup. When combined with advanced Micron memory, FWDNXT’s (pronounced “forward next”) artificial intelligence (AI) hardware and software technology enables Micron to explore deep learning solutions required for data analytics, particularly in IoT and edge computing. With this acquisition, Micron is integrating compute, memory, tools and software into a comprehensive AI development platform. This platform in turn provides the key building blocks required to explore innovative memory optimized for AI workloads.
“FWDNXT is an architecture designed to create fast-time-to-market edge AI solutions through an extremely easy to use software framework with broad modeling support and flexibility,” said Micron Executive Vice President and Chief Business Officer Sumit Sadana. “FWDNXT’s five generations of machine learning inference engine development and neural network algorithms, combined with Micron’s deep memory expertise, unlocks new power and performance capabilities to enable innovation for the most complex and demanding edge applications.”
Bringing Memory and Compute Together With Micron DLA Technology
FWDNXT provides efficient and high-performance hardware and software solutions based on deep learning and neural networks. As companies develop more complex AI and machine learning systems, the hardware used to train and run those models becomes increasingly important.
The Micron Deep Learning Accelerator (DLA) technology, powered by the AI inference engine from FWDNXT, equips Micron with the tools to observe, assess and ultimately develop innovation that brings memory and computing closer together, resulting in higher performance and lower power.
Micron’s DLA technology provides an easy-to-use software programmable platform that supports a broad range of machine learning frameworks and neural networks and allows for processing vast amounts of data quickly in an easy-to-use interface.
Using CNNs Running on DLA To Gain New Insights
Micron’s DLA can consume massive amounts of data and then return insights that launch discoveries. For example, Micron is collaborating with doctors and researchers at Oregon Health & Science University to use convolutional neural networks (CNNs) running on DLA to process and analyze 3D electron microscopy images. The goal of this collaboration is to discover new insights for treating cancer. Micron is also partnering with physicists at leading nuclear research organizations who are experimenting with DLA-based CNNs to classify the results of high energy-particle collisions in near real time and detect rare particle interactions that are believed to occur in nature.