Artificial Intelligence (AI)

We are seeing a New Age of AI Processing beginning to impact all areas of society. These incredible advances are built on decades of research into neuromorphic processing and Neural Net modeling, which when combined with the massive amounts of data available to train these models result in new tools with amazing emergent characteristics.

These models contain billions of parameters which comprise the inference engines of the models, and require more complex GPU and CPU clusters and databanks to run. To overcome the speed, energy and memory bottleneck changes of these models we are also seeing an explosion of new AI processor architectures coming on the scene – generally available ones like from NVIDIA as well as custom in-house processors for Google, Meta, Intel and others. New startups entering the AI processor space with their own ideas for how to increase efficiency, model size, clustering and scaling are also emerging. And with scale comes concerns over system reliability, fault tolerance, energy consumption and cost.

The IEEE, in their 2022 Technology Roadmap, talked specifically about the need of a new memory technology that “combines the best features of current memories in a fabrication technology compatible with CMOS process flow and that can be scaled beyond the present limits of SRAM and FLASH…. [and that therefore] development of electrically accessible non-volatile memory with high speed and high density would initiate a revolution in computer architecture.”*

We think that 4DS is potentially that memory, at the right time, for the most important market in the world.

* IEEE, The International Roadmap for Devices and Systems: 2022, “Beyond CMOS”, chapter 1.2.2.