Specialized hardware solves high-order optimization problems with in-memory computing

The rise of AI, graphic processing, combinatorial optimization and other data-intensive applications has resulted in data-processing bottlenecks, as ever greater amounts of data must be shuttled back and forth between the memory and compute elements in a computer. The physical distance is small, but the process can occur billions of times per second. Inevitably, the energy and time required to move so much data adds up. In response, computer engineers are designing specialized hardware accelerators with innovative architectures to improve the performance of such applications.

Read Full Article