In 1977, John Backus wrote a seminal paper titled, Can Programming Be Liberated From the von Neumann Style? In this paper, Backus defined the implications of what we refer to today as the “memory ...

From a conceptual standpoint, the idea of embedding processing within main memory makes logical sense since it would eliminate many layers of latency between compute and memory in modern systems and ...

Figure 1: The declarative versus nondeclarative memory account. In this Perspective, I review data showing that different types of memory are not solely distinguishable on the basis of consciousness ...

New memory-centric chip technologies are emerging that promise to solve the bandwidth bottleneck issues in today’s systems. The idea behind these technologies is to bring the memory closer to the ...

There are a host of hardware accelerators for various machine-learning ML models. To wit, Renesas has come up with a ternary SRAM-based system to accelerate convolutional-neural-network (CNN) ...

The cost associated with moving data in and out of memory is becoming prohibitive, both in terms of performance and power, and it is being made worse by the data locality in algorithms, which limits ...

First and foremost, we breathe in order to absorb oxygen—but this vital rhythm could also have other functions. Over the past ...

Part one of this two-part article discussed current trends impacting the evolution of data processing architectures, including the implications of higher transistor budgets afforded by Moore’s Law, ...