In recent years, the limits of the multicore approach emerged in the so-called “dark silicon”
issue and diminishing returns of an ever-increasing core count. Hardware manufacturers …

Modern computing systems are overwhelmingly designed to move data to computation. This
design choice goes directly against at least three key trends in computing that cause …

Many modern workloads, such as neural networks, databases, and graph processing, are
fundamentally memory-bound. For such workloads, the data movement between main …

The “memory wall” problem or so-called von Neumann bottleneck limits the efficiency of
conventional computer architectures, which move data from memory to CPU for …

Graph convolutional neural networks (GCNs) have emerged as an effective approach to
extend deep learning for graph data analytics. Given that graphs are usually irregular, as …

Simple graph algorithms such as PageRank have been the target of numerous hardware
accelerators. Yet, there also exist much more complex graph mining algorithms for problems …

Data movement between the CPU and main memory is a first-order obstacle against improv
ing performance, scalability, and energy efficiency in modern systems. Computer systems …

Many modern workloads, such as neural networks, databases, and graph processing, are
fundamentally memory-bound. For such workloads, the data movement between main …

Memory-bound sparse gathering, caused by irregular random memory accesses, has
become an obstacle in several on-demand applications such as embedding lookup in …

Near-Data-Processing (NDP) architectures present a promising way to alleviate data
movement costs and can provide significant performance and energy benefits to parallel …