Approximate computing has emerged as a new paradigm for high-performance and energy-
efficient design of circuits and systems. For the many approximate arithmetic circuits …

The low communication bandwidth between memory and processing units in conventional
von Neumann machines does not support the requirements of emerging applications that …

Hardware acceleration of Deep Neural Networks (DNNs) aims to tame their enormous
compute intensity. Fully realizing the potential of acceleration in this domain requires …

Domain-specific hardware accelerators Page 1 48 COMMUNICATIONS OF THE ACM | JULY
2020 | VOL. 63 | NO. 7 contributed articles FROM THE SIMPLE embedded processor in your …

Datacenter applications demand microsecond-scale tail latencies and high request rates
from operating systems, and most applications handle loads that have high variance over …

Deep Neural Networks (DNNs) are compute-intensive learning models with growing
applicability in a wide range of domains. FPGAs are an attractive choice for DNNs since they …

Many companies are deploying services, either for consumers or industry, which are largely
based on machine-learning algorithms for sophisticated processing of large amounts of …

Motivated by the variance in the numerical precision requirements of Deep Neural Networks
(DNNs)[1],[2], Stripes (STR), a hardware accelerator is presented whose execution time …

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 …

We describe a 7-nm predictive process design kit (PDK) called the ASAP7 PDK, developed
in collaboration with ARM Ltd. for academic use. The PDK is realistic, based on current …