Low-precision techniques can effectively reduce the computational complexity and bandwidth requirements of a convolutional neural network (CNN) infere......
The performance of lossy data-center networks (DCNs) may degrade due to packet dropping (and possible retransmission) under congestion. In this articl......
Systolic array architecture is widely used in spatial hardware and well-suited for many tensor processing algorithms. Many systolic array architecture......
For nonvolatile main memory (NVMM), both security and endurance are important. However, the diffusion property of memory encryption renders existing b......
Emerging nonmemory technologies have been widely employed in intermittently powered the Internet of Things (IoT) devices to bridge program execution a......
Computing-in-memory (CiM) is a popular design alternative to overcome the von Neumann bottleneck and improve the performance of artificial intelligenc......
Since its invention half a century ago, dynamic random access memory (DRAM) has required dynamic refresh operations that block read accesses to refres......
Massive amounts of multi-sensor information pose a huge computational challenge for the design of a real-time automated driving module. The proposed h......
In this work, we design a programmable analog calculation unit (ACU) for approximately computing arbitrary functions with two operands. By implementin......
Battery-less IoT devices powered through energy harvesting face a fundamental imbalance between the potential volume of collected data and the amount ......
DESIGNERS MAKING DEEP LEARNING COMPUTING MORE EFFICIENT CANNOT RELY SOLELY ON HARDWARE. INCORPORATING SOFTWARE-OPTIMIZATION TECHNIQUES SUCH AS MODEL C......
This article presents an efficient dataflow methodology for solving Euler atmospheric dynamic equations. The authors map a complex Euler stencil kerne......
