Related papers: Routability in 3D IC Design: Monolithic 3D vs. Sky…
Compute in-memory (CIM) is a promising technique that minimizes data transport, the primary performance bottleneck and energy cost of most data intensive applications. This has found wide-spread adoption in accelerating neural networks for…
3D die-stacked DRAM has emerged as a key technology for delivering high bandwidth and high density for applications such as high-performance computing, graphics, and machine learning. However, different applications place diverse and…
Large-scale artificial intelligence models are transforming industries and redefining human machine collaboration. However, continued scaling exposes critical limitations in hardware, including constraints on computation, bandwidth, and…
Mode-division-multiplexing (MDM) is attractive as a means to increase the link capacity of a single wavelength for optical interconnects via the use of multiple mode-channels in multimode bus waveguide.In order to route the data in MDM…
State-of-the-art all-vanadium redox flow batteries employ porous carbonaceous materials as electrodes. The battery cells possess non-scalable fixed electrodes inserted into a cell stack. In contrast, a conductive particle network dispersed…
In the past few years, we have witnessed an increased interest in the use of 2D materials for the realization of hybrid photonic nonlinear waveguides. Although graphene has attracted most of the attention, other families of 2D materials…
Three-dimensional interconnected nanowire networks have recently attracted notable attention for the fabrication of new devices for energy harvesting/storage, sensing, catalysis, magnetic and spintronic applications and for the design of…
A plethora of two-dimensional (2D) materials entered the physics and engineering scene in the last two decades. Their robust, membrane-like sheet permit -- mostly require -- deposition, giving rise to solid-solid dry interfaces whose bodily…
Transport of ions in molecular-scale confined spaces is central to all aspects of life and technology: into a crack, it may break steel within days; through a membrane separator, it determines the efficiency of electrochemical energy…
Memory system is often the main bottleneck in chipmultiprocessor (CMP) systems in terms of latency, bandwidth and efficiency, and recently additionally facing capacity and power problems in an era of big data. A lot of research works have…
As the modern CPU, GPU, and NPU chip design complexity and transistor counts keep increasing, and with the relentless shrinking of semiconductor technology nodes to nearly 1 nanometer, the placement and routing have gradually become the two…
Understanding depairing effects in a hybrid-superconducting interface utilizing high spin-orbit materials such as topological insulators or 1D semiconducting nanowires is becoming an important research topic in the study of…
With the globalization of manufacturing and supply chains, ensuring the security and trustworthiness of ICs has become an urgent challenge. Split manufacturing (SM) and layout camouflaging (LC) are promising techniques to protect the…
The rising use of deep learning and other big-data algorithms has led to an increasing demand for hardware platforms that are computationally powerful, yet energy-efficient. Due to the amount of data parallelism in these algorithms,…
The present work experimentally demonstrates the fabrication of CVD grown monolayer MoS2 ultra thin quantum well based double barrier resonant tunneling device (RTD) architecture well compatible with conventional CMOS fabrication…
As artificial intelligence (AI) and machine learning (ML) technologies disrupt a wide range of industries, cloud datacenters face ever-increasing demand in inference workloads. However, conventional CPU-based servers cannot handle excessive…
Hierarchical ring networks, which hierarchically connect multiple levels of rings, have been proposed in the past to improve the scalability of ring interconnects, but past hierarchical ring designs sacrifice some of the key benefits of…
The heterogeneous integration of silicon with III-V materials provides a way to overcome silicon's limited optical properties toward a broad range of photonic applications. Hybrid modes are a promising way to make heterogeneous Si/III-V…
The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale model training and evaluation. We set out to simplify this…
Spiking neural networks (SNNs) are powerful models of spatiotemporal computation and are well suited for deployment on resource-constrained edge devices and neuromorphic hardware due to their low power consumption. Leveraging attention…