Related papers: Taming Process Variations in CNFET for Efficient L…
Hardware accelerators for convolution neural networks (CNNs) enable real-time applications of artificial intelligence technology. However, most of the existing designs suffer from low hardware utilization or high area cost due to complex…
Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving. Current systems suffer from three compounding inefficiencies: (1) the absence of unified KV cache…
Comparators have multifarious applications in various fields, especially used in analog to digital converters. Over the years, we have seen many different designs of single stage, dynamic latch type and double tail type comparators based on…
Carbon nanotubes (CNTs) have recently attracted attention as materials for flexible thermoelectric devices. To provide theoretical guideline of how defects influence the thermoelectric performance of CNTs, we theoretically studied the…
The inference of ML models composed of diverse structures, types, and sizes boils down to the execution of different dataflows (i.e. different tiling, ordering, parallelism, and shapes). Using the optimal dataflow for every layer of…
With a growing number of cores in modern high-performance servers, effective sharing of the last level cache (LLC) is more critical than ever. The primary agenda of such systems is to maximize performance by efficiently supporting…
Video compression is widely used in digital television, surveillance systems, and virtual reality. Real-time video decoding is crucial in practical scenarios. Recently, neural video compression (NVC) combines traditional coding with deep…
High Performance and Energy Efficiency are critical requirements for Internet of Things (IoT) end-nodes. Exploiting tightly-coupled clusters of programmable processors (CMPs) has recently emerged as a suitable solution to address this…
High performance p- and n-type single-walled carbon nanotube (SWNT) field-effect transistors (FETs) are obtained by using high and low work function metals, Pd and Al as source/drain (S/D) electrodes respectively. Ohmic contacts made to…
Detecting cyberattacks in photovoltaic (PV) monitoring and MPPT control signals requires models that are robust to bias, drift, and transient spikes, yet lightweight enough for resource-constrained edge controllers. While deep learning…
Last Level Cache (LLC) is a precious and critical resource that impacts the performance of applications running on top of CPUs. In this paper, we reveal the significant impact of LLC on the performance of the 5G user plane function (UPF)…
Carbon nanotube (CNT)-polymer composites are widely engineered using surface coatings and chemical treatments to improve interfacial bonding and load transfer. It has been suggested in the nanocomposite literature that nanotube curvature,…
The transient negative capacitance (NC) of solid ferroelectric materials used in field effect transistors can reduce the power dissipation of electronics. Here we show that similar negative capacitance appears in the recently discovered…
The recent research advances in deep learning have led to the development of small and powerful Convolutional Neural Network (CNN) architectures. Meanwhile Field Programmable Gate Arrays (FPGAs) has become a popular hardware target choice…
Recent literature including our past work provide analysis and solutions for using (i) erasure coding, (ii) parallelism, or (iii) variable slicing/chunking (i.e., dividing an object of a specific size into a variable number of smaller…
Key-Value cache (\texttt{KV} \texttt{cache}) compression has emerged as a promising technique to optimize Large Language Model (LLM) serving. It primarily decreases the memory consumption of \texttt{KV} \texttt{cache} to reduce the…
Traditional digital implementations of neural accelerators are limited by high power and area overheads, while analog and non-CMOS implementations suffer from noise, device mismatch, and reliability issues. This paper introduces a CMOS…
Hybrid vision transformers combine the elements of conventional neural networks (NN) and vision transformers (ViT) to enable lightweight and accurate detection. However, several challenges remain for their efficient deployment on…
This paper presents a fully-integrated CMOS voltage reference designed in a 90 nm process node using low voltage threshold (LVT) transistor models. The voltage reference leverages subthreshold operation and near-weak inversion…
The elegant simplicity of the device concept and the urgent need for a new "transistor" at the twilight of Moore's law have inspired many researchers in industry and academia to explore the physics and technology of negative capacitance…