Related papers: Apparate: Evading Memory Hierarchy with GodSpeed W…
In-memory computing is a promising alternative to traditional computer designs, as it helps overcome performance limits caused by the separation of memory and processing units. However, many current approaches struggle with unreliable…
With the great success of artificial intelligence (AI) technologies in pattern recognitions and signal processing, it is interesting to introduce AI technologies into wireless communication systems. Currently, most of studies are focused on…
The never-ending demand for high performance and energy efficiency is pushing designers towards an increasing level of heterogeneity and specialization in modern computing systems. In such systems, creating efficient memory architectures is…
The rapid development of chargeable devices has caused a great deal of interest in efficient and stable wireless power transfer (WPT) solutions. Most conventional WPT technologies exploit outdated electromagnetic field control methods…
The advancements in microwave power transfer (MPT) over past decades have enabled wireless power transfer over long distances. The latest breakthroughs in wireless communication, namely massive MIMO, small cells and millimeter-wave…
Quantum computing is poised to redefine the algorithmic foundations of communication systems. While quantum superposition and entanglement enable quadratic or exponential speedups for specific problems, identifying use cases where these…
Putting the DRAM on the same package with a processor enables several times higher memory bandwidth than conventional off-package DRAM. Yet, the latency of in-package DRAM is not appreciably lower than that of off-package DRAM. A promising…
The present von Neumann computing paradigm involves a significant amount of information transfer between a central processing unit (CPU) and memory, with concomitant limitations in the actual execution speed. However, it has been recently…
Cellular data traffic almost doubles every year, greatly straining network capacity. The main driver for this development is wireless video. Traditional methods for capacity increase (like using more spectrum and increasing base station…
Over the past two decades, the storage capacity and access bandwidth of main memory have improved tremendously, by 128x and 20x, respectively. These improvements are mainly due to the continuous technology scaling of DRAM (dynamic…
Recent advances in reprogrammable hardware (e.g., FPGAs) and memory technology (e.g., DDR4, HBM) promise to solve performance problems inherent to graph processing like irregular memory access patterns on traditional hardware (e.g., CPU).…
The quest for energy-efficient, scalable neuromorphic computing has elevated compute-in-memory (CIM) architectures to the forefront of hardware innovation. While memristive memories have been extensively explored for synaptic implementation…
A main challenge of 5G and beyond wireless systems is to efficiently utilize the available spectrum and simultaneously reduce the energy consumption. From the radio resource allocation perspective, the solution to this problem is to…
In this paper, we present GradPIM, a processing-in-memory architecture which accelerates parameter updates of deep neural networks training. As one of processing-in-memory techniques that could be realized in the near future, we propose an…
The rise of generative AI workloads, particularly language model inference, is intensifying on/off-chip memory pressure. Multimodal inputs such as video streams or images and downstream applications like Question Answering (QA) and analysis…
By all measures, wireless networking has seen explosive growth over the past decade. Fourth Generation Long Term Evolution (4G LTE) cellular technology has increased the bandwidth available for smartphones, in essence, delivering broadband…
Emerging applications, such as big data analytics and machine learning, require increasingly large amounts of main memory, often exceeding the capacity of current commodity processors built on DRAM technology. To address this, recent…
We introduce a world vision in which data is endowed with memory. In this data-centric systems paradigm, data items can be enabled to retain all or some of their previous values. We call this ability "remembrance" and posit that it empowers…
The assumption of maximum parallelism support for the successful realization of scalable quantum computers has led to homogeneous, ``sea-of-qubits'' architectures. The resulting architectures overcome the primary challenges of reliability…
Computing has a huge memory problem. The memory system, consisting of multiple technologies at different levels, is responsible for most of the energy consumption, performance bottlenecks, robustness problems, monetary cost, and hardware…