English
Related papers

Related papers: MemPool-3D: Boosting Performance and Efficiency of…

200 papers

Latency and energy consumption are key metrics in the performance of deep neural network (DNN) accelerators. A significant factor contributing to latency and energy is data transfers. One method to reduce transfers or data is reusing data…

Hardware Architecture · Computer Science 2024-10-15 Michael Gilbert , Yannan Nellie Wu , Joel S. Emer , Vivienne Sze

Achieving high compute utilization across a wide range of AI workloads is crucial for the efficiency of versatile DNN accelerators. This paper presents the Voltra chip and its utilization-optimised DNN accelerator architecture, which…

Hardware Architecture · Computer Science 2026-02-13 Xiaoling Yi , Ryan Antonio , Yunhao Deng , Fanchen Kong , Joren Dumoulin , Jun Yin , Marian Verhelst

Processing-in-memory (PIM) is a promising computing paradigm to tackle the "memory wall" challenge. However, PIM system-level benefits over traditional von Neumann architecture can be reduced when the memory array cannot fully store all the…

Hardware Architecture · Computer Science 2025-03-03 Peilin Chen , Xiaoxuan Yang

Monolithic 3D (M3D) technology enables high density integration, performance, and energy-efficiency by sequentially stacking tiers on top of each other. M3D-based network-on-chip (NoC) architectures can exploit these benefits by adopting…

Emerging Technologies · Computer Science 2019-06-12 Shouvik Musavvir , Anwesha Chatterjee , Ryan Gary Kim , Dae Hyun Kim , Partha Pratim Pande

Poor DRAM technology scaling over the course of many years has caused DRAM-based main memory to increasingly become a larger system bottleneck. A major reason for the bottleneck is that data stored within DRAM must be moved across a…

Hardware Architecture · Computer Science 2018-02-02 Saugata Ghose , Kevin Hsieh , Amirali Boroumand , Rachata Ausavarungnirun , Onur Mutlu

As the demand for high-speed and low-power electronics continues to grow, the quasi-delay-insensitive (QDI) asynchronous domain of digital design has emerged as a promising alternative to traditional clock-based designs. However, the…

Hardware Architecture · Computer Science 2026-05-05 Xiameng Zhang , Kushal Ponugoti , Ashiq Sakib , Madhava Vemuri

Monolithic three-dimensional integration of memory and logic circuits could dramatically improve performance and energy efficiency of computing systems. Some conventional and emerging memories are suitable for vertical integration,…

Emerging Technologies · Computer Science 2015-09-11 Gina C. Adam , Brian D. Hoskins , Mirko Prezioso , Dmitri B. Strukov

3D die stacking and 2.5D interposer design are promising technologies to improve integration density, performance and cost. Current approaches face serious issues in dealing with emerging security challenges such as side channel attacks,…

Cryptography and Security · Computer Science 2025-08-28 Peng Gu , Shuangchen Li , Dylan Stow , Russell Barnes , Liu Liu , Yuan Xie , Eren Kursshan

Large-scale HPC simulations of plasma dynamics in fusion devices require efficient parallel I/O to avoid slowing down the simulation and to enable the post-processing of critical information. Such complex simulations lacking parallel I/O…

Transformer-based models dominate modern AI workloads but exacerbate memory bottlenecks due to their quadratic attention complexity and ever-growing model sizes. Existing accelerators, such as Groq and Cerebras, mitigate off-chip traffic…

Hardware Architecture · Computer Science 2026-02-12 Jinxin Yu , Yudong Pan , Mengdi Wang , Huawei Li , Yinhe Han , Xiaowei Li , Ying Wang

Today every circuit has to face the power consumption issue for both portable device aiming at large battery life and high end circuits avoiding cooling packages and reliability issues that are too complex. It is generally accepted that…

Hardware Architecture · Computer Science 2010-07-15 C. N. Marimuthu , P. Thangaraj , Aswathy Ramesan

Lattice Boltzmann method (LBM) is a promising approach to solving Computational Fluid Dynamics (CFD) problems, however, its nature of memory-boundness limits nearly all LBM algorithms' performance on modern computer architectures. This…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-08-11 Yuankun Fu , Fengguang Song

Memcomputing is a novel paradigm of computation that utilizes dynamical elements with memory to both store and process information on the same physical location. Its building blocks can be fabricated in hardware with standard electronic…

Emerging Technologies · Computer Science 2018-07-03 Forrest Sheldon , Pietro Cicotti , Fabio L. Traversa , Massimiliano Di Ventra

Embedding representations power machine intelligence in many applications, including recommendation systems, but they are space intensive -- potentially occupying hundreds of gigabytes in large-scale settings. To help manage this outsized…

Machine Learning · Computer Science 2021-02-09 Antonio Ginart , Maxim Naumov , Dheevatsa Mudigere , Jiyan Yang , James Zou

The ever increasing demand for ML-driven intelligence in a wide spectrum of domains has led to ubiquity of GPUs. At the same time, GPUs are notorious for their power consumption needs and often dominate power allocation in a typical ML…

Hardware Architecture · Computer Science 2026-05-22 Shaizeen Aga , Mohamed Assem Ibrahim

High-Performance Computing (HPC) and Artificial Intelligence (AI) workloads typically demand substantial memory bandwidth and, to a degree, memory capacity. CXL memory expansion modules, also known as CXL "type-3" devices, enable…

Operating Systems · Computer Science 2024-12-18 Rohit Sehgal , Vishal Tanna , Vinicius Petrucci , Anil Godbole

We present four high performance hybrid sorting methods developed for various parallel platforms: shared memory multiprocessors, distributed multiprocessors, and clusters taking advantage of existence of both shared and distributed memory.…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-03-04 Thoria Alghamdi , Gita Alaghband

Implementing embedded neural network processing at the edge requires efficient hardware acceleration that couples high computational performance with low power consumption. Driven by the rapid evolution of network architectures and their…

Hardware Architecture · Computer Science 2021-06-25 Petar Jokic , Erfan Azarkhish , Andrea Bonetti , Marc Pons , Stephane Emery , Luca Benini

According to the increasing complexity of network application and internet traffic, network processor as a subset of embedded processors have to process more computation intensive tasks. By scaling down the feature size and emersion of chip…

Hardware Architecture · Computer Science 2012-04-13 Mehdi Alipour , Hojjat Taghdisi

Public cloud providers seek to meet stringent performance requirements and low hardware cost. A key driver of performance and cost is main memory. Memory pooling promises to improve DRAM utilization and thereby reduce costs. However,…

‹ Prev 1 3 4 5 6 7 10 Next ›