English
Related papers

Related papers: CIDER: Boosting Memory-Disaggregated Key-Value Sto…

200 papers

Sparse deep learning has reduced computation significantly, but its irregular non-zero data distribution complicates the data flow and hinders data reuse, increasing on-chip SRAM access and thus power consumption of the chip. This paper…

Hardware Architecture · Computer Science 2025-03-26 Kai-Chieh Hsu , Tian-Sheuan Chang

Large language models (LLMs) demonstrate remarkable capabilities but face substantial serving costs due to their high memory demands, with the key-value (KV) cache being a primary bottleneck. State-of-the-art KV cache compression…

Machine Learning · Computer Science 2025-09-03 Yanqi Zhang , Yuwei Hu , Runyuan Zhao , John C. S. Lui , Haibo Chen

A superoptimizing compiler--one that performs a meaningful search of the program space as part of the optimization process--can find optimization opportunities that are missed by even the best existing optimizing compilers. We created…

Programming Languages · Computer Science 2024-09-04 Zhengyang Liu , Stefan Mada , John Regehr

Many computational factors limit broader deployment of large language models. In this paper, we focus on a memory bottleneck imposed by the key-value (KV) cache, a computational shortcut that requires storing previous KV pairs during…

Machine Learning · Computer Science 2024-06-13 Harry Dong , Xinyu Yang , Zhenyu Zhang , Zhangyang Wang , Yuejie Chi , Beidi Chen

Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-04-14 Yuzhen Mao , Qitong Wang , Martin Ester , Ke Li

Distributed optimization is the standard way of speeding up machine learning training, and most of the research in the area focuses on distributed first-order, gradient-based methods. Yet, there are settings where some…

Machine Learning · Computer Science 2025-11-03 Matin Ansaripour , Shayan Talaei , Giorgi Nadiradze , Dan Alistarh

Emerging non-volatile memory (NVM)-based Computing-in-Memory (CiM) architectures show substantial promise in accelerating deep neural networks (DNNs) due to their exceptional energy efficiency. However, NVM devices are prone to device…

Machine Learning · Computer Science 2023-12-12 Zheyu Yan , Xiaobo Sharon Hu , Yiyu Shi

We present Keigo, a concurrency- and workload-aware storage middleware that enhances the performance of log-structured merge key-value stores (LSM KVS) when they are deployed on a hierarchy of storage devices. The key observation behind…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-18 Rúben Adão , Zhongjie Wu , Changjun Zhou , Oana Balmau , João Paulo , Ricardo Macedo

Constrained devices, such as smart sensors, wearable devices, and Internet of Things nodes, are increasingly prevalent in society and rely on secure communications to function properly. These devices often operate autonomously, exchanging…

Fault-tolerant distributed applications require mechanisms to recover data lost via a process failure. On modern cluster systems it is typically impractical to request replacement resources after such a failure. Therefore, applications have…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-01-26 Lukas Hübner , Demian Hespe , Peter Sanders , Alexandros Stamatakis

Disaggregated inference has become an essential framework that separates the prefill (P) and decode (D) stages in large language model inference to improve throughput. However, the KV cache transfer faces significant delays between prefill…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-08 Weiqing Li , Guochao Jiang , Xiangyong Ding , Zhangcheng Tao , Chuzhan Hao , Chenfeng Xu , Yuewei Zhang , Hao Wang

Quantum key distribution (QKD) is a promising technique for secure communication based on quantum mechanical principles. To improve the secure key rate of a QKD system, most studies on reconciliation primarily focused on improving the…

Quantum Physics · Physics 2021-09-21 Hao-Kun Mao , Qiong Li , Peng-Lei Hao , Bassem Abd-El-Atty , Abdullah M. Iliyasu

Computing-in-Memory (CIM) macros have gained popularity for deep learning acceleration due to their highly parallel computation and low power consumption. However, limited macro size and ADC precision introduce throughput and accuracy…

Hardware Architecture · Computer Science 2026-05-01 Ming-Han Lin , Tian-Sheuan Chang

Memory disaggregation architecture physically separates CPU and memory into independent components, which are connected via high-speed RDMA networks, greatly improving resource utilization of databases. However, such an architecture poses…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-12-21 Qing Wang , Youyou Lu , Jiwu Shu

Digital Compute-in-Memory (CIM) architectures have shown great promise in Deep Neural Network (DNN) acceleration by effectively addressing the "memory wall" bottleneck. However, the development and optimization of digital CIM accelerators…

Hardware Architecture · Computer Science 2025-05-05 Yingjie Qi , Jianlei Yang , Yiou Wang , Yikun Wang , Dayu Wang , Ling Tang , Cenlin Duan , Xiaolin He , Weisheng Zhao

The "Disaggregated Server" concept has been proposed for datacenters where the same type server resources are aggregated in their respective pools, for example a compute pool, memory pool, network pool, and a storage pool. Each server is…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-03-09 Bulent Abali , Richard J. Eickemeyer , Hubertus Franke , Chung-Sheng Li , Marc A. Taubenblatt

Large language models cache all previously computed key-value (KV) pairs during generation, and this KV cache grows linearly with sequence length, making it a primary memory bottleneck for serving. Quantizing the KV cache to fewer bits…

Machine Learning · Computer Science 2026-05-11 Fei Zuo , Zikang Zhou , Hao Cong , Xiaoyan Xi , Ho Fai Leung

Key-Value Stores (KVS) implemented with log-structured merge-tree (LSM-tree) have gained widespread acceptance in storage systems. Nonetheless, a significant challenge arises in the form of high write amplification due to the compaction…

Databases · Computer Science 2025-08-20 Jianshun Zhang , Fang Wang , Sheng Qiu , Yi Wang , Jiaxin Ou , Junxun Huang , Baoquan Li , Peng Fang , Dan Feng

Massive amounts of data have led to the training of large-scale machine learning models on a single worker inefficient. Distributed machine learning methods such as Parallel-SGD have received significant interest as a solution to tackle…

Machine Learning · Computer Science 2022-03-31 S Vineeth

Software-controlled heterogeneous memory systems have the potential to improve performance, efficiency, and cost tradeoffs in emerging systems. Delivering on this promise requires an efficient operating system (OS) mechanisms and policies…

Operating Systems · Computer Science 2020-04-13 Sudarsun Kannan , Yujie Ren , Abhishek Bhatacharjee