English
Related papers

Related papers: RECIPE : Converting Concurrent DRAM Indexes to Per…

200 papers

Neural networks (NNs) are growing in importance and complexity. A neural network's performance (and energy efficiency) can be bound either by computation or memory resources. The processing-in-memory (PIM) paradigm, where computation is…

Hardware Architecture · Computer Science 2023-03-28 Geraldo F. Oliveira , Juan Gómez-Luna , Saugata Ghose , Amirali Boroumand , Onur Mutlu

Byte-addressable non-volatile memory (NVM) sitting on the memory bus is employed to make persistent memory (PMem) in general-purpose computing systems and embedded systems for data storage. Researchers develop software drivers such as the…

Hardware Architecture · Computer Science 2024-03-12 Qing Xu , Qisheng Jiang , Chundong Wang

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…

Machine Learning · Computer Science 2021-02-16 Heesu Kim , Hanmin Park , Taehyun Kim , Kwanheum Cho , Eojin Lee , Soojung Ryu , Hyuk-Jae Lee , Kiyoung Choi , Jinho Lee

Indexes are models: a B-Tree-Index can be seen as a model to map a key to the position of a record within a sorted array, a Hash-Index as a model to map a key to a position of a record within an unsorted array, and a BitMap-Index as a model…

Databases · Computer Science 2018-05-01 Tim Kraska , Alex Beutel , Ed H. Chi , Jeffrey Dean , Neoklis Polyzotis

The rapid development of multi-core system and increase of data-intensive application in recent years call for larger main memory. Traditional DRAM memory can increase its capacity by reducing the feature size of storage cell. Now further…

Hardware Architecture · Computer Science 2016-06-13 Shenchen Ruan , Haixia Wang , Dongsheng Wang

The recent development of differentiable simulation codes for particle accelerators has enabled gradient-based workflows that promise finer control and more realistic modeling of accelerator facilities. However, when using reverse-mode…

Learned indexes have attracted significant research interest due to their ability to offer better space-time trade-offs compared to traditional B+-tree variants. Among various learned indexes, the PGM-Index based on error-bounded piecewise…

Databases · Computer Science 2024-10-02 Qiyu Liu , Siyuan Han , Yanlin Qi , Jingshu Peng , Jin Li , Longlong Lin , Lei Chen

The Transformer-based detectors (i.e., DETR) have demonstrated impressive performance on end-to-end object detection. However, transferring DETR to different data distributions may lead to a significant performance degradation. Existing…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Peidong Jia , Jiaming Liu , Senqiao Yang , Jiarui Wu , Xiaodong Xie , Shanghang Zhang

As machine learning algorithms are shown to be an increasingly valuable tool, the demand for their access has grown accordingly. Oftentimes, it is infeasible to run inference with larger models without an accelerator, which may be…

Machine Learning · Computer Science 2025-06-03 Spencer Banasik

Processing-in-memory (PIM) reduces data movement by executing near memory, but our large-scale characterization on real PIM hardware shows that end-to-end performance is often limited by disjoint host and device address spaces that force…

Emerging Technologies · Computer Science 2025-11-20 I-Ting Lee , Bao-Kai Wang , Liang-Chi Chen , Wen Sheng Lim , Da-Wei Chang , Yu-Ming Chang , Chieng-Chung Ho

AI clusters today are one of the major uses of High Bandwidth Memory (HBM). However, HBM is suboptimal for AI workloads for several reasons. Analysis shows HBM is overprovisioned on write performance, but underprovisioned on density and…

Storage Class Memory (SCM) is a class of memory technology which has recently become viable for use. Their namearises from the fact that they exhibit non-volatility of data, similar to secondary storage while also having latencies…

Hardware Architecture · Computer Science 2019-09-27 Aditya K Kamath , Leslie Monis , A Tarun Karthik , Basavaraj Talawar

Non-volatile random access memory (NVRAM) offers byte-addressable persistence at speeds comparable to DRAM. However, with caches remaining volatile, automatic cache evictions can reorder updates to memory, potentially leaving persistent…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-08-20 Yuanhao Wei , Naama Ben-David , Michal Friedman , Guy E. Blelloch , Erez Petrank

Despite their impressive performance on complex tasks, current language models (LMs) typically operate in a vacuum: Each input query is processed separately, without retaining insights from previous attempts. Here, we present Dynamic…

Machine Learning · Computer Science 2025-04-11 Mirac Suzgun , Mert Yuksekgonul , Federico Bianchi , Dan Jurafsky , James Zou

Index structures are important for efficient data access, which have been widely used to improve the performance in many in-memory systems. Due to high in-memory overheads, traditional index structures become difficult to process the…

Databases · Computer Science 2019-05-16 Pengfei Li , Yu Hua , Pengfei Zuo , Jingnan Jia

Even with generational improvements in DRAM technology, memory access latency still remains the major bottleneck for application accelerators, primarily due to limitations in memory interface IPs which cannot fully account for variations in…

Hardware Architecture · Computer Science 2021-08-24 Sasindu Wijeratne , Sanket Pattnaik , Zhiyu Chen , Rajgopal Kannan , Viktor Prasanna

The substantial memory requirements of Large Language Models (LLMs), particularly for long-context fine-tuning, have renewed interest in CPU offloading to augment limited GPU memory. However, as context lengths grow, relying on CPU memory…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-31 Yong-Cheng Liaw , Shuo-Han Chen

The rapid growth of LLMs has revolutionized natural language processing and AI analysis, but their increasing size and memory demands present significant challenges. A common solution is to spill over to CPU memory; however, traditional…

Machine Learning · Computer Science 2024-11-15 Yi Xu , Ziming Mao , Xiangxi Mo , Shu Liu , Ion Stoica

As dynamic random access memory (DRAM) and other current transistor-based memories approach their scalability limits, the search for alternative storage methods becomes increasingly urgent. Phase-change memory (PCM) emerges as a promising…

Hardware Architecture · Computer Science 2025-11-10 Mahek Desai , Rowena Quinn , Marjan Asadinia

Data structures used in software development have inbuilt redundancy to improve software reliability and to speed up performance. Examples include a Doubly Linked List which allows a faster deletion due to the presence of the previous…

Databases · Computer Science 2025-08-05 Pratyush Mahapatra , Mark D. Hill , Michael M. Swift