检索结果-内蒙古大学图书馆

IEEE COMPUTER ARCHITECTURE LETTERS 2025年第1期24卷 57-60页

作者： Xia, Qirong Ji, Houxiang Zhou, Yang Kim, Nam Sung Univ Illinois Urbana IL 61801 USA

Data compression has been widely used by datacenters to decrease the consumption of not only the memory and storage capacity but also the interconnect bandwidth. Nonetheless, the CPU cycles consumed for data compression notably contribute to the overall datacenter taxes. To provide a cost-efficient data compression capability for datacenters, Intel has introduced QuickAssist Technology (QAT), a PCIe-attached data-compression accelerator. In this work, we first comprehensively evaluate the compression/decompression performance of the latest on-chip QAT accelerator and then compare it with that of the previous-generation off-chip QAT accelerator. Subsequently, as a compelling application for QAT, we take a Linux memory optimization kernel feature: compressed cache for swap pages (zswap), re-implement it to use QAT efficiently, and then compare the performance of QAT-based zswap with that of CPU-based zswap. Our evaluation shows that the deployment of CPU-based zswap increases the tail latency of a co-running latency-sensitive application, Redis by 3.2-12.1x, while that of QAT-based zswap does not notably increase the tail latency compared to no deployment of zswap.

关键词： System-on-chip Throughput Kernel Linux compression algorithms Benchmark testing Support vector machines Huffman coding Heuristic algorithms Translation Data compression hardware accelerator operating system

来源：评论

学校读者我要写书评

暂无评论

Marmotini: A Weight Density Adaptation Architecture With Hybrid compression Method for Spiking Neural Network

引用

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS 2024年第12期32卷 2293-2302页

作者： Wang, Zilin Zhong, Yi Ou, Zehong Yang, Youming Feng, Shuo Chen, Guang Cui, Xiaoxin Jia, Song Wang, Yuan Peking Univ MPW Ctr Sch Integrated Circuits Key Lab Microelect Devices & Circuits Beijing 100871 Peoples R China Peking Univ Sch Software & Microelect Beijing 102600 Peoples R China Peking Univ Beijing Adv Innovat Ctr Integrated Circuits Beijing 100871 Peoples R China

Brain-inspired spiking neural network (SNN) has recently attracted widespread interest owing to its event-driven nature and relatively low-power hardware for transmitting highly sparse binary spikes. To further improve energy efficiency, some matrix compression algorithms are used for weight storage. However, the weight sparsity of different layers varies greatly. For a multicore neuromorphic system, it is difficult for the same compression algorithm to adapt to all the layers of SNN model. In this work, we propose a weight density adaptation architecture with hybrid compression method for SNN, named Marmotini. It is a multicore heterogeneous design, including three types of cores to complete computation of different weight sparsity. Benefiting from the hybrid compression method, Marmotini minimizes the waste of neurons and weights as much as possible. Besides, for better flexibility, a reconfigurable core that can be configured to compute convolutional layer or fully connected layer is proposed. Implemented on Xilinx Kintex UltraScale XCKU115 field-programmable gate array (FPGA) board, Marmotini can operate at 150-MHz frequency, achieving 244.6-GSOP/s peak performance and 54.1-GSOP/W energy efficiency at 0% spike sparsity.

关键词： Multicore processing Neurons Computer architecture compression algorithms Indexes Convolution Synapses Convolutional neural network field-programmable gate array (FPGA) neuromorphic computing spiking neural network (SNN)

来源：评论

学校读者我要写书评

暂无评论

Huffman Deep compression of Edge Node Data for Reducing IoT Network Traffic

引用

IEEE ACCESS 2024年 12卷 122988-122997页

作者： Said Nasif, Ammar Ali Othman, Zulaiha Samsiah Sani, Nor Kamrul Hasan, Mohammad Abudaqqa, Yousra Univ Kebangsaan Malaysia Fac Informat Sci & Technol Res Ctr Artificial Intelligent Technol Bangi 43600 Selangor Malaysia Univ Kebangsaan Malaysia Fac Informat Sci & Technol Res Ctr Cyber Secur Bangi 43600 Selangor Malaysia

Data compression at the Internet of Things (IoT) edge node aims to minimize data traffic in smart cities. The traditional Huffman Coding Algorithm (HCA) is shown as the most effective compression algorithm for sensor data. However, implementing the algorithm at IoT edge nodes is hindered due to memory limitations;HCA requires a large amount of memory to construct a Huffman tree to compress data. To address this issue, this paper proposes a new lossless Huffman Deep compression (HDC) algorithm that incorporates the sliding window technique to fit in memory, reduces the complexity of the Huffman tree using deep learning pruning and pooling techniques, and uses pattern matching with pattern weights instead of using symbol matching and symbol frequencies in HCA. This paper introduces a sliding window approach to minimize memory usage, leveraging pattern matching and weights for higher compression and employing deep learning techniques to reduce the Huffman tree size through pruning and pooling. Experiments were performed using the Esp8266 MCU IoT node on eight numerical attributes from sensors of six of Malaysia's air pollution station datasets. The findings demonstrate that the HDC algorithm has substantially reduced data size (p-value<0.0005), achieving a higher compression ratio (CR) by 1.4x while reducing data size by up to 59%. Furthermore, this achievement is attained while utilizing less than 80 KB of IoT memory and consuming at most 44 mAmps per slide compression. Moreover, the compression performance correlated linearly with the number of patterns in each sliding window. With such excellent performance, using HDC at IoT edge is a considerable solution to reduce the smart-cities network traffic.

关键词： Internet of Things Entropy Random access memory Symbols Deep learning compression algorithms Wireless sensor networks Smart cities Data compression Traffic control compression data traffic deep learning IoT IoT edge node IoT network pooling pruning sensor smart city WSN

来源：评论

学校读者我要写书评

暂无评论

Data-Aware Adaptive compression for Stream Processing

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第9期36卷 4531-4549页

作者： Zhang, Yu Zhang, Feng Li, Hourun Zhang, Shuhao Guo, Xiaoguang Chen, Yuxing Pan, Anqun Du, Xiaoyong Renmin Univ China Sch Informat Key Lab Data Engn & Knowledge Engn MOE Beijing 100872 Peoples R China Nanyang Technol Univ NTU Sch Comp Sci & Engn SCSE Singapore 639798 Singapore Tencent Inc Database R&D Dept Shenzhen Peoples R China

Stream processing has been in widespread use, and one of the most common application scenarios is SQL query on streams. By 2021, the global deployment of IoT endpoints reached 12.3 billion, indicating a surge in data generation. However, the escalating demands for high throughput and low latency in stream processing systems have posed significant challenges due to the increasing data volume and evolving user requirements. We present a compression-based stream processing engine, called CompressStreamDB, which enables adaptive fine-grained stream processing directly on compressed streams, to significantly enhance the performance of existing stream processing solutions. CompressStreamDB utilizes nine diverse compression methods tailored for different stream data types and integrates a cost model to automatically select the most efficient compression schemes. CompressStreamDB provides high throughput with low latency in stream SQL processing by identifying and eliminating redundant data among streams. Our evaluation demonstrates that CompressStreamDB improves average performance by 3.84x and reduces average delay by 68.0% compared to the state-of-the-art stream processing solution for uncompressed streams, along with 68.7% space savings. Besides, our edge trials show an average throughput/price ratio of 9.95x and a throughput/power ratio of 7.32x compared to the cloud design.

关键词： Encoding compression algorithms Real-time systems Low latency communication Data processing Costs Delays Data compaction and compression stream processing edge computing

来源：评论

学校读者我要写书评

暂无评论

compression of Multichannel Signals With Irregular Sampling Rates and Data Gaps

引用

IEEE ACCESS 2024年 12卷 193195-193211页

作者： Cervenansky, Pablo Martin, Alvaro Seroussi, Gadiel PEDECIBA Informat Montevideo 11800 Uruguay Univ Republica Fac Ingn Inst Comp Montevideo 11300 Uruguay Univ Republica Fac Ingn Inst Ingn Elect Montevideo 11300 Uruguay

In this work, we study the compression of multichannel signals with irregular sampling rates and data gaps. We consider state-of-the-art algorithms, which were originally designed to compress gapless signals with regular sampling, adapt them to operate with signals with irregular sampling rates and data gaps, and then evaluate their performance experimentally, through the compression of signals obtained from real-world datasets. Both the original algorithms and our schemes compress signals by exploiting their temporal, and, in some cases, spatial correlation. They work in a near-lossless fashion, guaranteeing a bounded absolute error between each decompressed sample and its original value. This includes the important lossless compression case, which corresponds to an error bound of zero. Our schemes first encode the position of the gaps, using arithmetic coding combined with a Krichevsky-Trofimov probability assignment on a Markov model, and then encode the data values separately. Our experimental analysis consists of comparing the compression performance of our schemes with each other, and with representative special-purpose and general-purpose lossless compression algorithms. We also measure and compare the schemes' running times, to assess their practicality. From the results we extract some general conclusions: in the lossless case, TS2Diff and LZMA attain the best compression performance, whereas our adaptation of algorithm APCA is preferred for positive error bounds. At the same time, our adaptation of APCA, and TS2Diff, attain some of the best running times.

关键词： Encoding Correlation Image coding Approximation algorithms Data models compression algorithms Principal component analysis Time series analysis Classification algorithms Arrays Multichannel signal compression time series compression near-lossless compression irregular sampling rate data gaps

来源：评论

学校读者我要写书评

暂无评论

DNA Sequences compression algorithms Based on the Two bits Codation Method

DNA Sequences Compression Algorithms Based on the Two bits C...

引用

IEEE International Conference on Bioinformatics and Biomedicine

作者： Bacem Saada Jing Zhang Harbin Engineering University

ISBN: (纸本)9781467368001

Nowadays a large number of DNA sequences is being stored on online databases. To reduce this quantity of information, researchers have been trying to implement new DNA sequences compression techniques based on the LOSSLESS algorithms. In this article we will compare two algorithms using the binary representation of DNA sequences. Those two algorithms are characterized by their ease of implementation. The first one transforms the DNA sequence into extended-ASCII representation while the second algorithm transforms it into a hexadecimal representation. Thereafter, we will apply the RLE technique to further enhance the compression of entire genomes.

关键词： DNA sequences Extended-ASCII code Hexadecimal compression 2-Bits compression method Horizontal compression Vertical compression DNA Sequence Horizontal compression Vertical compression binary representation compression algorithms online databases

来源：评论

学校读者我要写书评

暂无评论

Hybrid-Smash: A Heterogeneous CPU-GPU compression Library

引用

IEEE ACCESS 2024年 12卷 32706-32723页

作者： Penaranda, Cristian Reano, Carlos Silla, Federico Univ Politecn Valencia DISCA Valencia 46022 Spain Univ Valencia Dept Informat ETSE Burjassot 46100 Spain

compression algorithms are widely used to reduce data size and improve application performance. Nevertheless, data compression has a computational cost which can limit its use. GPUs could be leveraged to reduce compression time. However, existing GPU-based compression libraries expect data to compress in GPU memory, although it is usually stored in CPU memory. Additionally, setup time of GPUs could be a problem when compressing small data sizes. In this paper, we implement a new GPU-based compression library. Contrary to existing ones, our library uses data located in CPU memory. Performance results show that, for the same compression algorithms, GPUs are beneficial for larger data sizes whereas smaller data sizes are compressed faster using CPUs. Therefore, we enhance our proposal with Hybrid-Smash: a heterogeneous CPU-GPU compression library, which transparently uses CPU or GPU compression depending on data size, thus improving compression for any data size.

关键词： Graphics processing units Image coding compression algorithms Symbols Proposals Artificial intelligence Parallel processing Performance evaluation Central Processing Unit Hybrid intelligent systems Data systems Size control Lossless compression parallel computing GPU

来源：评论

学校读者我要写书评

暂无评论

Universal Graph compression: Stochastic Block Models

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2024年第2期70卷 1473-1497页

作者： Bhatt, Alankrita Wang, Ziao Wang, Chi Wang, Lele Calif Inst Technol Caltech Pasadena CA 91125 USA Univ British Columbia Dept Elect & Comp Engn Vancouver BC V6T 1Z4 Canada Microsoft Res Redmond WA 98052 USA

Motivated by the prevalent data science applications of processing large-scale graph data such as social networks and biological networks, this paper investigates lossless compression of data in the form of a labeled graph. Particularly, we consider a widely used random graph model, stochastic block model (SBM), which captures the clustering effects in social networks. An information-theoretic universal compression framework is applied, in which one aims to design a single compressor that achieves the asymptotically optimal compression rate, for every SBM distribution, without knowing the parameters of the SBM. Such a graph compressor is proposed in this paper, which universally achieves the optimal compression rate with polynomial time complexity for a wide class of SBMs. Existing universal compression techniques are developed mostly for stationary ergodic one-dimensional sequences. However, the adjacency matrix of SBM has complex two-dimensional correlations. The challenge is alleviated through a carefully designed transform that converts two-dimensional correlated data into almost i.i.d. submatrices. The sequence of submatrices is then compressed by a Krichevsky-Trofimov compressor, whose length analysis is generalized to identically distributed but arbitrarily correlated sequences. In four benchmark graph datasets, the compressed files from competing algorithms take 2.4 to 27 times the space needed by the proposed scheme.

关键词： compression algorithms source coding graph theory

来源：评论

学校读者我要写书评

暂无评论

AIS-Based Vessel Trajectory compression: A Systematic Review and Software Development

IEEE OPEN JOURNAL OF VEHICULAR TECHNOLOGY

引用

IEEE OPEN JOURNAL OF VEHICULAR TECHNOLOGY 2024年 5卷 1193-1214页

作者： Liu, Ryan Wen Zhou, Shiqi Yin, Shangkun Shu, Yaqing Liang, Maohan Wuhan Univ Technol Sch Nav Hubei Key Lab Inland Shipping Technol Wuhan 430063 Peoples R China Wuhan Univ Technol Hainan Inst Sanya 572000 Peoples R China Wuhan Univ Technol State Key Lab Maritime Technol & Safety Wuhan 430063 Peoples R China Natl Univ Singapore Dept Civil & Environm Engn Singapore 117576 Singapore

With the advancement of satellite and 5G communication technologies, vehicles can transmit and exchange data from anywhere in the world. It has resulted in the generation of massive spatial trajectories, particularly from the Automatic Identification System (AIS) for surface vehicles. The massive AIS data lead to high storage requirements and computing costs, as well as low data transmission efficiency. These challenges highlight the critical importance of vessel trajectory compression for surface vehicles. However, the complexity and diversity of vessel trajectories and behaviors make trajectory compression imperative and challenging in maritime applications. Therefore, trajectory compression has been one of the hot spots in research on trajectory data mining. The major purpose of this work is to provide a comprehensive reference source for beginners involved in vessel trajectory compression. The current trajectory compression methods could be broadly divided into two types, batch (offline) and online modes. The principles and pseudo-codes of these methods will be provided and discussed in detail. In addition, compressive experiments on several publicly available data sets have been implemented to evaluate the batch and online compression methods in terms of computation time, compression ratio, trajectory similarity, and trajectory length loss rate. Finally, we develop a flexible and open software, called AISCompress, for AIS-based batch and online vessel trajectory compression. The conclusions and associated future works are also given to inspire future applications in vessel trajectory compression.

关键词： Trajectory Artificial intelligence Safety Software Real-time systems compression algorithms Approximation algorithms Automatic identification system (AIS) vessel trajectory trajectory compression error metrics similarity measure

来源：评论

学校读者我要写书评

暂无评论

Efficient compression for Remote Sensing: Multispectral Transform and Deep Recurrent Neural Networks for Lossless Hyper-Spectral Imagine

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第2期15卷 531-541页

作者： Anuradha, D. Sekhar, Gillala Chandra Mishra, Annapurna Thapar, Puneet El-Ebiary, Yousef A. Baker Syamala, Maganti Panimalar Engn Coll Dept CSBS Chennai Tamil Nadu India Inst Aeronaut Engn Dept Comp Sci & Engn Hyderabad 500043 India Silicon Inst Technol Dept Elect & Commun Engn Bhubaneswar 751024 India Lovely Profess Univ Comp Sci & Engn Dept Phagwara Punjab India UniSZA Univ Fac Informat & Comp Kuala Terengganu Malaysia Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Vaddeswaram 522302 Andhra Pradesh India

Remote sensing technologies, which are essential for everything from environmental monitoring to disaster relief, enable large-scale multispectral data collection. In the field of hyper-spectral imaging, where high-dimensional data is required for precise analysis, effective compression techniques are critical for transmission and storage. In the field of hyper-spectral imaging, the development of efficient compression techniques is critical because datasets containing high-dimensional information must be transmitted and stored efficiently without sacrificing analytical precision. The paper presents advanced compression techniques that combine deep Recurrent Neural Networks (RNNs) with multispectral transforms to achieve lossless compression in hyper-spectral imaging. The Discrete Wavelet Transform (DWT) is used to efficiently capture spectral and spatial information by utilizing the properties of multispectral transforms. Simultaneously, deep RNNs are used to model the hyper-spectral data with complex dependencies, allowing for sequential compression. The overall compression efficiency that is increased by the integration of spatial and spectral information allows for reduced storage requirements and improved transmission efficiency. Python software is used to implement the proposed model. When compared to Liner Spectral Mixture Analysis (LSMA) based compression, Spatial Orientation Tree Wavelet (STW)-Wavelet Difference Reduction (WDR), and DPCM, the proposed DWT-RNN-LSTM method has a better PSNR value of 45 dB and a lower MSE of 7.50%. Adaptive compression methods are presented in order to dynamically adapt to various data properties and ensure application in various hyperspectral scenes. Studies on hyper-spectral images of various sizes and resolutions demonstrate the approach's scalability and generalization, as well as the utility and adaptability of the proposed compression framework in a variety of remote sensing scenarios.

关键词： Multi-Spectral transform lossless compression hyper-spectral data deep recurrent neural network compression algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：