检索结果-内蒙古大学图书馆

Adaptive circuit learning of born machine: towards realization of amplitude embedding and quantum data loading

QUANTUM SCIENCE AND TECHNOLOGY 2025年第2期10卷 025019-025019页

作者： Li, Chun-Tse Cheng, Hao-Chung Natl Taiwan Univ Dept Elect Engn Taipei 10639 Taiwan Natl Taiwan Univ Grad Inst Commun Engn Taipei 10639 Taiwan Natl Taiwan Univ Dept Math Taipei 106319 Taiwan Natl Taiwan Univ Ctr Quantum Sci & Engn Taipei 106319 Taiwan Natl Ctr Theoret Sci Phys Div Taipei 106319 Taiwan Hon Hai Quantum Comp Res Ctr Taipei 114 Taiwan

Quantum data loading plays a central role in quantum algorithms and quantum information processing. Many quantum algorithms hinge on the ability to prepare arbitrary superposition states as a subroutine, with claims of exponential speedups often predicated on access to an efficient data-loading oracle. In practice, constructing a circuit to prepare a generic n-qubit quantum state typically demands computational efforts scaling as O(2n), posing a significant challenge for quantum algorithms to outperform their classical counterparts. To address this critical issue, various hybrid quantum-classical approaches have been proposed. However, many of these solutions favor simplistic circuit architectures, which are susceptible to substantial optimization challenges. In this study, we harness quantum circuits as Born machines to generate probability distributions. Drawing inspiration from methods used to investigate electronic structures in quantum chemistry and condensed matter physics, we propose a framework called Adaptive Circuit Learning of Born Machine, which dynamically expands the ansatz circuit. Our algorithm is designed to selectively integrate two-qubit entangled gates that best capture the intricate entanglement present within the target state. Empirical experiments underscore the efficacy of our approach in encoding real-world data through amplitude embedding, demonstrating not only compliance with but also enhancement over the performance benchmarks set by prior research.

关键词： quantum machine learning data loading amplitude encoding Born machine

来源：评论

学校读者我要写书评

暂无评论

PERFORMANCE MODELING OF MULTIPROCESSOR SYSTEMS FOR DIFFERENT data loading SCHEMES

MICROPROCESSING AND MICROPROGRAMMING

引用

MICROPROCESSING AND MICROPROGRAMMING 1993年第4期36卷 167-178页

作者： ATIQUZZAMAN, M LA TROBE UNIV DEPT COMP SCI & COMP ENGNBUNDOORAVIC 3083AUSTRALIA

When evaluating the performance of an algorithm in a multiprocessor system, most authors assume that the data are already loaded in the system. This assumption gives rise to a large error between the predicted and actual performances, specially for fine-grained tasks like image processing. Different data loading and interprocessor communication techniques can result in a significant difference in the performance of a machine. To quantify the amount of time spent for data loading and unloading as compared to the total processing time, different data loading and unloading schemes have been developed in this paper. A comparison of performance of a machine under the different schemes has also been presented. The comparison will give an insight into the considerable amount of time data loading, unloading, and interprocessor communications may require depending on the task, the architecture of the machine, and the method used to load and unload data to and from the machine respectively. It has been shown that concurrent data loading, unloading, communication, and processing using state-of-the-art processors helps in significantly reducing the overhead. An expression to determine the optimum number of processors in a machine has been developed.

关键词： PERFORMANCE MODELING data loading MULTIPROCESSOR SYSTEMS LINEAR ARRAY MULTIPROCESSOR

来源：评论

学校读者我要写书评

暂无评论

Scalable Parallel data loading in SciDB 5

Scalable Parallel Data Loading in SciDB

引用

IEEE International Conference on Big data (IEEE Big data)

作者： Kim, Sangchul Lee, Junhee Kim, Taehoon Moon, Bongki Seoul Natl Univ Seoul 08826 South Korea

ISBN: (纸本)9781538627150

SciDB is an array-based DBMS popularly used for scientific data analysis. One major hurdle in processing large-scale scientific data is pre-processing before loading data, which includes extraneous file conversion from a raw data format to a software-specific format, which causes a significant I/O overhead. Moreover, data loading is typically followed by array transformation, which requires data to be sorted and redistributed by hashing. In order to reduce the overhead, we streamline the conversion process and modify the distribution method in loading stages. In addition, we eliminate two heavy-duty steps, namely sort and redistribution, which account for a dominant portion of the redimensioning cost. Our experiments show that the data loading time can be reduced up to 65% compared with the vanilla loader of SciDB.

关键词： Array database Model SciDB data loading

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis on Parallel data loading based on Concurrency Features

Performance Analysis on Parallel Data Loading based on Concu...

引用

International Conference on Decision Aid Sciences and Applications (DASA)

作者： Rahman, Mohammad Ashekur Ul Hussna, Asma George, Fabian Parsia Latif, Mir Lubna Mehrin, Yousra Esfar-E-Alam, A. M. BRAC Univ Dept Comp Sci & Engn Dhaka Bangladesh

ISBN: (纸本)9781665495011

data migration and batch processing remain rudimentary processes in database systems while dealing with enormous volumes of data from multiple sources. Even before running Extract, Transform, Load (ETL) on parallel architectures, extensive querying and performance in a way challenges are required. Real-time data analysis, together with data aggregation and transformation, remains a problem for decision-making since data warehouses retain historical data and update it on a regular basis. However, optimization lessens resource consumption as well as ensures parallel processing efficiency while reducing the time window. The ultimate purpose of this paper is to instantly improve the performance of parallel data loading through concurrency. The conducted analysis shows concurrency on the Oracle database significantly improves the performance gain along with data loading time.

关键词： ETL data loading parallel multi-processing data warehouse Oracle SQLite concurrency

来源：评论

学校读者我要写书评

暂无评论

Accelerating data loading in Deep Neural Network Training 26

Accelerating Data Loading in Deep Neural Network Training

引用

26th International Conference on High Performance Computing, data and Analytics (HiPCW)

作者： Yang, Chih-Chieh Cong, Guojing IBM Corp Data Centr Syst TJ Watson Res Ctr Yorktown Hts NY 10598 USA

ISBN: (纸本)9781728145358

data loading can dominate deep neural network training time on large-scale systems. We present a comprehensive study on accelerating data loading performance in large-scale distributed training. We first identify performance and scalability issues in current data loading implementations. We then propose optimizations that utilize CPU resources to the data loader design. We use an analytical model to characterize the impact of data loading on the overall training time and establish the performance trend as we scale up distributed training. Our model suggests that I/O rate limits the scalability of distributed training, which inspires us to design a locality-aware data loading method. By utilizing software caches, our method can drastically reduce the data loading communication volume in comparison with the original data loading implementation. Finally, we evaluate the proposed optimizations with various experiments. We achieved more than 30x speedup in data loading using 256 nodes with 1,024 learners.

关键词： machine learning distributed training scalability data loading data locality

来源：评论

学校读者我要写书评

暂无评论

Expedited Rating of data Stores Using Agile data loading Techniques 13

Expedited Rating of Data Stores Using Agile Data Loading Tec...

引用

22nd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Barahmand, Sumita Ghandeharizadeh, Shahram USC Comp Sci Dept 941 W 37th Pl Los Angeles CA 90089 USA

ISBN: (纸本)9781450322638

To benchmark and rate a data store, one must repeat experiments that impose a different amount of load on the data store. Workloads that modify the benchmark database may require the same database to be loaded repeatedly. This may constitute a significant portion of the time to rate a data store. This paper presents several agile data loading techniques to expedite the rating process. These techniques include generating the disk image of the database once and re-using it, restoring the updated data items to their original value, maintaining in-memory state of the database across different experiments to avoid repeated loading of the database all together, and a hybrid of the third technique in combination with the other two. These techniques are general purpose and apply to a variety of cloud benchmarks. We investigate their implementation and evaluation in the context of one, the BG benchmark. Obtained results show a factor of two to twelve speedup in the rating process. As an example, when evaluating MongoDB with a million member BG database, we show these techniques expedite BG's rating from 4 months (123 days) of continuous running to less than 11 days for the first rating experiment. Subsequent ratings of MongoDB with different workloads using the same database is much faster, in the order of hours.

关键词： Cloud benchmarks data stores data loading Rating

来源：评论

学校读者我要写书评

暂无评论

Accelerate data loading in Distributed Training with Fast Reconfigurable Optical Network

Accelerate Data Loading in Distributed Training with Fast Re...

引用

2024 Asia Communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical Communications, IPOC 2024

作者： Li, Wenzhe Zhang, Xinhang Jia, Wenxuan Chen, Zhuohan Yuan, Guojun Wang, Zhan Zhang, Peiheng High Performance Computing Center Institute of Computing Technology CAS Beijing China Department of Intelligent Science and Technology Hangzhou Institute of Advanced Study UCAS Hangzhou China Institute of Intelligent Computing Technology Chinese Academy of Sciences Suzhou China

We enhance our prior all-optical reconfigurable network to accelerate the data loading with minimized communication distance between compute and storage nodes. A novel corresponding data loading scheme is proposed to ... 详细信息

ISBN: (纸本)9798350379266

关键词： data loading Distributed Deep Learning Reconfigurable optical network

来源：评论

学校读者我要写书评

暂无评论

Optimised Transformation Algorithm For Hadoop data loading in Web ETL Framework

引用

EAI ENDORSED TRANSACTIONS ON SCALABLE INFORMATION SYSTEMS 2020年第25期7卷 1-8页

作者： Gupta, Gaurav Kumar, Neelesh Chhabra, Indu CSIR Indian Inst Petr Res Planning & Project Management Dehra Dun Uttarakhand India CSIR Cent Sci Instruments Org BioMed Instrumentat Chandigarh India Panjab Univ Dept Comp Sci & Applica Chandigarh India

Web ETL unlike conventional ETL framework requires considerable improvements in all the three layers i.e. Extraction,Transformation and loading due to the inherent nature of web input data. Websites are huge and are unique source Transformation, out of such huge information available on the websites, finding and analysing the required and relevant data is critical as the data may be foul consisting of redundant data or misspelled. Determining integrated record that stands for identical real world entities in abundant ways is the major problem to be analysed for any database. Hence, Web ETL transformation layer functionality of data transformation becomes mandatory in determining the pertinent information tobe examined. Since the data on the web is "very voluminous" hence loading only clean data in data warehouse is necessary for fast processing to achieve accurate result. The present research focuses on data transformation in web ETL framework and proposes a modified technique to employ token wise sentence sorting to remove redundant records from the patent database along with Levenshtein distance used for string matching. Afterwards the cleaned data is transformed and loaded from this staging area to hadoop environment. The integration of proposed transformation technique with hadoop system delimits the constraint of data processing, storage and retrieval of large data structure from conventional data warehouse system.

关键词： Redundant data data Transformation data loading Levenshtein Distance Matching Hadoop

来源：评论

学校读者我要写书评

暂无评论

Parallel In-Situ data Processing with Speculative loading 14

Parallel In-Situ Data Processing with Speculative Loading

引用

ACM SIGMOD International Conference on Management of data

作者： Cheng, Yu Rusu, Florin UC Merced 5200 N Lake Rd Merced CA 95343 USA

ISBN: (纸本)9781450323765

Traditional databases incur a significant data-to-query delay due to the requirement to load data inside the system before querying. Since this is not acceptable in many domains generating massive amounts of raw data, e.g., genomics, databases are entirely discarded. External tables, on the other hand, provide instant SQL querying over raw files. Their performance across a query workload is limited though by the speed of repeated full scans, tokenizing, and parsing of the entire file. In this paper, we propose SCANRAW, a novel database physical operator for in-situ processing over raw files that integrates data loading and external tables seamlessly while preserving their advantages: optimal performance across a query workload and zero time-to-query. Our major contribution is a parallel super-scalar pipeline implementation that allows SCANRAW to take advantage of the current many-and multi-core processors by overlapping the execution of independent stages. Moreover, SCANRAW overlaps query processing with loading by speculatively using the additional I/O bandwidth arising during the conversion process for storing data into the database such that subsequent queries execute faster. As a result, SCANRAW makes optimal use of the available system resources - CPU cycles and I/O bandwidth - by switching dynamically between tasks to ensure that optimal performance is achieved. We implement SCANRAW in a state-of-the-art database system and evaluate its performance across a variety of synthetic and real-world datasets. Our results show that SCANRAW with speculative loading achieves optimal performance for a query sequence at any point in the processing. Moreover, SCANRAW maximizes resource utilization for the entire workload execution while speculatively loading data and without interfering with normal query processing.

关键词： data loading raw file processing external tables

来源：评论

学校读者我要写书评

暂无评论

SCANRAW: A database Meta-Operator for Parallel In-Situ Processing and loading

引用

ACM TRANSACTIONS ON dataBASE SYSTEMS 2015年第3期40卷 1–45页

作者： Cheng, Yu Rusu, Florin Univ Calif Merced Sch Engn Merced CA 95343 USA

Traditional databases incur a significant data-to-query delay due to the requirement to load data inside the system before querying. Since this is not acceptable in many domains generating massive amounts of raw data (e.g., genomics), databases are entirely discarded. External tables, on the other hand, provide instant SQL querying over raw files. Their performance across a query workload is limited though by the speed of repeated full scans, tokenizing, and parsing of the entire file. In this article, we propose SCANRAW, a novel database meta-operator for in-situ processing over raw files that integrates data loading and external tables seamlessly, while preserving their advantages: optimal performance across a query workload and zero time-to-query. We decompose loading and external table processing into atomic stages in order to identify common functionality. We analyze alternative implementations and discuss possible optimizations for each stage. Our major contribution is a parallel superscalar pipeline implementation that allows SCANRAW to take advantage of the current many-and multicore processors by overlapping the execution of independent stages. Moreover, SCANRAW overlaps query processing with loading by speculatively using the additional I/O bandwidth arising during the conversion process for storing data into the database, such that subsequent queries execute faster. As a result, SCANRAW makes intelligent use of the available system resources-CPU cycles and I/O bandwidth-by switching dynamically between tasks to ensure that optimal performance is achieved. We implement SCANRAW in a state-of-the-art database system and evaluate its performance across a variety of synthetic and real-world datasets. Our results show that SCANRAW with speculative loading achieves the best-possible performance for a query sequence at any point in the processing. Moreover, SCANRAW maximizes resource utilization for the entire workload execution while speculatively loading data a

关键词： Design Performance data access operator external table data loading access path system database operator

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：