Data Mining

Hasso Plattner's A Course in In-Memory Data Management: The Inner Mechanics PDF

By Hasso Plattner

ISBN-10: 3642552692

ISBN-13: 9783642552694

ISBN-10: 3642552706

ISBN-13: 9783642552700

Recent achievements in and software program improvement, comparable to multi-core CPUs and DRAM capacities of a number of terabytes in step with server, enabled the advent of a innovative expertise: in-memory info administration. This expertise helps the versatile and very quick research of huge quantities of firm information. Professor Hasso Plattner and his learn crew on the Hasso Plattner Institute in Potsdam, Germany, were investigating and educating the corresponding techniques and their adoption within the software program for years.

This publication relies on an internet path that used to be first introduced in autumn 2012 with greater than 13,000 enrolled scholars and marked the winning place to begin of the openHPI e-learning platform. The path is especially designed for college students of computing device technology, software program engineering, and IT comparable topics, yet addresses company specialists, software program builders, know-how specialists, and IT analysts alike. Plattner and his crew specialize in exploring the interior mechanics of a column-oriented dictionary-encoded in-memory database. lined issues contain - among others - actual information garage and entry, simple database operators, compression mechanisms, and parallel subscribe to algorithms. past that, implications for destiny firm purposes and their improvement are mentioned. step-by-step, readers will comprehend the novel variations and benefits of the hot know-how over conventional row-oriented, disk-based databases.

In this thoroughly revised 2nd variation, we comprise the suggestions of hundreds of thousands after all contributors on openHPI and take into consideration most recent developments in demanding- and software program. greater figures, motives, and examples extra ease the certainty of the suggestions provided. We introduce complicated facts administration thoughts akin to obvious mixture caches and supply new showcases that reveal the potential for in-memory databases for 2 varied industries: retail and lifestyles sciences.

Show description

Read or Download A Course in In-Memory Data Management: The Inner Mechanics of In-Memory Databases PDF

Best data mining books

Download e-book for iPad: Automated Data Collection with R: A Practical Guide to Web by Simon Munzert, Christian Rubba, Dominic Nyhuis, Peter Meiner

A palms on advisor to internet scraping and textual content mining for either newbies and skilled clients of R Introduces basic recommendations of the most structure of the net and databases and covers HTTP, HTML, XML, JSON, SQL.

Provides easy suggestions to question net records and knowledge units (XPath and commonplace expressions). an intensive set of workouts are offered to steer the reader via every one process.

Explores either supervised and unsupervised suggestions in addition to complicated concepts similar to info scraping and textual content administration. Case reviews are featured all through in addition to examples for every process provided. R code and ideas to workouts featured within the publication are supplied on a helping site.

Min Chen's Big data Related Technologies, Challenges and Future PDF

This Springer short offers a finished assessment of the heritage and up to date advancements of huge info. the worth chain of massive information is split into 4 stages: facts new release, info acquisition, facts garage and information research. for every section, the ebook introduces the overall historical past, discusses technical demanding situations and reports the most recent advances.

Read e-book online Databases Theory and Applications: 26th Australasian PDF

This e-book constitutes the refereed lawsuits of the twenty sixth Australasian Database convention, ADC 2015, held in Melbourne, VIC, Australia, in June 2015. The 24 complete papers provided including five demo papers have been rigorously reviewed and chosen from forty three submissions. The Australasian Database convention is an annual overseas discussion board for sharing the most recent study developments and novel purposes of database structures, information pushed purposes and information analytics among researchers and practitioners from worldwide, really Australia and New Zealand.

Additional resources for A Course in In-Memory Data Management: The Inner Mechanics of In-Memory Databases

Example text

4 shows a rough comparison between a Uniform Memory Access (UMA) and a Non-Uniform Memory Access (NUMA) system architecture. A UMA system is characterized by a deterministic access time for an arbitrary memory address independent of which processor makes the request as every memory chip is accessed through a central memory bus as shown in Fig. 4a. For NUMA systems on the other hand the access time depends on the memory location relative to the processor. Local (adjacent) memory can be accessed faster than nonlocal (adjacent to another processor) memory or shared memory (shared amongst processors) as shown in Fig.

Each of those systems offers a high level of parallel computing for a price of about $50,000. Despite the introduction of massive parallelism, the disk totally dominated all thinking and performance optimizations not long ago. It was extremely slow, but necessary to store data. Compared to the speed development of CPUs, the development of disk performance could not keep up. This resulted in a complete distortion of the whole model of working with databases and large amounts of data. Today, the increasing size of main memory available in servers combined with its ever decreasing price initiate a shift from disk-based to main-memory based database management systems.

In the early 2000s multi-core architectures were introduced, starting a trend towards growing parallelism. Today, a typical enterprise computing board comprises eight CPUs and 10 to 16 cores per CPU, adding up to 80 to 128 cores per server. An address space of 64 bit ensures that the increasing amount of main memory can be addressed, with current servers supporting up to 6 TB. The maximum data throughput between a CPU and DRAM typically approximates 85 GB/s and it is possible to transfer more than 6 GB/s between servers via a typical InfiniBand FDR 4x link.

Download PDF sample

A Course in In-Memory Data Management: The Inner Mechanics of In-Memory Databases by Hasso Plattner


by Kenneth
4.1

Rated 4.29 of 5 – based on 5 votes