投资一次，省一百万次——基于llvm的表达式编译

Datenbanksysteme für Business, Technologie und Web Pub Date : 2017-03-01 DOI:10.15496/publikation-25721

D. Butterstein, Torsten Grust

{"title":"投资一次，省一百万次——基于llvm的表达式编译","authors":"D. Butterstein, Torsten Grust","doi":"10.15496/publikation-25721","DOIUrl":null,"url":null,"abstract":"We demonstrate how a surgical change to PostgreSQL’s evaluation strategy for SQL expressions can have a noticeable impact on overall query runtime performance. (This is an abridged version of [BG16], originally demonstrated at VLDB 2016.) The evaluation of scalar or Boolean expressions often takes the backseat in a discussion of query processing although table scans, ﬁlters, aggregates, projections","PeriodicalId":421643,"journal":{"name":"Datenbanksysteme für Business, Technologie und Web","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Invest Once, Save a Million Times - LLVM-based Expression Compilation in PostgreSQL\",\"authors\":\"D. Butterstein, Torsten Grust\",\"doi\":\"10.15496/publikation-25721\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We demonstrate how a surgical change to PostgreSQL’s evaluation strategy for SQL expressions can have a noticeable impact on overall query runtime performance. (This is an abridged version of [BG16], originally demonstrated at VLDB 2016.) The evaluation of scalar or Boolean expressions often takes the backseat in a discussion of query processing although table scans, ﬁlters, aggregates, projections\",\"PeriodicalId\":421643,\"journal\":{\"name\":\"Datenbanksysteme für Business, Technologie und Web\",\"volume\":\"15 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Datenbanksysteme für Business, Technologie und Web\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.15496/publikation-25721\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Datenbanksysteme für Business, Technologie und Web","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.15496/publikation-25721","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

我们将演示如何对PostgreSQL的SQL表达式求值策略进行手术式更改，从而对整体查询运行时性能产生显著影响。(这是[BG16]的精简版本，最初在VLDB 2016上展示。)在查询处理的讨论中，标量或布尔表达式的求值通常处于次要位置，而表扫描、过滤器、聚合、投影等则处于次要位置

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Invest Once, Save a Million Times - LLVM-based Expression Compilation in PostgreSQL

We demonstrate how a surgical change to PostgreSQL’s evaluation strategy for SQL expressions can have a noticeable impact on overall query runtime performance. (This is an abridged version of [BG16], originally demonstrated at VLDB 2016.) The evaluation of scalar or Boolean expressions often takes the backseat in a discussion of query processing although table scans, ﬁlters, aggregates, projections

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Datenbanksysteme für Business, Technologie und Web

自引率

0.00%

发文量

期刊最新文献

SportsTables: A new Corpus for Semantic Type Detection Accelerating Large Table Scan using Processing-In-Memory Technology The InsightsNet Climate Change Corpus (ICCC) On the State of German (Abstractive) Text Summarization The Easiest Way of Turning your Relational Database into a Blockchain - and the Cost of Doing So