Towards Optimizing Learned Index for High Performance, Memory Efficiency and NUMA Awareness

计算机科学 索引(排版) 万维网
作者
Lixiao Cui,K. C. Yang,Yusen Li,Gang Wang,Xiaoguang Liu
出处
期刊:ACM Transactions on Architecture and Code Optimization [Association for Computing Machinery]
卷期号:22 (3): 1-26
标识
DOI:10.1145/3736168
摘要

Learned indexes provide significant performance advantages over classical ordered indexes. However, current learned indexes face challenges regarding tradeoffs between performance and space, as well as scalability issues in platforms with multiple NUMA nodes. These limitations hinder the practical application of learned indexes in production environments. This article presents DiffLex, a learned index with high-performance, memory-efficiency, and NUMA-awareness. The core design of DiffLex is to perform differentiated management based on the popularity of data. For optimal performance, DiffLex stores newly inserted data in sparse delta arrays and frequently accessed data in sparse hot cache arrays. However, for cold data that occupy a majority of the storage space, DiffLex stores them in dense arrays and conducts compression to reduce memory costs. DiffLex ensures NUMA-awareness by partitioning sparse deltas and replicating the hot cache arrays across multiple NUMA nodes. Additionally, we propose a persistent version of DiffLex tailored for emerging persistent memory devices. Our evaluation results demonstrate that DiffLex achieving 3.88× and 1.82× performance improvements compared to state-of-the-art learned indexes, while maintaining a compact index size.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
123发布了新的文献求助10
刚刚
王桐发布了新的文献求助30
1秒前
英俊的铭应助Arjun采纳,获得10
1秒前
酷波er应助幸福大米采纳,获得10
1秒前
SHERRY发布了新的文献求助10
1秒前
1L聚合釜发布了新的文献求助10
1秒前
传奇3应助墩墩采纳,获得10
2秒前
4秒前
研友_nxwN7L发布了新的文献求助10
4秒前
小蘑菇应助xueshanfeihu采纳,获得30
6秒前
6秒前
Owen应助p1nk采纳,获得10
8秒前
8秒前
chz完成签到,获得积分10
9秒前
pokexuejiao应助Fly采纳,获得10
9秒前
9秒前
orixero应助sl采纳,获得30
10秒前
123完成签到,获得积分10
10秒前
Ljc发布了新的文献求助10
10秒前
12秒前
Arjun发布了新的文献求助10
12秒前
12秒前
qingtian发布了新的文献求助10
14秒前
依依完成签到,获得积分10
14秒前
汉堡包应助橙橙采纳,获得10
15秒前
缓慢怜菡应助chz采纳,获得30
16秒前
yuuu发布了新的文献求助10
16秒前
17秒前
科目三应助Arjun采纳,获得10
18秒前
Cheungup发布了新的文献求助10
19秒前
22秒前
sl发布了新的文献求助30
23秒前
001发布了新的文献求助10
24秒前
共享精神应助kakaxi采纳,获得10
25秒前
26秒前
26秒前
天天快乐应助白白采纳,获得10
27秒前
可可豆发布了新的文献求助10
28秒前
30秒前
橙橙发布了新的文献求助10
32秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Geist der Kunst und Kultur 1000
Resistance Spot Welding Dataset for Automobile Body-in-White Quality Analysis 748
悉尼大学博士学位论文,题目:Modelling and testing of one-sided stitched laminated composites. 作者:Kristopher P. Plain 700
Child and Adolescent Psychology 600
Machine Learning for Asset Management and Pricing 600
Numerical analysis of the coupled atmosphere-ocean models (CAO II). II 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7414435
求助须知:如何正确求助?哪些是违规求助? 9017949
关于积分的说明 19210719
捐赠科研通 7046009
什么是DOI,文献DOI怎么找? 3233989
关于科研通互助平台的介绍 2396208
邀请新用户注册赠送积分活动 2216132