Java is the “go-to” programming language choice for developing scalableenterprise cloud applications . In such systems, even a few percent CPU timesavings can offer a significant competitive advantage . In this paper, we present DJXPerf, a lightweight, object-centric memoryprofiler for Java, which associates memory-hierarchy performance metrics (e.g., cache/TLB misses) with Java objects . We study and optimize anumber of Java and Scala programs, including well-known benchmarks andreal-world applications, and demonstrate significant speedups . DJXperf incurs only ~8% runtimeoverhead and ~5% memory overhead on average, requiring no modifications tohardware, OS, Java virtual machine, or application source code, which makes itattractive to use in production. Guided by DJxperf

Author(s) : Bolun Li, Pengfei Su, Milind Chabbi, Shuyin Jiao, Xu Liu

Links : PDF - Abstract

Code :

Keywords : java - djxperf - memory - applications - object -

Leave a Reply

Your email address will not be published. Required fields are marked *