Software Performance Analysis
Michel R. Dagenais (Dept. of Computer Engineering, Ecole, Polytechnique, Montreal, Canada) Karim Yaghmour (Opersys, Montreal, Canada), Charles Levert (Ericsson Research, Montreal, Canada) Makan Pourzandi, (Ericsson Research, Montreal, Canada)
TL;DR
This paper reviews Linux performance analysis tools, focusing on data collection, processing algorithms, overhead, and precision, to help optimize application speed.
Contribution
It provides an in-depth comparison of traditional and advanced Linux performance analysis tools, emphasizing their underlying algorithms and trade-offs.
Findings
Comprehensive overview of Linux performance tools
Analysis of data collection and processing algorithms
Discussion on tool overhead and precision
Abstract
The key to speeding up applications is often understanding where the elapsed time is spent, and why. This document reviews in depth the full array of performance analysis tools and techniques available on Linux for this task, from the traditional tools like gcov and gprof, to the more advanced tools still under development like oprofile and the Linux Trace Toolkit. The focus is more on the underlying data collection and processing algorithms, and their overhead and precision, than on the cosmetic details of the graphical user interface frontends.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsEmbedded Systems and FPGA Design