Preferential Path Profiling: Compactly Numbering Interesting Paths

Vaswani, Kapil and Nori, Aditya V and Chilimbi, Trishul M (2007) Preferential Path Profiling: Compactly Numbering Interesting Paths. In: ACM Sigplan Notices, 42 (1). pp. 351-362.

PDF Preferential_Path_Profiling.pdf Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Path profiles provide a more accurate characterization of a program’s dynamic behavior than basic block or edge profiles, but are relatively more expensive to collect. This has limited their use in practice despite demonstrations of their advantages over edge pro-files for a wide variety of applications. We present a new algorithm called preferential path profiling (PPP), that reduces the overhead of path profiling. PPP leverages the observation that most consumers of path profiles are only interested in a subset of all program paths. PPP achieves low overhead by separating interesting paths from other paths and assigning a set of unique and compact numbers to these interesting paths.We draw a parallel between arithmetic coding and path numbering, and use this connection to prove an optimality result for the compactness of path numbering produced by PPP. This compact path numbering enables our PPP implementation to record path information in an array instead of a hash table. Our experimental results indicate that PPP reduces the runtime overhead of profiling paths exercised by the largest (ref) inputs of the SPEC CPU2000 benchmarks from 50% on average (maximum of 132%) to 15% on average (maximum of 26%) as compared to a state-of-the-art path profiler.

Item Type:	Journal Article
Publication:	ACM Sigplan Notices
Publisher:	ACM
Additional Information:	Copyright of this article belongs to ACM
Keywords:	Profiling, preferential paths, arithmetic coding, dynamic analysis
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	25 Aug 2008
Last Modified:	01 Mar 2019 07:36
URI:	http://eprints.iisc.ac.in/id/eprint/15660

Actions (login required)

View Item