Abstract

Trace files are widely used in research and academia to study the behavior of programs. They are simple to process and guarantee repeatability. Unfortunately, they tend to be very large. This paper describes vpc3, a fundamentally new approach to compressing program traces. Vpc3 employs value predictors to bring out and amplify patterns in the traces so that conventional compressors can compress them more effectively. In fact, our approach not only results in much higher compression rates but also provides faster compression and decompression. For example, compared to bzip2, vpc3's geometric mean compression rate on SPECcpu2000 store address traces is 18.4 times higher, compression is ten times faster, and decompression is three times faster.

Citations

461	D: A block-sorting lossless data compression algorithm - Burrows, Wheeler - 1994
142	Speculative execution based on value prediction - Gabbay - 1996
101	ATOM: a flexible interface for building high performance program analysis tools - Eustace, Srivastava - 1995
77	Efficient representations and abstractions for quantifying and exploiting data reference locality - Chilimbi - 2001
29	Compressing extended program traces using value predictors - Burtscher, Jeeradit - 2003
27	Differential FCM: Increasing Value Prediction Accuracy by Improving Table - Goeman, Vandierendonck, et al. - 2001
21	Hybrid load-value predictors - Burtscher, Zorn - 2002
20	Address trace compression through loop detection and reduction - ELNOZAHY - 1999
6	Exploring Last n Value - Burtscher, Zorn - 1999