Compressible memory data structures for event-based trace analysis

The article presents a new compressible memory data structure for trace events. Its primary intention is to aid the analysis of huge traces by reducing the memory requirements significantly. Furthermore, customized evaluation algorithms reduce the computational effort. The data structure as well as algorithms for construction and evaluation are discussed in detail. Experiments with real-life traces demonstrate the theoretically derived capabilities of the new approach. Key words: Performance Analysis, Tracing, Data Structures, Compression

• Type: Journal
• Year: 2006
• Where: FGCS
• Authors: Andreas Knüpfer, Wolfgang E. Nagel
• Keywords: Compressible Memory Data, Data Structures, FGCS 2006, Huge Traces