Compressible memory data structures for event-based trace analysis

Authors:
Andreas Knüpfer;Wolfgang E. Nagel
Affiliations:
Center for High Performance Computing(ZHR), TU Dresden, Dresden, Germany;Center for High Performance Computing(ZHR), TU Dresden, Dresden, Germany
Venue:
Future Generation Computer Systems
Year:
2006

Citing 9
Cited 0

Using C++ template metaprograms

C++ gems
Expression templates

C++ gems
Call graph construction in object-oriented languages

Proceedings of the 12th ACM SIGPLAN conference on Object-oriented programming, systems, languages, and applications
A framework for call graph construction algorithms

ACM Transactions on Programming Languages and Systems (TOPLAS)
Experiences tuning SMG98: a semicoarsening multigrid benchmark based on the hypre library

ICS '02 Proceedings of the 16th international conference on Supercomputing
Reconsidering custom memory allocation

OOPSLA '02 Proceedings of the 17th ACM SIGPLAN conference on Object-oriented programming, systems, languages, and applications
Performance Optimization for Large Scale Computing: The Scalable VAMPIR Approach

ICCS '01 Proceedings of the International Conference on Computational Science-Part II
Gprof: A call graph execution profiler

SIGPLAN '82 Proceedings of the 1982 SIGPLAN symposium on Compiler construction
A new data compression technique for event based program traces

ICCS'03 Proceedings of the 2003 international conference on Computational science: PartIII

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper 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.