Performance Optimization for Large Scale Computing: The Scalable VAMPIR Approach
ICCS '01 Proceedings of the International Conference on Computational Science-Part II
Performance Tuning on Parallel Systems: All Problems Solved?
PARA '00 Proceedings of the 5th International Workshop on Applied Parallel Computing, New Paradigms for HPC in Industry and Academia
High Performance Event Trace Visualization
PDP '05 Proceedings of the 13th Euromicro Conference on Parallel, Distributed and Network-Based Processing
Compressible memory data structures for event-based trace analysis
Future Generation Computer Systems
A new data compression technique for event based program traces
ICCS'03 Proceedings of the 2003 international conference on Computational science: PartIII
Recording the control flow of parallel applications to determine iterative and phase-based behavior
Future Generation Computer Systems
Hi-index | 0.00 |
This paper addresses performance and scalability issues of state-of-the-art trace analysis. The Complete Call Graph (CCG) data structure is proposed as an alternative to the common linear storage schemes. By transparent in-memory compression CCGs are capable of exploiting redundancy as frequently found in traces and thus reduce the memory requirements notably. Evaluation algorithms can be designed to take advantage of CCGs, too, such that the computational effort is reduced in the same order of magnitude as the memory requirements.