Extending a Light-weight Runtime System by Dynamic Instrumentation for Performance Evaluation

Increasing complexity of current and future systems poses a new challenge for software engineers. In a previous work we presented a light-weight runtime system for abstraction of heterogeneous parallel systems. This runtime system adapts an application to the current system state in order to improve the utilization of the available resources. For online evaluation of such adaptions, we propose a versatile instrumentation mechanism that can be used by the runtime system. We show that this technique introduces only minor overhead and we compare it to the Dyninst mechanism.

[1]  Jeffrey K. Hollingsworth,et al.  Efficient instrumentation for code coverage testing , 2002, ISSTA '02.

[2]  Kunle Olukotun,et al.  The case for a single-chip multiprocessor , 1996, ASPLOS VII.

[3]  Stamatis Vassiliadis,et al.  The MOLEN polymorphic processor , 2004, IEEE Transactions on Computers.

[4]  Koushik Chakraborty,et al.  Dynamic heterogeneity and the need for multicore virtualization , 2009, OPSR.

[5]  James Laudon,et al.  Performance/Watt: the new server focus , 2005, CARN.

[6]  Norman P. Jouppi,et al.  Single-ISA heterogeneous multi-core architectures for multithreaded workload performance , 2004, Proceedings. 31st Annual International Symposium on Computer Architecture, 2004..

[7]  G.E. Moore,et al.  Cramming More Components Onto Integrated Circuits , 1998, Proceedings of the IEEE.

[8]  James R. Larus,et al.  EEL: machine-independent executable editing , 1995, PLDI '95.

[9]  Alessandro Orso,et al.  A generic instrumentation framework for collecting dynamic information , 2004, SOEN.

[10]  Wolfgang Karl,et al.  A Light-Weight Approach to Dynamical Runtime Linking Supporting Heterogenous, Parallel, and Reconfigurable Architectures , 2009, ARCS.

[11]  Rainer Buchty,et al.  Providing Guidance Information for Application-Mapping on Heterogeneous Parallel Systems , 2009 .

[12]  Wolfgang Karl,et al.  Delivering Guidance Information in Heterogeneous Systems , 2010, ARCS Workshops.

[13]  Oscar Naim,et al.  MDL: a language and compiler for dynamic program instrumentation , 1997, Proceedings 1997 International Conference on Parallel Architectures and Compilation Techniques.

[14]  木村 康則,et al.  20世紀の名著名論:Gordon Moore: Cramming More Components onto Integrated Circuits , 2005 .

[15]  Pradeep Dubey,et al.  Larrabee: A Many-Core x86 Architecture for Visual Computing , 2009, IEEE Micro.

[16]  Harish Patil,et al.  Pin: building customized program analysis tools with dynamic instrumentation , 2005, PLDI '05.