Abstract
Subroutine profiling is a well-known performance tool. For application or system programmers, it determines "hot spots" where the program spends most of its time, and where careful rewriting can most help performance. For compiler authors, it can give information about programming style in such hot spots, and can indicate where compiler improvements may be useful. For hardware designers and analysts, it can be the starting point to explain performance behavior.
- For information on collect, er_print, and related utilities see http://developers.sun.com/sunstudio/analyzer_in-dex.htmlGoogle Scholar
- John L. Henning (ed.), "SPEC CPU2006 Benchmark Descriptions", Computer Architecture News, Volume 34, No. 4, September 2006. Google ScholarDigital Library
- www.spec.org/cpu2006/docs/runrules.htmlGoogle Scholar
Index Terms
- Subroutine profiling results for the CPU2006 benchmarks
Recommendations
Edge profiling versus path profiling: the showdown
POPL '98: Proceedings of the 25th ACM SIGPLAN-SIGACT symposium on Principles of programming languagesEdge profiles are the traditional control flow profile of choice for profile-directed compilation. They have been the basis of path-based optimizations that select "hot" paths, even though edge profiles contain strictly less information than path ...
Can we trust profiling results?: understanding and fixing the inaccuracy in modern profilers
ICS '19: Proceedings of the ACM International Conference on SupercomputingProfilers are an indispensable component in modern software stack of data centers and supercomputers. Profilers collect detailed performance data during program execution and guide code optimization across the entire software stack. The accuracy of the ...
Vector vs. superscalar and VLIW architectures for embedded multimedia benchmarks
MICRO 35: Proceedings of the 35th annual ACM/IEEE international symposium on MicroarchitectureMultimedia processing on embedded devices requires an architecture that leads to high performance, low power consumption, reduced design complexity, and small code size. In this paper, we use EEMBC, an industrial benchmark suite, to compare the VIRAM ...
Comments