Abstract
We propose the use of the Confidence Interval of estimated Mean (CIM), a metric based on statistical sampling theory, to evaluate the quality of a given phase classification and for comparing different phase classification schemes. Previous research on phase classification used the Weighted Average of Coefficient of Variation (CoVwa) to estimate phase classification quality. We found that the phase quality indicated by CoVwa could be inconsistent across different phase classifications. We explain the reasons behind this inconsistency and demonstrate the inconsistency using data from several SPEC CPU2000 benchmark programs. We show that the Confidence Interval of estimated Mean (CIM) correctly estimates the quality of phase classification with a meaningful statistical interpretation.
Original language | English (US) |
---|---|
Pages (from-to) | 9-12 |
Number of pages | 4 |
Journal | IEEE Computer Architecture Letters |
Volume | 6 |
Issue number | 1 |
DOIs | |
State | Published - Jan 2007 |
Bibliographical note
Funding Information:VI. ACKNOWLEDGEMENT This work was supported in part by grant NSF no. CCF-0541162, EIA-0220021, Intel, the University of Minnesota Digital Technology Center, and the Minnesota Supercomputing Institute. REFERENCES