Name
Abstract | ||
|---|---|---|
Modern computers provide excellent opportunities for performing fast computations. They are equipped with powerful microprocessors and large memories. However, programs are not necessarily able to exploit those computer resources effectively. In this paper, we present the way in which we have implemented a nearest neighbor classification. We show how performance can be improved by exploiting the ability of superscalar processors to issue multiple instructions per cycle and by using the memory hierarchy adequately. This is accomplished by the use of floating-point arithmetic which usually outperforms integer arithmetic, and block (tiled) algorithms which exploit the data locality of programs allowing for an efficient use of the data stored in the cache memory. Our results are validated with both an analytical model and empirical results. We show that regular codes could be performed faster than more complex irregular codes using standard data sets. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1007/s10044-007-0065-y | Pattern Anal. Appl. |
Keywords | Field | DocType |
floating-point arithmetic,standard data set,large memory,data locality,complex irregular code,efficient use,memory hierarchy,analytical model,nearest neighbor classification,exploiting computer resource,cache memory,integer arithmetic,floating point arithmetic,instructions per cycle | Instructions per cycle,k-nearest neighbors algorithm,Locality,Memory hierarchy,CPU cache,Computer science,Floating point,Microprocessor,Parallel computing,Artificial intelligence,Machine learning,Computation | Journal |
Volume | Issue | ISSN |
10 | 4 | 1433-755X |
Citations | PageRank | References |
8 | 0.50 | 22 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| José R. Herrero | 1 | 94 | 16.90 |
| Juan J. Navarro | 2 | 323 | 42.90 |