120.kmeans
SPEC ACCEL Benchmark Description File

Benchmark Name

123.nw

Benchmark Author

University of Virginia

Benchmark Program General Category

Dynamic Programming, Bioinformatics

Benchmark Description

Needleman-Wunsch is a nonlinear global optimization method for DNA sequence alignments. The potential pairs of sequences are organized in a 2D matrix. In the first step, the algorithm fills the matrix from top left to bottom right, step-by-step. The optimum alignment is the pathway through the array with maximum score, where the score is the value of the maximum weighted path ending at that cell. Thus, the value of each data element depends on the values of its northwest-, north- and west-adjacent elements. In the second step, the maximum path is traced backward to deduce the optimal alignment.

Input Description

Input is the number of rows/columns, penalty, opencl file and times to loop kernel. Data is set internally to the requested conditions.

Output Description

Output is the traceback of the generated path.

The output file nw.out contains detailed timing information about the run. It also shows which device was selected along with what devices where available to OpenCL.

Programming Language

C++

Known portability issues

None

Reference

https://www.cs.virginia.edu/~skadron/wiki/rodinia/index.php/Main_Page

[1] S. Che, M. Boyer, J. Meng, D. Tarjan, J. W. Sheaffer, S.-H. Lee, and K. Skadron. Rodinia: A Benchmark Suite for Heterogeneous Computing. In Proceedings of the IEEE International Symposium on Workload Characterization (IISWC), pp. 44-54, Oct. 2009.

[2] S. Che, J. W. Sheaffer, M. Boyer, L. G. Szafaryn, L. Wang, and K. Skadron. A Characterization of the Rodinia Benchmark Suite with Comparison to Contemporary CMP Workloads. In Proceedings of the IEEE International Symposium on Workload Characterization, Dec. 2010.