Locality-Aware Task Scheduling and Data Distribution for OpenMP Programs on NUMA Systems and Manycore Processors

Table 4

Pattern-based [15] and real-world benchmarks.

Benchmark	Behavior	Data distribution; heuristic; guidance
Map; (pattern-based)	1D vector scaling	Coarse
Reduction; (pattern-based)	Iterative implementation of merge; phase of BOTS Sort	Fine
Vecmul	Vector cross product	Coarse
Matmul	Blocked matrix multiplication with; BLAS operations in task computation	Coarse
Jacobi	Blocked 2D heat equation solver	Fine
SparseLU	LU factorization of sparse matrix.; Derived from BOTS SparseLU.	Coarse