@article {14153, title = {Use of linear algebra kernels to build an efficient finite element solver}, journal = {Parallel Computing}, volume = {21}, year = {1995}, month = {1995/01//}, pages = {161 - 173}, abstract = {For scientific codes to achieve good performance on computers with hierarchical memories, it is necessary that the ratio of memory references to arithmetic operations be low. In this paper, we show that Level 3 BLAS linear algebra kernels can be used to satisfy this requirement to produce an efficient implementation of a parallel finite element solver on a shared memory parallel computer with a fast cache memory.}, keywords = {Cache memory, finite element, hp-version, Level 3 BLAS, Parallel algorithm, shared memory multiprocessor}, isbn = {0167-8191}, doi = {16/0167-8191(94)00030-E}, url = {http://www.sciencedirect.com/science/article/pii/016781919400030E}, author = {Elman, Howard and Lee,Dennis K. -Y.} }