CUDA GPU libraries and novel sparse matrix-vector multiplication - implementation and performance enhancement in unstructured finite element computations.
Richard HaneyRam MohanPublished in: Int. J. Comput. Sci. Eng. (2019)
Keyphrases
- sparse matrix
- finite element
- gpu accelerated
- floating point
- parallel implementation
- graphics processors
- graphics processing units
- parallel computation
- finite element analysis
- finite element model
- compute unified device architecture
- soft tissue
- random projections
- finite element method
- mesh generation
- finite difference
- boundary element
- graphics hardware
- material properties
- real time
- parallel computing
- gpu implementation
- parallel algorithm
- image processing
- feature selection