OpenCL Performance Portability for Xeon Phi Coprocessor and NVIDIA GPUs: A Case Study of Finite Element Numerical Integration.
Krzysztof BanasFilip KruzelPublished in: Euro-Par Workshops (2) (2014)
Keyphrases
- finite element
- graphics processing units
- numerical integration
- massively parallel
- general purpose
- gpu implementation
- ordinary differential equations
- parallel computing
- parallel programming
- differential equations
- numerical solution
- parallel processing
- zernike moments
- graphics hardware
- high performance computing
- real time
- finite element analysis
- parallel implementation
- mesh generation
- floating point
- computing systems
- probability density
- parallel architectures
- diffusion equation
- parallel algorithm
- shape analysis