Evaluating the Performance of NVIDIA's A100 Ampere GPU for Sparse Linear Algebra Computations.
Yuhsiang Mike TsaiTerry CojeanHartwig AnztPublished in: CoRR (2020)
Keyphrases
- linear algebra
- parallel implementation
- graphics processing units
- graphics processors
- graphics hardware
- gpu implementation
- image processing
- sparse matrices
- computer architecture
- singular value decomposition
- parallel computing
- parallel computation
- sparse representation
- general purpose
- compute unified device architecture
- high dimensional
- information systems
- multiscale