A Hierarchical Jacobi Iteration for Structured Matrices on GPUs using Shared Memory.
Mohammad Shafaet IslamQiqi WangPublished in: HPEC (2022)
Keyphrases
- shared memory
- parallel programming
- parallel architectures
- multi core systems
- parallel algorithm
- message passing
- commodity hardware
- parallel computing
- distributed memory
- multi processor
- parallel machines
- parallel computation
- parallel architecture
- general purpose
- multi core processors
- shared memory multiprocessors
- parallel computers
- parallel execution
- memory access
- address space
- high end
- single processor
- graphics processing units
- efficient implementation
- belief propagation
- shared memory multiprocessor
- cloud computing
- dynamic programming