Implementing and Optimizing a GPU-aware MPI Library for Intel GPUs: Early Experiences.
Chen-Chun ChenKawthar Shafie KhorassaniGoutham Kalikrishna Reddy KunchamRahul VaidyaMustafa AbduljabbarAamir ShafiHari SubramoniDhabaleswar K. PandaPublished in: CCGrid (2023)
Keyphrases
- parallel programming
- multi core processors
- graphics processing units
- parallel computing
- parallel implementation
- general purpose
- parallel algorithm
- single instruction multiple data
- graphics hardware
- high performance computing
- parallel processing
- computer architecture
- parallel computation
- shared memory
- gpu implementation
- message passing interface
- graphics processors
- highly parallel
- parallel architectures
- efficient implementation
- cloud computing
- processing units
- memory bandwidth
- massively parallel
- commodity hardware
- programming environment
- real time
- parallel computers
- message passing
- cpu implementation
- case study
- computational power
- computing systems
- graphics cards
- compute unified device architecture
- heterogeneous computing