CuPBoP: CUDA for Parallelized and Broad-range Processors.
Ruobing HanJun ChenBhanu GargJeffrey YoungJaewoong SimHyesoon KimPublished in: CoRR (2022)
Keyphrases
- distributed memory
- parallel implementation
- parallel computing
- shared memory
- parallel computation
- parallel algorithm
- parallel programming
- compute unified device architecture
- parallel processing
- single processor
- map reduce
- comprehensive set
- parallel computers
- multiprocessor systems
- general purpose
- multithreading
- high end
- parallel architecture
- high performance computing
- real time
- computing systems
- gpu implementation
- parallel architectures
- embedded processors