Coordinating GPU threads for OpenMP 4.0 in LLVM.
Carlo BertolliSamuel AntãoAlexandre E. EichenbergerKevin O'BrienZehra SuraArpith C. JacobTong ChenOlivier SallenavePublished in: LLVM@SC (2014)
Keyphrases
- graphics processing units
- parallel programming
- multi threaded
- parallel computing
- transactional memory
- multi core processors
- shared memory
- high performance computing
- parallel computation
- real time
- graphics hardware
- parallel algorithm
- general purpose
- multithreading
- parallel execution
- parallel processing
- massively parallel
- gpu implementation
- parallel implementation
- computing systems
- graphics processors
- parallel architectures
- graphic processing unit
- multi processor
- gpu accelerated
- commodity hardware
- cloud computing
- floating point
- heterogeneous computing
- processing units
- data transfer
- computing resources
- efficient implementation
- autonomous agents
- operating system
- data management
- level parallelism
- neural network
- data sets