Implementing OpenMP's SIMD Directive in LLVM's GPU Runtime.
Eric WrightJohannes DoerfertShilei TianBarbara M. ChapmanSunita ChandrasekaranPublished in: ICPP (2023)
Keyphrases
- parallel programming
- massively parallel
- graphics processing units
- parallel processing
- parallel algorithm
- parallel implementation
- parallel computing
- highly parallel
- parallel architectures
- shared memory
- real time
- single instruction multiple data
- parallel computation
- high performance computing
- transactional memory
- processor array
- efficient implementation
- parallel execution
- distributed memory
- graphics hardware
- graphics processors
- general purpose
- multi core processors
- gpu implementation
- method invocation
- parallel computers
- image processing
- parallel architecture
- computing systems
- peer to peer