C-for-Metal: High Performance Simd Programming on Intel GPUs.
Guei-Yuan LuehKaiyu ChenGang ChenJoel FuentesWei-Yu ChenFangwen FuHong JiangHongzheng LiDaniel RheePublished in: CGO (2021)
Keyphrases
- single instruction multiple data
- graphics processing units
- highly parallel
- massively parallel
- parallel processing
- real time
- multicore processors
- parallel architectures
- general purpose
- parallel implementation
- programming language
- scientific computing
- parallel computing
- parallel programming
- parallel algorithm
- high performance computing
- computing systems
- grain size
- processing elements
- multi core processors
- gpu implementation
- efficient implementation
- array processor
- memory bandwidth
- neural network
- graphics hardware
- computer architecture
- object oriented programming
- development environment
- floating point
- fine grained
- software engineering
- object oriented