QCD Library for GPU Cluster with Proprietary Interconnect for GPU Direct Communication.
Norihisa FujitaHisafumi FujiiToshihiro HanawaYuetsu KodamaTaisuke BokuYoshinobu KuramashiMike ClarkPublished in: Euro-Par Workshops (1) (2014)
Keyphrases
- real time
- graphics hardware
- graphics processors
- gpu implementation
- parallel processing
- graphics processing units
- gpu accelerated
- parallel computing
- communication systems
- parallel implementation
- cluster of workstations
- communication protocol
- parallel computation
- clustering algorithm
- hierarchical structure
- open source
- neural network