Selectively GPU Cache Bypassing for Un-Coalesced Loads.
Chen ZhaoFei WangZhen LinHuiyang ZhouNanning ZhengPublished in: ICPADS (2016)
Keyphrases
- prefetching
- load balancing
- real time
- response time
- graphics hardware
- multithreading
- parallel computing
- data access
- hit rate
- query processing
- graphics processors
- parallel implementation
- main memory
- embedded processors
- gpu implementation
- memory bandwidth
- cache misses
- dynamic response
- memory hierarchy
- cache management
- graphics processing units
- parallel computation
- web caching
- back end
- general purpose
- replacement policy
- caching scheme
- cache replacement
- heterogeneous computing
- gpu accelerated
- garbage collection
- data management
- database systems
- neural network