Hiding I/O latency with pre-execution prefetching for parallel applications.
Yong ChenSurendra BynaXian-He SunRajeev ThakurWilliam GroppPublished in: SC (2008)
Keyphrases
- prefetching
- disk array
- web prefetching
- response time
- buffer pool
- access patterns
- replacement policy
- hit rate
- access latency
- web documents
- web caching
- user perceived latency
- hit ratio
- cache misses
- caching scheme
- parallel processing
- web page prediction
- web logs
- web usage mining
- web objects
- information extraction
- multiprocessor systems
- file system
- prediction accuracy
- machine learning