Niijima: sound and automated computation consolidation for efficient multilingual data-parallel pipelines.
Guoqing Harry XuMargus VeanesMichael BarnettMadan MusuvathiTodd MytkowiczBen ZornHuan HeHaibo LinPublished in: SOSP (2019)
Keyphrases
- data sets
- database
- data structure
- data collection
- efficient computation
- big data
- raw data
- training data
- data analysis
- digital libraries
- prior knowledge
- data sources
- data points
- image data
- data processing
- synthetic data
- missing data
- high quality
- databases
- parallel implementation
- complex data
- data objects
- experimental data
- computer systems
- natural language
- knowledge discovery
- end users
- xml documents