Completed
Computation and cost of energy used to perform it
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
A Superfacility Model for Data-Intensive Science
Automatically move to the next video in the Classroom when playback concludes
- 1 Welcome!
- 2 "Big Data" and science
- 3 Science and Internet of Things
- 4 Many science challenges are at the boundary of theory and experiment
- 5 Roadmap of the talk
- 6 Science and search facilities
- 7 Automated search and meta-data analysis
- 8 Past and future high-performance facilities
- 9 Filtering and de-noising data
- 10 Math challenges in energy science data
- 11 Machine learning for science
- 12 Amount of available data grows faster than our computational capabilities
- 13 DOE ECP, Department of Energy exascale Computing Project
- 14 Computation and cost of energy used to perform it
- 15 The most costly thing inside a machine is moving data around
- 16 Data vs. simulations: The irregularity spectrum
- 17 Programming models for exascale computations
- 18 Example: whole-mantle seismic model
- 19 Example: analysis of genome
- 20 Problems with distributed hash tables
- 21 Optimizing algorithm for matrix multiplication
- 22 7 Giants of Data and 7 Dwarfs of Simulation
- 23 Systems for data analysis
- 24 Why high-level languages like Julia are key
- 25 Specialization of computer architectures
- 26 High-Performance Computing Policies
- 27 Acknowledgements
