Making Leaps in Scientific Productivity through Scalable Computation and Data
| Main Author: | Evans, Ben |
|---|---|
| Format: | info Proceeding eJournal |
| Bahasa: | eng |
| Terbitan: |
, 2018
|
| Online Access: |
https://zenodo.org/record/3336620 |
Daftar Isi:
- Through NCRIS programs, we have established a large collection of reference datasets next to NCI’s peak computing capability so to provide a significant improvement to the accessibility of climate, weather, geophysics and environmental data in a form suitable for HPC modelling and modern high performance data analysis. These FAIR datasets and services have since become a central infrastructure which is used by the climate community, many NCRIS capabilities (e.g, IMOS, TERN, AuScope, AAL), and government programs (e.g., weather prediction, Digital Earth Australia). As a result there are now significant successes in productivity of scientific outcomes through adoption of these national investment in HPC and data products. The colocating of scientific datasets with HPC computational infrastructure has a long and steady timeline with deepening alignment to demonstrate the success of the approach. Furthermore, the historical disconnect in approaches between the sciences with large volume data and that of the long tail of data are also now steadily closing. The standards for interoperability and interconnectivity between scientific fields have been slowly maturing, and in many cases transdisciplinary science is now a reality. The technical infrastructure for underpinning science is no longer advancing according to Moore’s law (and equivalents) and is evolving in unexpected ways - affecting both HPC models and data. These have required us to consider our software and algorithms, increasing our effort for improvements and maintainability, and reconsidering some old assumptions of data precision and reproducibility. In this talk I will discuss the journey so far and challenges ahead.