Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
research:start [2018-09-29 11:46]
Julian Kunkel [High-Performance Storage]
research:start [2019-01-04 18:02] (current)
Line 78: Line 78:
 individual workflows and the overall system load. All this must be achieved with system interoperability and standardised application programming interfaces (APIs). Additionally,​ data centres are seeing challenges supporting mixed workflows of HPC and data analytics; The general consensus is that this needs to change and requires new methods and thinking about how to access storage, describe data and manage workflows. individual workflows and the overall system load. All this must be achieved with system interoperability and standardised application programming interfaces (APIs). Additionally,​ data centres are seeing challenges supporting mixed workflows of HPC and data analytics; The general consensus is that this needs to change and requires new methods and thinking about how to access storage, describe data and manage workflows.
  
-The efficient, convenient, and robust data management and execution of data-driven workflows are key for productivity in computer-aided RD&E particularly for data-intense research such as climate/​weather with complex processing workflows. Still, the storage stack is based on low-level I/O that requires complex manual tuning. ​+The efficient, convenient, and robust data management and execution of data-driven workflows are key for productivity in computer-aided RD&E particularly for data-intense research such as climate/​weather with complex processing workflows. Still, the storage stack is based on low-level I/O that requires complex manual tuning.
 In this environment,​ we are researching a novel I/O API that will lift the abstraction to a new level paving the road for intelligent storage systems. In this environment,​ we are researching a novel I/O API that will lift the abstraction to a new level paving the road for intelligent storage systems.
 One key benefit of these systems is the exploitation of heterogeneous storage and compute infrastructures by scheduling user workloads efficiently across a system topology -- a concept called Liquid Computing. One key benefit of these systems is the exploitation of heterogeneous storage and compute infrastructures by scheduling user workloads efficiently across a system topology -- a concept called Liquid Computing.
-These systems and API will provide ​the core infrastructure ​for scientific ​applications ​but also enable to host big-data tools like Spark in an efficient manner. +These systems ​can improve the data handling over time without user intervention ​and lead towards an era with smart system infrastructure. 
 +They bear the opportunity to become ​the core I/O infrastructure ​in scientific ​computing ​but also enable to host big-data tools like Spark in an efficient manner.
  
 **We believe -- intelligent storage systems are the solution.** **We believe -- intelligent storage systems are the solution.**