High-performance computing infrastructure: The open science high-performance computing infrastructure such as Teragrid can be modeled as a graph by representing the supercomputing sites as nodes. Additionally, POP sites may be represented as nodes, and fiber connections of the underlying network may be represented as edges. Each supercomputer site provides redundant power and air cooling systems. Replicating the computing systems to achieve robustness is not a pragmatic strategy due to the extremely high cost of these systems. Identify other mechanisms that can increase the robustness of this system.
Already registered? Login
Not Account? Sign up
Enter your email address to reset your password
Back to Login? Click here