… HPC application traces and real runs on the Argonne Fusion cluster. Experiments show that
our error feedback … In Section IV, we describe our error feedback control model in the context …

… overhead (see Section VB), at the same time providing application developers useful
feedback regarding resilience from a higher-level point of view. Our methodology and pluggable …

… Control Signal Calculator: The error (err) in the system state is calculated as the diference
… The feedback controller calculates the feedback to the actuator as a function of this error. It …

… the successful application of classic control theory to HPC … to the requested deadlines (12.4
percent error). The rest of the … the performance modeling of HPC applications. Section 4 …

… tracking of error propagation and resilience properties, and we use it to present a set of
computation patterns that are responsible for making representative HPC applications naturally …

… Software and hardware fault tolerance, scaling performance issues, soft error effect on … the
performance feedback to the Analyzer. This component analyzes the feedback and generates …

… HPC application developers to develop autotuning technology that meets these goals and is
compatible with the development of HPC … For tuning tools that rely on dynamic feedback at …

… At runtime, the model is a posteriori tuned to support activities such as feedbackoriented …
These issues are addressed typically by programmers in a “trial and error” manner, ie by …

… 4.2 Error Feedback Prediction In our detector, we use curve … error feedback model that
can significantly simplify the prediction. We also demonstrate the identity between the feedback …

… are untenable in emergent applications that use HPCs as inputs to complete a feedback loop
and … In this paper, we define HPC error as magnitude of difference between corresponding …