System and Application Scenarios for Disaster Management Processes, the Rainfall-Runoff Model Case Study

Abstract

Part 5: Industrial Management and Other ApplicationsInternational audienceIn the future, the silicon technology will continue to reduce following the Moore’s law. Device variability is going to increase due to a loss in controllability during silicon chip fabrication. Then, the mean time between failures is also going to decrease. The current methodologies based on error detection and thread re-execution (roll back) can not be enough, when the number of errors increases and arrives to a specific threshold. This dynamic scenario can be very negative if we are executing programs in HPC systems where a correct, accurate and time constrained solution is expected. The objective of this paper is to describe and analyse the needs and constraints of different applications studied in disaster management processes. These applications fall mainly in the domains of the High Performance Computing (HPC). Even if this domain can have differences in terms of computation needs, system form factor and power consumption, it nevertheless shares some commonalities

Harnessing Performance Variability: A HPC-Oriented Application Scenario

“…The quality of service (QoS) of the RR model is expressed in terms of accuracy, that is proportional to the number of Montecarlo iterations; and the expected execution time [11], [13]. Accordingly, each of the three flood warning levels can be mapped to a given quality of service level: …”

Just-In-Time Execution Through On-Demand Resource Allocation in HPC Systems

“…HARPA-OS enables the management of multiple applications that compete on the usage of multiple many core computation devices. It also exposes a run-time library [11,12] that is in charge of: a) synchronizing the execution of applications with the runtime-variable resource allocations; and b) notifying to the resource manager the runtime-variable Quality of Service goals of applications, so that the HARPA-OS scheduling policy, which can be either chosen from a set of predefined ones or implemented from scratch, is able to take into account the feedback coming from applications when computing resource allocations.…”

Flood Prediction Model Simulation With Heterogeneous Trade-Offs In High Performance Computing Framework

“…Shorter response time in critical situations can for example be acquired by decreasing the number of Monte-Carlo samples (also decreasing the precision of the results), or by allocating more computational resources (maintaining the same precision level if the load is rebalanced appropriately). We identified two main application scenarios (Portero, Kuchař, Vavřík, Golasowski & Vondrák 2014) that support the different workload of the system based on the flood emergency situation.…”