Triple-C: Resource-usage prediction for semi-automatic parallelization of groups of dynamic image-processing tasks

Abstract

With the emergence of dynamic video processing, such as in image analysis, runtime estimation of resource usage would be highly attractive for automatic parallelization and QoS control with shared resources. A possible solution is to characterize the application execution using model descriptions of the resource usage. In this paper, we introduce Triple-C, a prediction model for Computation, Cache-memory and Communication-bandwidth usage with scenario-based Markov chains. As a typical application, we explore a medical imaging function to enhance objects of interest in X-ray angiography sequences. Experimental results show that our method can be successfully applied to describe the resource usage for dynamic imageprocessing tasks, even if the flow graph dynamically switches between groups of tasks. An average prediction accuracy of 97% is reached with sporadic excursions of the prediction error up to 20-30%. As a case study, we exploit the prediction results for semi-automatic parallelization. Results show that with Triple-C prediction, dynamic processing tasks can be executed in real-time with a constant low latency.

Large-scale analysis of neuroimaging data on commercial clouds with content-aware resource allocation strategies

“…More critically, most approaches do require an estimate of the execution time for each job and application to make efficient and accurate allocation and scheduling decisions (Kim et al, 2009; Garg et al, 2010). Typically, these estimates are obtained by analytical modeling of the underlying source code (which is not always available), or using empirical and historical data of each job and application type (Albers et al, 2009; Kim et al, 2009; Garg et al, 2010; Matsunaga and Fortes, 2010). However, when the job to be executed (in our case a registration) is homogeneous (i.e.…”

“…Most works in the literature related to scheduling or resource-provisioning would assume either the worst-case scenario for the number of cycles needed for an application (by source code profiling; see Li et al, 2009), or they would rely on a historical average estimate (Smith et al, 1998; Kapadia et al, 1999), or learned models of the usage of computational resources for an application (Albers et al, 2009; Matsunaga and Fortes, 2010). For the same application (e.g.…”

“…6 More critically, most approaches do require an estimate of the execution time for each job and application to make efficient and accurate allocation and scheduling decisions [5], [19]. Typically these estimates are obtained by analytical modeling of the underlying source code (which is not always available), or using empirical and historical data of each job and application type [5], [19], [28], [29]. However, when the job to be executed (in our case a registration) is homogeneous (i.e., the same job and parameters is executed on different data of the same size), we would have to rely on an average estimate of execution time [30]- [32].…”

“…Most works in the literature related to scheduling or resource provisioning would assume either the worst case scenario for the number of cycles needed for an application (by source code profiling) [32], or they would rely on a historical average estimate [30], [31], or learned models of the usage of computational resources for an application [28], [29]. For the same application (e.g., a registration) with data size equal for each case, this means that the execution time is either estimated using a constant (a worst case value is assumed) or as the historical mean (or maximum) of previous executions for the same core type.…”

Developing a Toolkit for Task Characteristics Prediction Based on Analysis of Queue’s History of a Supercomputer

“…The purpose of this work is to do predictive analytics on resource allocation using machine learning methods. Using algorithms, including machine learning algorithms, to predict required resources for jobs has been pursued by several previous studies [3][4][5][6][7][8]. Using historical data is a reasonable method to improve the performance of the schedulers in order to utilize the overall HPC system efficiently [9].…”