Sandra Méndez

Methodology for Performance Evaluation of the Input/Output System on Computer Clusters

The increase of processing units, speed and computational power, and the complexity of scientific applications that use high performance computing require more efficient Input/Output (I/O) systems. In order to efficiently use the I/O it is necessary to know its performance capacity to determine if it fulfills applications I/O requirements. This paper proposes a methodology to evaluate I/O performance on computer clusters under different I/O configurations. This evaluation is useful to study how different I/O subsystem configurations will affect the application performance. This approach encompasses the characterization of the I/O system at three different levels: application, I/O system and I/O devices. We select different system configuration and/or I/O operation parameters and we evaluate the impact on performance by considering both the application and the I/O architecture. During I/O configuration analysis we identify configurable factors that have an impact on the performance of the I/O system. In addition, we extract information in order to select the most suitable configuration for the application.

A Parallel I/O Behavior Model for HPC Applications Using Serial I/O Libraries

Analyzing and understanding an applications Input/Output (I/O) access patterns provides key information to gain insight into how the behavior of an application affects its performance in different systems. In this paper, we propose a portable model to represent the I/O behavior of parallel applications that use serial I/O libraries, as part of a more holistic model for I/O of parallel applications. The model allows actions such as replication of the application behavior on different HPC systems and evaluation of the I/O performance without running the real application. In this paper, we evaluate the portability of the proposed model for MADbench2 and ABYSS- P in four HPC systems. We analyze the impact of the parallel system configuration in a Cloud environment for the ABYSS-P application by using the proposed I/O behavior model.

PIOM-PX: A Framework for Modeling the I/O Behavior of Parallel Scientific Applications

Current parallel scientific applications generate a huge amount of data that must be managed efficiently for the HPC storage systems. However, the I/O performance depends on the application I/O behavior and the configuration of the underlying I/O system. To understand the I/O behavior in the software stack and its impact on the I/O operations defined in the application logic, we propose a design framework named PIOM-PX, which allows to define an I/O behavior model based on the I/O phases of HPC applications at POSIX-IO level. We validate our framework using the IOR benchmark for four I/O patterns and we analyze the I/O behavior of NAS BT-IO.

Analyzing the Parallel I/O Severity of MPI Applications

Performance evaluation of parallel applications plays an important role in High Performance Computing (HPC). This is also applied to parallel I/O performance evaluation, which requires understanding the I/O pattern of the application and having knowledge about the performance capacity of the HPC I/O system. In this paper, we present a methodology to evaluate the I/O performance of parallel applications based on the I/O severity degree. We define the I/O severity concept taking into account the I/O requirements of a parallel application, the mapping of I/O processes and the configuration of the I/O subsystem. Requirements are expressed in units denominated I/O phases, which are defined using the temporal and spatial pattern of different files of the application. Our approach is applied to the I/O kernels of scientific applications such as S3DIO, FLASH-IO and BT-IO on the SuperMUC supercomputer. Experimental results show that our methodology allows us to identify if a parallel application is limited by the I/O subsystem and identifying possible root causes of the I/O problems.