Carmen B. Navarrete

AutoTune: a plugin-driven approach to the automatic tuning of parallel applications

Performance analysis and tuning is an important step in programming multicore- and manycore-based parallel architectures. While there are several tools to help developers analyze application performance, no tool provides recommendations about how to tune the code. The AutoTune project is extending Periscope, an automatic distributed performance analysis tool developed by Technische Universitat Munchen, with plugins for performance and energy efficiency tuning. The resulting Periscope Tuning Framework will be able to tune serial and parallel codes for multicore and manycore architectures and return tuning recommendations that can be integrated into the production version of the code. The whole tuning process --- both performance analysis and tuning --- will be performed automatically during a single run of the application.

A multi-aspect online tuning framework for HPC applications

Developing software applications for high-performance computing (HPC) requires careful optimizations targeting a myriad of increasingly complex, highly interrelated software, hardware and system components. The demands placed on minimizing energy consumption on extreme-scale HPC systems and the associated shift towards hete rogeneous architectures add yet another level of complexity to program development and optimization. As a result, the software optimization process is often seen as daunting, cumbersome and time-consuming by software developers wishing to fully exploit HPC resources. To address these challenges, we have developed the Periscope Tuning Framework (PTF), an online automatic integrated tuning framework that combines both performance analysis and performance tuning with respect to the myriad of tuning parameters available to today’s software developer on modern HPC systems. This work introduces the architecture, tuning model and main infrastructure components of PTF as well as the main tuning plugins of PTF and their evaluation.

DVFS automatic tuning plugin for energy related tuning objectives

Energy consumption will become one of the dominant cost factors that will govern the next generation of large HPC centers. In this paper we present the Dynamic Voltage Frequency Scaling (DVFS) Plugin to automatically tune several energy related tuning objectives at a region-level of HPC applications. This plugin works with the Periscope Tuning Framework which provides an automatic tuning framework including analysis, experiment creation, and evaluation. The tuning actions are based on changes in the frequency via the DVFS. The tuning objectives include the tuning of energy consumption, total cost of ownership, energy delay product and power capping. The tuning is based on a model that relies on performance data and predicts energy consumption, time, and power consumption at different CPU frequencies.

Energy model derivation for the DVFS automatic tuning plugin: tuning energy and power related tuning objectives

Energy consumption will become one of the dominant cost factors that will govern the next generation of large HPC centers. In this paper we present the Dynamic Voltage Frequency Scaling (DVFS) Plugin to automatically tune several energy related tuning objectives at a region-level of HPC applications. This plugin works with the Periscope Tuning Framework which provides an automatic tuning framework including analysis, experiment creation, and evaluation. The tuning actions are based on changes in the frequency via the DVFS. The tuning objectives include the tuning of energy consumption, total cost of ownership, energy delay product and power capping. The tuning is based on a model that relies on performance data and predicts energy consumption, time, and power consumption at different CPU frequencies. The derivation of the models for the DVFS plugin with the principal component analysis is included.

Node level power measurements on a petaflop system

The complexity and size of scientific and engineering challenges are continually increasing to the point where they are approaching exascale computing. One of the main challenges is to be able to run scientific software applications on these extremely large systems in an energy efficient manner, as power consumption will become one of the dominant cost factors that will govern the next generation of large high performance computing data centers. In this paper, we present the results of node level power measurements on a petaflop HPC system.

MPI and Non-MPI Simulations for Epitaxial Surface Growth

Usually, theories of surface growth are based on the study of global processes without taking in account the local behaviour of atoms. We have implemented two Monte-Carlo simulations. In this work we present these two simulations. Both makes use of local principles of thermodynamic for atomic deposition, relaxation and diffusion of a growing surface, and are based on a simple model that allows us to simulate the growing process of a surface of a certain material. The first one is a quasi-static model whereas the second recreates the atomic interaction. The obtained results agree with those that use global theories and with experimental results of scanning tunneling microscopy (STM)

Epitaxial surface growth with local interaction, parallel and non-parallel simulations

Usually, theories of surface growth are based on the study of global processes without taking into account the local behaviour of atoms. In this work we present two simulations making use of a parallel computing library. These two simulations are based on a simple model that allows us to simulate the surface growing process of a certain material. The first one is a quasi-static model whereas the second recreates the atomic interaction considering the free atoms in continuous movement along the surface. Both simulations make use of local principles of thermodynamic for atomic deposition, relaxation and diffusion of a growing surface. The obtained results agree with those that use global theories and with experimental results of Scanning Tunneling Microscopy (STM).