Virtual Institute — High Productivity Supercomputing

19th VI-HPS Tuning Workshop (NLHPC, Santiago, Chile)

Date

Tuesday 27th - Thursday 29th October 2015.

Location

The workshop will take place at the NLHPC National Laboratory for HPC, Center for Mathematical Modeling, Universidad de Chile, Santiago, Chile, in the 7th floor meeting room, Beauchef 851, Edificio Norte.

Goals

This workshop organized by VI-HPS and the Universidad de la Frontera (UFRO, Temuco, Chile) at NLHPC will:

  • give an overview of the VI-HPS programming tools suite
  • explain the functionality of individual tools, and how to use them effectively
  • offer hands-on experience and expert assistance using the tools

Programme Overview

Presentations and hands-on sessions are planned on the following topics:

  • Setting up, welcome and introduction
  • Score-P instrumentation and measurement
  • Scalasca automated trace analysis
  • Periscope automated performance analysis
  • Paraver trace analysis and performance prediction
  • MAQAO performance analysis & optimization
  • PAPI hardware performance counters

A brief overview of the capabilities of these and associated tools is provided in the VI-HPS Tools Guide.

The workshop will be held in English and run from 09:00 to not later than 18:00 each day, with breaks for lunch and refreshments. There is no course fee, however, all participants are responsible for their own lunches, travel and accommodation.

Classroom capacity is limited, therefore priority will be given to applicants with parallel codes already running on the workshop computer system (Leftraru), and those bringing codes from similar Linux cluster systems to work on. Participants are therefore encouraged to prepare their own MPI, OpenMP and hybrid MPI+OpenMP parallel application codes for analysis.

Participants are expected to use their own notebook computers with SSH/X11 software installed to connect to Leftraru.

TW19@NLHPC class back TW19@NLHPC class front

Programme in Detail

Day 1: Tuesday 27 October
08:30 (registration & set-up of course accounts on workshop computers)
09:00 Welcome [Andrés Ávila, UFRO]
  • Introduction to VI-HPS & overview of tools [Alexandre Strube, JSC]
  • Introduction to parallel performance engineering [Alexandre Strube]
    		•
    11:00 (break)
    11:30 Leftraru computer system and software environment
  • Building and running NPB-MZ-MPI on Leftraru [Michael Firbach, TUM]
  • PAPI hardware performance counters [Andrés Ávila, UFRO]
    • 13:00 (lunch)
    14:30 MAQAO performance analysis tools [Andres Charif-Rubial, UVSQ]
  • MAQAO hands-on exercises [Andres Charif-Rubial & Emmanuel Oseret]
    • 16:00 (break)
    16:30 Hands-on coaching to apply tools to analyze participants' own code(s)
  • Review of day and schedule for remainder of workshop
    • 18:00 (adjourn)

    Day 2: Wednesday 28 October
    09:30 Score-P instrumentation & measurement toolset [Michael Firbach, TUM]
  • Score-P hands-on exercises
  • CUBE profile explorer hands-on exercises [Alexandre Strube, JSC]
  • Score-P analysis scoring & measurement filtering  [Michael Firbach]
    		•
    11:00 (break)
    11:30 Scalasca automated trace analysis [Alexandre Strube, JSC]
  • Scalasca hands-on exercises
    • 13:00 (lunch)
    14:30 Periscope Tuning Framework [Michael Firbach, TUM]
  • Periscope hands-on exercises
    		•
    16:00 (break)
    16:30 Hands-on coaching to apply tools to analyze participants' own code(s)
  • Review of day and schedule for remainder of workshop
    • 18:00 (adjourn)

    Day 3: Thursday 29 October
    09:30 Paraver tracing tools suite [Judit Gimenez, BSC]
  • Paraver hands-on exercises
    		•
    11:00 (break)
    11:30 Hands-on coaching to apply tools to analyze participants' own code(s)
    13:00 (lunch)
    14:30 Review
  • Presentation of participant's results and discussion
    • 16:30 (adjourn)

    Hardware and Software Platforms

    Leftraru: HP SL230/SL250 system:

    • 132 compute nodes each with two Intel Xeon E5-2660v2 'Ivy Bridge' processors (2.20GHz, 10 cores per processor, 2 hardware threads per core) and 48 GB memory
    • 12 Intel Xeon Phi 5110p co-processor cards
    • network: Infiniband FDR interconnect
    • software: Intel, MPICH & Open MPI; Intel & GCC compilers
    • filesystem: 274TB Lustre

    The local HPC system Leftraru is the primary platform for the workshop and will be used for the hands-on exercises. Course accounts will be provided during the workshop to participants without existing accounts. Other systems where up-to-date versions of the tools are installed can also be used when preferred, though support may be limited and participants are expected to already possess user accounts on non-local systems. Regardless of whichever systems they intend to use, participants should be familiar with the relevant procedures for compiling and running their parallel applications (via batch queues where appropriate).

    Registration

    http://encuesta.nlhpc.cl/index.php/114541/lang-en

    Contact

    Tuning Workshop Series

    Brian Wylie
    Jülich Supercomputing Centre
    Forschungszentrum Jülich GmbH
    Phone: +49 2461 61-6589
    Email: b.wylie[at]fz-juelich.de     		   

    Local Arrangements

    Andrés Ávila
    Centro de Excelencia de Modelación y Computación Científica
    Universidad de la Frontera
    Phone: +56 (45) 325921
    Email: andres.avila[at]ufrontera.cl