12th VI-HPS Tuning Workshop @ JSC

Oct 7, 2013, 12:30 PM → Oct 11, 2013, 4:30 PM CET

Rotunda, building 16.3, room 301 (Jülich Supercomputing Centre)

Goals

This workshop organized by VI-HPS for the German PRACE Advanced Training Centre (PATC) hosted by Jülich Supercomputing Centre 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 with participants' own application codes

Programme Overview

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

• Setting up, welcome and introduction
• Parallel file I/O bottlenecks and solutions
• Score-P instrumentation, measurement and analysis infrastructure
• Scalasca performance analysis toolset
• Vampir trace analysis toolset
• TAU performance system
• Paraver trace analysis toolset
• Periscope automated analysis tool
• MUST correctness checking of MPI
• STAT stack trace analysis tool (plus other tools to be determined)

Learning outcomes: Participants will become familiar with portable state-of-the-art parallel performance analysis and correctness checking tools.

Pre-requisites: Participants are strongly encouraged to bring their own MPI and OpenMP parallel applications to work with during the tuning workshop. They should be familiar with the procedures for compiling and running their applications on BlueGene (or similar HPC) systems. Places are limited and acceptance will be based on the participant information provided when registering.

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 fee for participation, however, participants are responsible for their own travel and accommodation, and to access the HPC systemsthey are expected to bring their own notebook computer suitably configured with SSH and X11 capabilities.

Hardware and Software Platforms

JUQUEEN: this 28-rack BlueGene/Q system will be used for the hands-on exercises:

• 28,672 compute nodes with IBM PowerPC A2 processors (1.6GHz, 16 cores per processor, 4-way hardware threads per core) and 16 GB memory per node
• software: IBM lightweight CNK, BlueGene MPI and XL compilers

The local HPC system Juqueen is the primary platform for the workshop, with an x86_64 Linux cluster used for analysis presentation tools not available on Juqueen. 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).

The programme in detail can be found on the VI-HPS training web site.

Registration

Registration is open and will close in September 2013 or whenever the class is full: the number of participants is limited and selection will be made based on the information provided when registering.

Contact
For any questions concerning the course please send an e-mail to b.wylie@fz-juelich.de.