The workshop was held in English and run from 09:00 to 17:30 each day, with breaks for lunch and refreshments (sponsored by SGI).
| Wed 9 Sep | |
| 08:30 | (registration & laptop set-up) |
| 09:00 | Welcome & Introduction to VI-HPS [Wylie, JSC]
|
| 09:30 | Introduction to performance engineering [Malony, U.Oregon] |
| 10:15 | Marmot correctness checking tool [Hilbrich, TUD-ZIH]
|
| 10:45 | (break) |
| 11:15 | TAU performance analysis toolset [Malony, U.Oregon]
|
| 12:30 | (lunch) |
| 13:30 | Scalasca performance analysis toolset [Wylie, JSC]
|
| 14:45 | (break) |
| 15:15 | Vampir performance analysis toolset [Doleschal, TUD-ZIH]
|
| 16:30 | Review of day and schedule for rest of workshop. Individual preparation of participants' own codes and further exercises. |
| 17:30 | (adjourn) |
| Thu 10 Sep | |
| 09:00 | Scalasca hands-on with participants' own code(s) [Geimer & Wylie, JSC]
|
| 12:30 | (lunch) |
| 13:30 | Marmot/Vampir hands-on with participants' own codes [Hilbrich & Doleschal, TUD-ZIH]
|
| 17:00 | Review of day and schedule for tomorrow |
| 17:30 | (adjourn) |
| Fri 11 Sep | |
| 09:00 | Coaching to apply tools to check, analyze & tune participants' own code(s). Additional presentations covering in-depth and advanced tool use (scheduled according to demand). |
| 12:00 | (lunch) |
| 14:30 | Review of workshop and participants' experiences with tools |
| 15:00 | (adjourn or continue with work to 17:30) |
Classroom capacity was limited, therefore priority was given to applicants with codes already running on the workshop computer systems, and those bringing codes from similar systems to work on. Participants were therefore encouraged to prepare their own MPI, OpenMP and hybrid OpenMP/MPI parallel application code(s) for analysis.
Participants used their own notebook computers for the workshop: power and network connections were provided. The first day tutorial used a Live-DVD for hands-on exercises: alternatives were arranged for those who didn't have access to an x86-compatible notebook computer with DVD drive.