Program

October 22, 2014

09:00-09:30

Welcome and Overview about Intel® Software Development Tools
Provides an overview about Intel® Software Development tools such as Intel® Parallel Studio XE and Intel® Cluster Studio XE. For developers not familiar with those suites, all components are briefly explained. For developers already working with some of the tools we also list the latest key features.

09:30-10:45

Intel® C++ and Fortran Compiler1)

10:45-11:00

Break

11:00-12:15

Intel® Architecture and Vectorization
Vectorization is an important aspect of Intel C++ and Fortran Compilers. Understanding the technical possibilities, limits and roadblocks of vectorization is crucial for compiling efficient and performance oriented applications. This module gives an introduction to the Intel architecture (IA32, Intel64 & Intel® MIC) in terms of their vectorization capabilities (also known as SIMD features). Furthermore it describes the technologies all Intel compilers provide for them, as well as typical problems and solutions in that area.

12:15-13:15

Lunch Break

13:15-13:45

Intel® Math Kernel Library and Intel® Performance Primitives1)

13:45-14:30

Intel® Threading Building Blocks and Intel® OpenMP*1)

14:30-14:45

Break

14:45-16:00

Intel® Vtune™ Amplifier XE: Performance Analysis incl. Demo
Intel® VTune™ Amplifier XE is a sophisticated analysis tool that helps to identify performance bottlenecks in serial and parallel programs. The tool also contains powerful techniques identifying the sources for concurrency inefficiencies in parallel/multi-core applications. In this module we will introduce common software optimization methodologies using the Intel® VTune™ Amplifier XE profiling tool. Multithreaded software written in native programming languages (e.g C/C++/FORTRAN) running on shared memory systems using standard parallel programming models (e.g. POSIX, OpenMP*) will be leveraged during the training to demonstrate various techniques of performance and applications scalability analysis.

16:00-16:30

Q & A

1)This training modules provide an introduction into the feature set of the Composer XE tool suite
which consists of the C++ and Fortran Compilers, domain specific performance libraries and
multithreading libraries. The focus of this module is on integration of Composer XE into
development environments on Windows and Linux and demonstrating the features and
performance benefits of the Intel Compilers. A brief overview of OpenMP 4.0 complements the
session.


l

October 23, 2014 

09:00-10:00

Numerical Stability with Intel® C++ and Fortran Compiler
This topic raises awareness about the effects of numerical stability for floating point computations and describes ways to influence it with the Intel® C++ & Fortran Compiler. It also includes guidelines how to achieve numerical reproducibility for multiple (heterogeneous) systems for the different
programming models supported by Intel® Composer XE.

10:00-10:45

Intel® Cilk™ Plus
Within this session, the task and data level parallelism features of Intel® Cilk™ Plus are explained. Task level parallelism can be realized with minimal changes to existing code, suitable for recursive algorithms and problems. Data level parallelism of Intel® Cilk™ Plus addresses the inherent gap of expressing vector operations in C/C++, required to achieve better vectorization.

10:45-11:00

Break

11:00-12:15

Intel® MPI and Intel® Trace Analyzer and Collector incl. Demo
This module gives an introduction to Intel® MPI and presents ways of MPI analysis with Intel® Trace Analyzer and Collector. Features for both will be learned while presenting some methodologies that apply on many codes.

12:15-13:15

Lunch Break

13:15-14:30

Intel Error Analysis Tools
Intel® Inspector XE is an easy to use memory error checker and thread checker for serial and parallel applications. The tool allows you to enhance productivity, cut cost and speed time-to-market by finding problems in implementations early. In this module you will find the Inspector XE workflow, learn how to use memory and threading analyses, how to manage results and work with source code. Team collaboration capabilities and some advanced features are also covered. We also provide an introduction to debugger support for Linux* and Windows* as part of Intel® Parallel Studio XE and Intel® Cluster Studio XE.

14:30-14:45

Break

14:45-16:00

Intel® Xeon Phi™ Architecture and Programming
We finally provide an introduction to the architecture of Intel® Xeon Phi™ coprocessor and how to program for it. It rather addresses general principles than providing an in depth programming guide. The audience is provided with information to consider for current SW design even if the coprocessor is not available yet.

16:00-16:30

Q & A

Accommodation

Here some suggestions for hotels:

RELEXA Waldhotel Schatten (15 min walking distance)
http://www.relexa-hotel-stuttgart.de/en/hotel

Commundo Tagungshotel (5 min bus ride, however heavily booked)
http://www.commundo-tagungshotels.de/stuttgart/stuttgart.html

ARCONA MO.HOTEL (15 min bus ride)
http://stuttgart.arcona.de

Hotel Römerhof (convenient by car, 5 min)
http://www.roemerhof-vaihingen.de/index.php/en

Pullmann Stuttgart Fontana Hotel (20 min bus ride, high budget)
http://www.pullmanhotels.com/gb/hotel-5425-pullman-stuttgart-fontana/index.shtml

Akzent Hotel Möhringer Hof (convenient by car, 20 min)
http://www.hotel-moehringerhof.de/en/hotel/rooms-in-hotel

Hotels in Stuttgart
http://www.stuttgart-tourist.de/en/hotels-stuttgart

Go to Editor View