"Fossies" - the Fresh Open Source Software Archive  

Source code changes of the file "doc/doxygen-user/manual/introduction.dox" between
scalasca-2.3.tar.gz and scalasca-2.3.1.tar.gz

About: SCALASCA v2 (Scalable Performance Analysis of Large-Scale Applications) is an toolset to analyze the performance behavior of parallel applications and to identify opportunities for optimization. Note: Requires the instrumentation and measurement infrastructure Score-P and the CUBE4 GUI.

introduction.dox  (scalasca-2.3):introduction.dox  (scalasca-2.3.1)
/**************************************************************************** /****************************************************************************
** SCALASCA http://www.scalasca.org/ ** ** SCALASCA http://www.scalasca.org/ **
***************************************************************************** *****************************************************************************
** Copyright (c) 1998-2014 ** ** Copyright (c) 1998-2016 **
** Forschungszentrum Juelich GmbH, Juelich Supercomputing Centre ** ** Forschungszentrum Juelich GmbH, Juelich Supercomputing Centre **
** ** ** **
** Copyright (c) 2009-2013 ** ** Copyright (c) 2009-2013 **
** German Research School for Simulation Sciences GmbH, ** ** German Research School for Simulation Sciences GmbH, **
** Laboratory for Parallel Programming ** ** Laboratory for Parallel Programming **
** ** ** **
** This software may be modified and distributed under the terms of ** ** This software may be modified and distributed under the terms of **
** a BSD-style license. See the COPYING file in the package base ** ** a BSD-style license. See the COPYING file in the package base **
** directory for details. ** ** directory for details. **
****************************************************************************/ ****************************************************************************/
skipping to change at line 29 skipping to change at line 29
Supercomputing is a key technology of modern science and engineering, Supercomputing is a key technology of modern science and engineering,
indispensable to solve critical problems of high complexity. However, since indispensable to solve critical problems of high complexity. However, since
the number of cores on modern supercomputers is increasing from generation to the number of cores on modern supercomputers is increasing from generation to
generation, HPC applications are required to harness much higher degrees of generation, HPC applications are required to harness much higher degrees of
parallelism to satisfy their growing demand for computing power. Therefore -- parallelism to satisfy their growing demand for computing power. Therefore --
as a prerequisite for the productive use of today's large-scale computing as a prerequisite for the productive use of today's large-scale computing
systems -- the HPC community needs powerful and robust performance analysis systems -- the HPC community needs powerful and robust performance analysis
tools that make the optimization of parallel applications both more effective tools that make the optimization of parallel applications both more effective
and more efficient. and more efficient.
Jointly developed at the Jülich Supercomputing Centre and the German The Scalasca Trace Tools developed at the Jülich Supercomputing Centre
Research School for Simulation Sciences (Aachen), the Scalasca Tracing Tools
are a collection of trace-based performance analysis tools that have been are a collection of trace-based performance analysis tools that have been
specifically designed for use on large-scale systems such as IBM Blue Gene or specifically designed for use on large-scale systems such as the IBM Blue
Cray XT and successors, but also suitable for smaller HPC platforms. While Gene series or Cray XT and successors, but also suitable for smaller HPC
the current focus is on applications using MPI @cite mpi_ref, OpenMP platforms. While the current focus is on applications using MPI @cite mpi_ref,
@cite openmp_ref or hybrid MPI+OpenMP, support for other parallel programming OpenMP @cite openmp_ref, POSIX threads, or hybrid MPI+OpenMP/Pthreads
paradigms may be added in the future. A distinctive feature of the Scalasca parallelization, support for other parallel programming paradigms may be
Tracing Tools is its scalable automatic trace-analysis component which added in the future. A distinctive feature of the Scalasca Trace Tools is
provides the ability to identify wait states that occur, for example, as a its scalable automatic trace-analysis component which provides the ability
result of unevenly distributed workloads @cite geimer_ea:2009. Especially to identify wait states that occur, for example, as a result of unevenly
when trying to scale communication intensive applications to large process distributed workloads @cite geimer_ea:2009. Especially when trying to scale
counts, such wait states can present severe challenges to achieving good communication intensive applications to large process counts, such wait
performance. In addition, the trace analyzer is able to identify the states can present severe challenges to achieving good performance. Besides
activities on the critical path of the target application merely identifying wait states, the trace analyzer is also able to pinpoint
@cite boehme_ea:2012, highlighting those routines which determine the length their root causes (i.e., delays) @cite boehme_ea:2010, and to identify the
of the program execution and therefore constitute the best candidates for activities on the critical path of the target application @cite boehme_ea:2012,
optimization. highlighting those routines which determine the length of the program
execution and therefore constitute the best candidates for optimization.
In contrast to previous versions of the Scalasca toolset -- which used a In contrast to previous versions of the Scalasca toolset -- which used a
custom measurement system and trace data format -- the Scalasca Tracing Tools custom measurement system and trace data format -- the Scalasca Trace Tools
2.x release series is based on the community-driven instrumentation and 2.x release series is based on the community-driven instrumentation and
measurement infrastructure Score-P @cite knuepfer_ea:2012. The Score-P measurement infrastructure Score-P @cite knuepfer_ea:2012. The Score-P
software is jointly developed by a consortium of partners from Germany and software is jointly developed by a consortium of partners from Germany and
the US, and supports a number of complementary performance analysis tools the US, and supports a number of complementary performance analysis tools
through the use of the common data formats CUBE4 for profiles and the Open through the use of the common data formats CUBE4 for profiles and the Open
Trace Format 2 (OTF2) @cite eschweiler_ea:2012 for event trace data. This Trace Format 2 (OTF2) @cite eschweiler_ea:2012 for event trace data. This
significantly improves interoperability between Scalasca and other significantly improves interoperability between Scalasca and other
performance analysis tool suites such as Vampir @cite knuepfer_ea:2008 and performance analysis tool suites such as Vampir @cite knuepfer_ea:2008 and
TAU @cite shende_ea:2006. Nevertheless, backward compatibility to Scalasca TAU @cite shende_ea:2006. Nevertheless, backward compatibility to Scalasca
1.x is maintained where possible, for example, the Scalasca trace analyzer is 1.x is maintained where possible, for example, the Scalasca trace analyzer is
 End of changes. 4 change blocks. 
19 lines changed or deleted 19 lines changed or added

Home  |  About  |  All  |  Newest  |  Fossies Dox  |  Screenshots  |  Comments  |  Imprint  |  Privacy  |  HTTPS