Foreword
Wes Bethel, Hank Childs, and Chuck Hansen have developed an eminently
readable and comprehensive book. It provides the very first in-depth intro-
duction to the interaction of two highly important and relevant topics in com-
putational science: high performance computing and scientific visualization.
The book provides a broad background on both topics, but more importantly,
for the first time in book form, they describe some of the most recent develop-
ments in scientific visualization as we move from the Petascale era to Exaflops
computing.
It has been exactly a quarter century since the 1987 publication of the
ground breaking report by McCormick, DeFanti, and Brown that defined the
field of scientific visualization. That report set in motion the development of
a field that has, by now, become an integral part of computational science. As
a community, we have come to accept the notion that scientific visualization
is the tool to “see the unseen” in the vast amount of data being produced by
numerical simulations. From understanding the behavior of subatomic par-
ticles in QCD to watching the explosion of supernovae or the evolution of
galaxies, we can now “see” these phenomena, as if they are truly happen-
ing in front of our eyes. The scientific visualization community has worked
diligently on refining algorithms, exploring new display technologies, thinking
about the challenge of distributed visualization, and developing large software
frameworks, and by now has become a fairly mature scientific activity.
In the same time frame, high performance computing has seen even more
dramatic developments. In 1987 we were still thinking of Cray vector comput-
ers and frame buffers when it came to HPC and visualization. In the 1990s
computing technology made a dramatic transition to MPPs using commodity
hardware and the MPI programming model, while increasing performance by
a factor of one million from the Gigaflops to the Petaflops level in 2012. Today,
were are close to yet another transformation of the HPC field as GPUs and
accelerators become integrated, while the amount of parallelism seems to be
ever increasing.
In the context of this potential rapid transformation of the high perfor-
mance computing field, the book by Bethel, Childs and Hansen arrives exactly
at the right time. It succeeds perfectly and solidly combines the two almost
parallel threads of development in scientific visualization and high perfor-
mance computing all into one single volume for the first time. It will provide
a solid foundation for anyone who considers using the most recent tools for
v
vi High Performance Visualization
visualization in order to understand complex simulation data or to under-
stand the ever increasing amount of experimental data. I highly recommend
this timely book for scientists and engineers. It closes an important gap in the
available literature on computational science and it is a great addition to the
CRC Press series on Computational Science. It provides a solid reference as
the community embarks on the Exascale adventure.
Horst Simon
Lawrence Berkeley National Laboratory and University of California, Berkeley
May 2012
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.