@MastersThesis{hubovskykunz:msthesis, author = {Rainer Hubovsky and Florian Kunz}, title = {Dealing with Massive Data: from Parallel I/O to Grid I/O}, year = {2004}, month = {January}, school = {Vienna University of Technology}, address = {Vienna, Austria}, URL = {http://www.cs.dartmouth.edu/pario/hubovsky_dictionary.pdf}, keywords = {parallel i/o, cluster i/o, grid i/o, distributed computing, pario-bib}, abstract = {Increasing requirements in HPC led to improvements of CPU power, but bandwidth of I/O subsystems does not keep up with the performance of processors any more. This problem is commonly known as the I/O bottleneck. Additionally, new and stimulating data-intensive problems in biology, physics, astronomy, space exploration, and human genom research arise, which bring new high-performance applications dealing with massive data spread over globally distributed storage resources. Therefore research in HPC focuses more on I/O systems: all leading hardware vendors of multiprocessor systems provided powerful concurrent I/O subsystems. In accordance researchers focus on the design of appropriate programming tools and models to take advantage of the available hardware resources. Numerous projects about this topic have appeared, from which a large and unmanageable quantity of publications have come. These publications concern themselves to a large extent with very special problems. Due to the time of their appearance the few overview papers deal with Parallel I/O or Cluster I/O. Substantial progress has been made in these research areas since then. Grid Computing has emerged as an important new field, distinguished from conventional Distributed Computing by its focus on large-scale resource sharing, innovative applications and, in some cases, high-performance orientation. Over the past five years, research and development efforts within the Grid community have produced protocols, services and tools that address precisely the challenges that arise when we try to build Grids, I/O being an important part of it. Therefore our work gives an overview of I/O in HPC.}, comment = {Like stockinger:dictionary, this master's thesis categorizes and describes a large set of parallel I/O-related projects and applications.} }