@InProceedings{uk:protein-folding,
  author = {B. Uk and M. Taufer and T. Stricker and G. Settanni and A. Cavalli
  and A. Caflisch},
  title = {Combining Task- and Data Parallelism to Speed up Protein Folding on
  a Desktop Grid Platform},
  booktitle = {Proceedings of the Third IEEE/ACM International Symposium on
  Cluster Computing and the Grid},
  year = {2003},
  month = {May},
  pages = {240--249},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo, Japan},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190240abs.htm},
  keywords = {protein folding, grid application, parallel I/O, pario-app,
  pario-bib},
  abstract = {The steady increase of computing power at lower and lower cost
  enables molecular dynamics simulations to investigate the process of protein
  folding with an explicit treatment of water molecules. Such simulations are
  typically done with well known computational chemistry codes like CHARMM.
  Desktop grids such as the United Devices MetaProcessor are highly attractive
  platforms, since scavenging for unused machines on Intra- and Internet
  delivers compute power that is almost free. However, the predominant
  programming paradigm for current desktop grids is pure task parallelism and
  might not fit the needs for protein folding simulations with explicit water
  molecules. A short overall turn-around time of a simulation remains highly
  important for research productivity, but the need for an accurate model and
  long simulation time-scales leads to tasks that are too large for optimal
  scheduling on a desktop grid. To address this problem, we introduce a
  combination of task- and data parallelism as a well suitable computing
  paradigm for protein folding investigations on grid platforms. As a proof of
  concept, we design and implement a simple system for protein folding
  simulations based on the notion of combined task and data parallelism with
  clustered workers. Clustered workers are machines grouped into small clusters
  according to network and CPU performance criteria and act as super-nodes
  within a desktop grid, permitting the utilization of data parallelism in
  addition to the task parallelism. We integrate our new paradigm into the
  existing software environment of the United Devices MetaProcessor. For a test
  protein, we reach a better quality of the folding calculations than we
  reached using just task parallelism on distributed systems.}
}