 
Summary: Filter Decomposition for Supporting CoarseGrained
Pipelined Parallelism
Wei Du Gagan Agrawal
Department of Computer Science and Engineering, Ohio State University, Columbus OH 43210
duw@cse.ohiostate.edu, agrawal@cse.ohiostate.edu
ABSTRACT
We consider the filter decomposition problem in supporting coarsegrained
pipelined parallelism. This form of parallelism is suitable for datadriven
applications in scenarios where the data is available on a repository or a data
collection site on the internet, and the final results are required on a user's
desktop. A filter decomposition algorithm takes an application divided into
a sequence of atomic filters, and maps them into a given number of filters.
We propose three polynomial time algorithms for this problem. Dynamic
programming algorithm MIN ONETRIP optimizes the one trip cost for a
packet passing through the pipeline. MIN BOTTLENECK is also a dy
namic programming algorithm, which minimizes the time spent on the bot
tleneck stage. Finally, MIN TOTAL is an approximate greedy algorithm
which tries to minimize the total execution time.
The results show that our heuristic algorithms work quite well in prac
tice, with the possible exception of MIN ONETRIP when the number of
