@techreport{fastflow_acc:tr-10-03,
  number = {TR-10-03},
  month = feb,
  author = {Marco Aldinucci and Marco Danelutto and Peter Kilpatrick and
            Massimiliano Meneghin and Massimo Torquati},
  keywords = {fastflow},
  abstract = {Shared memory multiprocessors come back to popularity thanks to
              rapid spreading of commodity multi-core architectures. As ever,
              shared memory programs are fairly easy to write and quite hard to
              optimise; providing multi-core programmers with optimising tools
              and programming frameworks is a nowadays challenge. Few efforts
              have been done to support effective streaming applications on
              these architectures. In this paper we introduce FastFlow, a
              low-level programming framework based on lock-free queues
              explicitly designed to support high-level languages for streaming
              applications. We compare FastFlow with state-of-the-art
              programming frameworks such as Cilk, OpenMP, and Intel TBB. We
              experimentally demonstrate that FastFlow is always more efficient
              than all of them in a set of micro-benchmarks and on a real world
              application; the speedup edge of FastFlow over other solutions
              might be bold for fine grain tasks, as an example +35% on OpenMP,
              +226% on Cilk, +96% on TBB for the alignment of protein P01111
              against UniProt DB using Smith-Waterman algorithm.},
  title = {Accelerating sequential programs using {FastFlow} and
           self-offloading},
  institution = {Universit{\`a} di Pisa, Dipartimento di Informatica, Italy},
  year = {2010},
}

This document was generated by bib2html 3.3.
(Modified by Luca Paolini, under the GNU General Public License)