id: 06104393
dt: a
an: 06104393
au: Tudruj, Marek; Maśko, Łukasz
ti: Scheduling parallel programs based on architecture-supported regions.
so: Wyrzykowski, Roman (ed.) et al., Parallel processing and applied
    mathematics. 9th international conference, PPAM 2011, Torun, Poland,
    September 11‒14, 2011. Revised selected papers, Part II. Berlin:
    Springer (ISBN 978-3-642-31499-5/pbk). Lecture Notes in Computer
    Science 7204, 51-60 (2012).
py: 2012
pu: Berlin: Springer
la: EN
cc: 
ut: 
ci: 
li: doi:10.1007/978-3-642-31500-8_6
ab: Summary: Modern multicore processor technology can fairly easily deliver
    special accelerator processors dedicated to fast optimised execution of
    critical computational functions. Multi CMP (Chip Multi-Processor)
    systems can be composed as a set of dedicated and general purpose
    computational modules interconnected by a global data exchange network.
    The paper proposes special program scheduling algorithms for such
    systems. Dedicated CMP modules assumed in the paper are based on a new
    data communication model called communication on the fly. It enables
    strong reduction of inter-process and inter-core communication
    overheads for intensively shared data.
rv: