K. Danckaert et al., Strategy for power efficient combined task and data parallelism exploration illustrated on a QSDPCM video codec, J SYST ARCH, 45(10), 1999, pp. 791-808
Application studies indicate that between 50% and 80% of the power cost in
image and video processing systems is due to data storage and transfers. Th
is is especially true for multi-processor realizations, because conventiona
l parallelization strategies ignore this cost and focus only on the perform
ance, whereas the power consumption also depends heavily on the way a syste
m is parallelized. We will demonstrate the impact of processor partitioning
on the memory requirements by exploring a QSDPCM video codec realization.
Furthermore, we show that a strategy for combined task and data parallelism
exploration leads to a significant power reduction. (C) 1999 Elsevier Scie
nce B.V. All rights reserved.