Reconciling Customization and Flexibility Through Compound Circuits

woe, 2008-09-03 14:30 - 15:30

The seminar will take place in the Jozef Plateauzaal at the Faculty of
Engineering at Ghent University. It is located in the Jozef Plateaustraat;
follow this link for an itinerary:


While parallelism and multi-cores are receiving much attention as a
major scalability path, customization is another, orthogonal and
complementary, scalability path which can target not easily
parallelizable programs or program sections. The key assets of
customization are cost and power efficiency. The key limitation
of customization is flexibility. In this study,
we present a method for achieving any desired balance between
flexibility and efficiency by automatically combining any set of
individual customization circuits into a larger compound
circuit. This circuit is significantly more cost efficient than the
simple union of all target circuits, and is configurable to behave as
any of the target circuits, while avoiding the routing and
configuration cost overhead of FPGAs. The more individual circuits are
included, the larger the number of applications which can potentially
benefit from this compound customization circuit, realizing
flexibility at a minimal cost. Moreover, we observe that the compound
circuit cost does not increase in proportion to the number of target
applications, due to the wide range of common data-flow and
control-flow patterns in programs. Currently, the target individual
circuits correspond to loops, like most accelerators in embedded
systems, but the aggregation method can accomodate circuits of any

Speaker's Bio:

Olivier Temam has obtained a PhD in Computer Science from University
of Rennes in 1993. He has been Assistant Professor at University of
Versailles from 1994 until 1999, and then Professor at University of
Paris Sud until 2004. He is now a senior research fellow at INRIA
Saclay in Paris (French research institute on computer science), where
he heads the Alchemy group, and Professor at Ecole Polytechnique. His
research interests include processor architecture and simulation,
program optimization, emerging technologies and paradigms, especially
bio-inspired computing.