Algorithms and tools for automatic generation of DSP hardware structures
Pedro Tomás,
Inesc-ID –
Abstract:
The increased complexity of Digital Signal Processing (DSP) algorithms demands for the development of more complex and more efficient hardware structures. The work presented describes the core components for the development of a tool capable of automatic generation of efficient hardware structures, therefore facilitating developers work. It comprises algorithms and techniques for i) balancing the paths in a graph, ii) scheduling of operations to functional units, iii) allocating registers and iv) generating the VHDL code. Results show that the developed techniques are capable of generating the hardware structure of typical DSP algorithms represented in data-flow graphs with over 2,000 nodes in around 200 ms, scaling to 80,000 nodes in about 214 s. Within the developed techniques, solving the scheduling problem is one of the most complex tasks: it is a NP-complete problem and directly influences the number of functional units and registers required. Therefore, experimental analysis was made on scheduling algorithms for time-constrained problems. Results show that simple list-based algorithms are more efficient in large problems than more complex algorithms: they run faster and tend to require less functional units.
This talk is a preparation for the defense of the master thesis entitled: “Algorithms and tools for automatic generation of DSP hardware structures”.
Date: 2006-Jan-10 Time: 14:00:00 Room: 336
For more information:
Upcoming Events
INESC Brussels HUB Winter Meeting 2023

This edition of the HUB Winter Meeting will be co-organised with Science Business and will take place on the 30 and 31 January, in Lisbon, at Instituto Superior Técnico, Department of Computer Science and Engineering.
Please see below a summary of the agenda, this will be updated on the INESC Brussels HUB website regularly (confirmed speakers and other relevant info). Places for onsite participation are limited so registration is mandatory. Online participants will be sent a ZOOM link for each specific session on the 27th January.
INESC Brussels HUB website: https://hub.inesc.pt/
Monday, 30 January
a) Digital Europe Programme & Chips Act: state of play and possibilities for INESC.
9h to 10h30 GMT
(Exclusive for INESC researchers and administrators).
b) Science Business: how can INESC tap into Science Business network, activities and communications tools.
(Exclusive for INESC researchers and administrators).
c) Networking Lunch (for all onsite participants).
d) Roundtable: From rhetoric to reality – Embedding international strategy in the DNA of research organisations.
(Closed-door, roundtable workshop, Chatham House rules, open to INESC researchers and administrators, external participants by invitation only).
e) Networking Dinner
(By invitation only – INESC researchers participating onsite in the event are elegible to join).
Tuesday, 31 January
f) Workshop: How they did it? Strategic positioning for structural success in Horizon Europe: a discussion of best practices.
(Exclusive for INESC researchers, administrators and international invited speakers).
g) The public consultation on European R&I Programmes: Towards FP10.
(Closed-door, roundtable workshop, Chatham House rules, open to INESC researchers and administrators, external participants by invitation only).
h) Networking Lunch (for all onsite participants).
i) Management Committee meeting (Directors and POB members)
The HUB Winter Meeting aims at bringing together researchers and administrators from the 5 INESC institutes, affiliated higher education institutions in Portugal and abroad, with key European and global players, to:
– Discuss key research and innovation issues at EU level.
– Inform institutional policy and strategy.
– Exchange best-practices about R&I management, career development and policy positioning.
– Promote, discuss and deliver vision, visibility, networking and impactful communication.
– Create, identify and deepen partnerships and collaboration opportunities for collaborative R&I.