Claudio Sansoe'

Claudio Sansoe'

Auto-generated profile, based on publicly available information

Claudio Sansoe'

Politecnico di Torino, Turin, Italy

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 March 2025 in ACM Transactions on Reconfigurable Technology and Systems
Verified
Journal Article
Open access
GBGiovanni Brignone
Giovanni Brignone
RBRoberto Bosio
Roberto Bosio
FOFabrizio Ottati
Fabrizio Ottati
CSClaudio Sansoè
Claudio Sansoè
Luciano LavagnoLuciano Lavagno
Luciano Lavagno
High-level synthesis (HLS) aims at democratizing custom hardware acceleration with highly abstracted software-like descriptions. However, efficient accelerators still require substantial low-level hardware optimizations, defeating the HLS intent. In the context of field-programmable gate arrays, digital signal processors (DSPs) are a crucial resource that typically requires a significant optimization effort for its efficient utilization, especially when used for sub-word vectorization. This work proposes SILVIA, an open-source LLVM transformation pass that automatically identifies superword-level parallelism within an HLS design and exploits it by packing multiple operations, such as additions, multiplications, and multiply-and-adds, into a single DSP. SILVIA is integrated in the flow of the commercial AMD Vitis HLS tool and proves its effectiveness by packing multiple operations on the DSPs without any manual source-code modifications on several diverse state-of-the-art HLS designs such as convolutional neural networks and basic linear algebra subprograms accelerators, reducing the DSP utilization for additions by 70% and for multiplications and multiply-and-adds by 50% on average.

1 October 2012
Verified
Conference Paper
Closed access
HAHaider Ali
Haider Ali
AAAntonio Aru
Antonio Aru
CSClaudio Sansoe'
Claudio Sansoe'
AAAnwar Ali
Anwar Ali
MMMuhammad Rizwan Mughal
Muhammad Rizwan Mughal
Innovative Antenna Design has recently become as one of most vital subsystem of Satellite Communication. In small satellites however, this subsystem is often overlooked, either due to consideration of weight or available space. Using traditional design approach is not feasible and does not offer any significant benefits. With increasing availability of “Commercial Off the Shelf” (COTS) components in S and higher bands it is now possible to design Antenna and RF subsystem which comply with given requirements. Space is a vast unexplored territory and it is important not to lose track and control of a satellite. As payloads become more demanding in terms of bandwidth requirements it is desirable to have a high data rate communication link. This calls for use of more directive and narrower beamwidth antennas with sufficient bandwidth. On the contrary, for the purpose of tracking and identification it is preferred to have a less directive and wider beamwidth antennas. Therefore, such an antenna subsystem is required that can address solution for this problem. Such provision is made in the antenna design of “AraMis” (Italian acronym for Modular Architecture for Satellites) nanosatellites project which is a modular based architecture. The aim is to design a nonmission specific antenna which provides dynamic reconfigurable solution, making it flexible from application stand point. Thus, allowing the reuse of same design architecture for even future missions needs.