Stefania Perri

Prof. Dr. Stefania Perri

Department of Mechanical, Energy and Management Engineering, University of Calabria, 87036 Rende, Italy
+1
orcid

Research Focus & Metrics

Academic Career Length

29Years (1998-Present)

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

Representative Publications

View All Publications
13 June 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
CSCristina Silvano
Cristina Silvano
DIDaniele Ielmini
Daniele Ielmini
FFFabrizio Ferrandi
Fabrizio Ferrandi
LFLeandro Fiorin
Leandro Fiorin
SCSerena Curzel
Serena Curzel
SPStefania Perri
Stefania Perri
Recent trends in deep learning (DL) have made hardware accelerators essential for various high-performance computing (HPC) applications, including image classification, computer vision, and speech recognition. This survey summarizes and classifies the most recent developments in DL accelerators, focusing on their role in meeting the performance demands of HPC applications. We explore cutting-edge approaches to DL acceleration, covering not only GPU- and TPU-based platforms but also specialized hardware such as FPGA- and ASIC-based accelerators, Neural Processing Units, open hardware RISC-V-based accelerators, and co-processors. This survey also describes accelerators leveraging emerging memory technologies and computing paradigms, including 3D-stacked Processor-In-Memory, non-volatile memories like Resistive RAM and Phase Change Memories used for in-memory computing, as well as Neuromorphic Processing Units, and Multi-Chip Module-based accelerators. Furthermore, we provide insights into emerging quantum-based accelerators and photonics. Finally, this survey categorizes the most influential architectures and technologies from recent years, offering readers a comprehensive perspective on the rapidly evolving field of deep learning acceleration.

24 December 2012 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
MLMarco Lanuzza
Marco Lanuzza
Pasquale CorsonelloPasquale Corsonello
Pasquale Corsonello
SPStefania Perri
Stefania Perri
In this brief, a new low-power level shifter (LS) is presented for robust logic voltage shifting from near/sub-threshold to above-threshold domain. The new circuit combines the multi-threshold CMOS technique along with novel topological modifications to guarantee a wide voltage conversion range with limited static power and total energy consumption. When implemented in a 90-nm technology process, the proposed design reliably converts 180-mV input signals into 1-V output signals, while maintaining operational frequencies above 1-MHz, also taking into account process-voltage-temperature variations.Post-layout simulation results demonstrate that the new LS reaches a propagation delay less than 22 ns, a static power dissipation of only 6.4 nW, and a total energy per transition of only 74 fJ for a 0.2-V 1-MHz input pulse.

11 March 2014 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
MLMarco Lanuzza
Marco Lanuzza
Pasquale CorsonelloPasquale Corsonello
Pasquale Corsonello
SPStefania Perri
Stefania Perri
Multisupply voltage design technique is widely used in modern system-on-chips to tradeoff energy and speed. Level shifters (LSs) allow different voltage domains to be interfaced. In this brief, a new LS is presented for fast and wide range voltage conversion. Because of a novel architecture combined with the use of multithreshold CMOS technique, the proposed circuit guarantees robust voltage shifting from the deep subthreshold to the above-threshold domain while exhibiting fast response and low energy consumption. When implemented in a 90-nm technology node, considering process-voltage-temperature variations, the proposed design reliably converts 100-mV input signals into 1 V output signals. Post-layout simulation results demonstrate that the new LS shows a propagation delay of 16.6 ns, a static power dissipation of 8.7 nW and a total energy per transition of only 77 fJ for a 0.2 V 1-MHz input pulse.

14 June 2013 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
SPStefania Perri
Stefania Perri
Pasquale CorsonelloPasquale Corsonello
Pasquale Corsonello
GCGiuseppe Cocorullo
Giuseppe Cocorullo
As transistors decrease in size more and more of them can be accommodated in a single die, thus increasing chip computational capabilities. However, transistors cannot get much smaller than their current size. The quantum-dot cellular automata (QCA) approach represents one of the possible solutions in overcoming this physical limit, even though the design of logic modules in QCA is not always straightforward. In this brief, we propose a new adder that outperforms all state-of-the-art competitors and achieves the best area-delay tradeoff. The above advantages are obtained by using an overall area similar to the cheaper designs known in literature. The 64-bit version of the novel adder spans over 18.72 μ 2 of active area and shows a delay of only nine clock cycles, that is just 36 clock phases.

3 October 2022 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Open access
FFFabio Frustaci
Fabio Frustaci
FSFanny Spagnolo
Fanny Spagnolo
SPStefania Perri
Stefania Perri
Pasquale CorsonelloPasquale Corsonello
Pasquale Corsonello
True random number generators (TRNGs) are fundamentals in many important security applications. Though they exploit randomness sources that are typical of the analog domain, digital-based solutions are strongly required especially when they have to be implemented on Field Programmable Gate Array (FPGA)-based digital systems. This paper describes a novel methodology to easily design a TRNG on FPGA devices. It exploits the runtime capability of the Digital Clock Manager (DCM) hardware primitives to tune the phase shift between two clock signals. The presented auto-tuning strategy automatically sets the phase difference of two clock signals in order to force on one or more flip-flops (FFs) to enter the metastability region, used as a randomness source. Moreover, a novel use of the fast carry-chain hardware primitive is proposed to further increase the randomness of the generated bits. Finally, an effective on-chip post-processing scheme that does not reduce the TRNG throughput is described. The proposed TRNG architecture has been implemented on the Xilinx Zynq XC7Z020 System on Chip (SoC). It passed all the National Institute of Standards and Technology (NIST) SP 800-22 statistical tests with a maximum throughput of 300×106 bit per second. The latter is considerably higher than the throughput of other previously published DCMbased TRNGs.

1 November 2012 in IEEE Transactions on Nanotechnology
Verified
Journal Article
Closed access
SPS. Perri
S. Perri
Pasquale CorsonelloPasquale Corsonello
Pasquale Corsonello
The quantum-dot cellular automata (QCA) approach is an attractive emerging technology suitable for the development of ultradense low-power high-performance digital circuits. Even though several solutions have been proposed recently for binary addition circuits, the design of efficient adders in QCA still poses several challenges since, most often, designers tend to implement strategies and methodologies close to those consolidated for the CMOS logic design. In this paper, we propose a new design method that exploits in original ways the properties of auxiliary propagate and generates signals to reduce the number of majority gates required to implement adders in QCA and/or the addition time. Three new formulations of basic logic equations frequently used in the designs of fast binary adders are proposed. To evaluate the potential advantage of the new strategy, two examples of application of the aforementioned method are discussed in this paper.