Marco Rios

Marco Rios

Auto-generated profile, based on publicly available information

Marco Rios

École Polytechnique Fédérale de Lausanne (EPFL), Embedded Systems Laboratory, Switzerland

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
10 February 2020 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
WSWilliam Andrew Simon
William Andrew Simon
YQYasir Mahmood Qureshi
Yasir Mahmood Qureshi
MRMarco Rios
Marco Rios
ALAlexandre Levisse
Alexandre Levisse
MZMarina Zapater
Marina Zapater
David AtienzaDavid Atienza
David Atienza
Area and power constrained edge devices are increasingly utilized to perform compute intensive workloads, necessitating increasingly area and power efficient accelerators. In this context, in-SRAM computing performs hundreds of parallel operations on spatially local data common in many emerging workloads, while reducing power consumption due to data movement. However, in-SRAM computing faces many challenges, including integration into the existing architecture, arithmetic operation support, data corruption at high operating frequencies, inability to run at low voltages, and low area density. To meet these challenges, this work introduces BLADE, a BitLine Accelerator for Devices on the Edge. BLADE is an in-SRAM computing architecture that utilizes local wordline groups to perform computations at a frequency 2.8× higher than state-of-the-art in-SRAM computing architectures. BLADE is integrated into the cache hierarchy of low-voltage edge devices, and simulated and benchmarked at the transistor, architecture, and software abstraction levels. Experimental results demonstrate performance/energy gains over an equivalent NEON accelerated processor for a variety of edge device workloads, namely, cryptography (4× performance gain/6× energy reduction), video encoding (6×/2×), and convolutional neural networks (3×/1.5×), while maintaining the highest frequency/energy ratio (up to 2.2Ghz@1V) of any conventional in-SRAM computing architecture, and a low area overhead of less than 8%.

1 August 2022 in IEEE Micro
Verified
Journal Article
Open access
FPFlavio Ponzina
Flavio Ponzina
SMSimone Machetti
Simone Machetti
MRMarco Rios
Marco Rios
BDBenoit Walter Denkinger
Benoit Walter Denkinger
ALAlexandre Levisse
Alexandre Levisse
David AtienzaDavid Atienza
David Atienza
The growing popularity of edgeAI requires novel solutions to support the deployment of compute-intense algorithms in embedded devices. In this article, we advocate for a holistic approach, where application-level transformations are jointly conceived with dedicated hardware platforms. We embody such a stance in a strategy that employs ensemble-based algorithmic transformations to increase robustness and accuracy in Convolutional Neural Networks (CNNs), enabling the aggressive quantization of weights and activations. Opportunities offered by algorithmic optimizations are then harnessed in domain-specific hardware solutions, such as the use of multiple ultra-low-power processing cores, the provision of shared acceleration resources, the presence of independently power-managed memory banks, and voltage scaling to ultra-low levels, greatly reducing (up to 60% in our experiments) energy requirements. Furthermore, we show that aggressive quantization schemes can be leveraged to perform efficient computations directly in memory banks, adopting in-memory computing solutions. We showcase that the combination of parallel in-memory execution and aggressive quantization leads to more than 70% energy and latency gains compared to baseline implementations.

23 January 2023 in IEEE Transactions on Emerging Topics in Computing
Verified
Journal Article
Closed access
MRMarco Rios
Marco Rios
FPFlavio Ponzina
Flavio Ponzina
ALAlexandre Levisse
Alexandre Levisse
GAGiovanni Ansaloni
Giovanni Ansaloni
David AtienzaDavid Atienza
David Atienza
By supporting the access of multiple memory words at the same time, Bit-line Computing (BC) architectures allow the parallel execution of bit-wise operations in-memory. At the array periphery, arithmetic operations are then derived with little additional overhead. Such a paradigm opens novel opportunities for Artificial Intelligence (AI) at the edge, thanks to the massive parallelism inherent in memory arrays and the extreme energy efficiency of computing in-situ, hence avoiding data transfers. Previous works have shown that BC brings disruptive efficiency gains when targeting AI workloads, a key metric in the context of emerging edge AI scenarios. This manuscript builds on these findings by proposing an end-to-end framework that leverages BC-specific optimizations to enable high parallelism and aggressive compression of AI models. Our approach is supported by a novel hardware module performing real-time decoding, as well as new algorithms to enable BC-friendly model compression. Our hardware/software approach results in a 91% energy savings (for a 1% accuracy degradation constraint) regarding state-of-the-art BC computing approaches.

9 September 2023 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
FPFlavio Ponzina
Flavio Ponzina
MRMarco Rios
Marco Rios
ALAlexandre Levisse
Alexandre Levisse
GAGiovanni Ansaloni
Giovanni Ansaloni
David AtienzaDavid Atienza
David Atienza
Compute memories are memory arrays augmented with dedicated logic to support arithmetic. They support the efficient execution of data-centric computing patterns, such as those characterizing Artificial Intelligence (AI) algorithms. These architectures can provide computing capabilities as part of the memory array structures (In-Memory Computing, IMC) or at their immediate periphery (Near-Memory Computing, NMC). By bringing the processing elements inside (or very close to) storage, compute memories minimize the cost of data access. Moreover, highly parallel (and, hence, high-performance) computations are enabled by exploiting the regular structure of memory arrays. However, the regular layout of memory elements also constrains the data range of inputs and outputs, since the bitwidths of operands and results stored at each address cannot be freely varied. Addressing this challenge, we herein propose a HW/SW co-design methodology combining careful per-layer quantization and inter-layer scaling with lightweight hardware support for overflow-free computation of dot-vector operations. We demonstrate their use to implement the convolutional and fully connected layers of AI models. We embody our strategy in two implementations, based on IMC and NMC, respectively. Experimental results highlight that an area overhead of only 10.5% (for IMC) and 12.9% (for NMC) is required when interfacing with a 2KB subarray. Furthermore, inferences on benchmark CNNs show negligible accuracy degradation due to quantization for equivalent floating-point implementations.

1 April 2019
Verified
Conference Paper
Open access
DBD. Bosch
D. Bosch
FAF. Andrieu
F. Andrieu
LCL. Ciampolini
L. Ciampolini
AMA. Makosiej
A. Makosiej
OWO. Weber
O. Weber
MVMaud Vinet
Maud Vinet
For the first time, we propose a 3D-monolithic SRAM architecture with a local back-plane for top-tier transistors enabling local back-bias assist techniques without area penalty as well as the capability to route two additional row-wise signals on individual back-planes. Experimental data are extracted from a 14nm planar Fully-Depleted-Silicon-on-Insulator (FDSOI) $0.078\mu \mathrm{m}^{2}$ SRAM in order to properly model 3D top-tier cells. Simulations show this technique yields a 7% bitline capacitance reduction, a 12%/16% read/write access time improvement at $V_{DD}=0.8\mathrm{V}$ and a reduction of minimum operating voltage $V_{min}$ by 60mV at $6\sigma$ w.r.t. planar SRAMs.