Marc Riera
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Marc Riera has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Antonio González
Universitat Politecnica de Catalunya, Barcelona, Spain
7 shared publications - Jose-Maria Arnau
Polytechnic University of Catalonia, Barcelona, Spain
2 shared publications - Alberto Bosio
Cole Centrale de Lyon, cully, France
1 shared publication - Alessandro Savino
University of California
1 shared publication - Alessandro Vallero
Dipartimento di Automatica ed Informatica, Politecnico di Torino, Torino, Italy
1 shared publication Antonio González
1 shared publication
Latest Publications
- Open Access
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 37 (7) , 1614-1629
Toward Efficient LUT-Based PIM: A Scalable and Low-Power Approach for Modern Workloads
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 37 (7) , 1614-1629
Open AccessToward Efficient LUT-Based PIM: A Scalable and Low-Power Approach for Modern Workloads
- Open Access
- 12 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1042-1051
ReDy: A Novel ReRAM-centric Dynamic Quantization Approach for Energy-efficient CNNs
Deep Neural Networks (DNNs) have achieved enormous success for a large variety of applications. The primary operation in DNNs is the dot product of quantized input activations and weights. Prior works have proposed the design of memory-centric architectures based on the Processing-In-Memory (PIM) paradigm. Resistive RAM (ReRAM) technology is especially appealing for PIM-based DNN accelerators due to its high density to store weights, low leakage energy, low read latency, and high performance capabilities to perform the DNN dot-products massively in parallel within the ReRAM crossbars. However, the main bottleneck of these architectures is the energy-hungry analog-to-digital conversions (ADCs) required to perform analog computations in-ReRAM, which penalizes the efficiency and performance benefits of PIM. To improve energy-efficiency of in-ReRAM analog dot-product computations we present ReDy, a hardware accelerator that implements a novel ReRAM-centric Dynamic quantization scheme to take advantage of the bit serial streaming and processing of activations. The energy consumption of ReRAM-based DNN accelerators is directly proportional to the numerical precision of the input activations of each DNN layer. In particular, ReDy exploits the fact that activations of CONV layers of DNNs are commonly grouped according to the size of their filters and the size of the ReRAM crossbars. Then, ReDy quantizes on-the-fly each group of activations with a different precision based on a novel heuristic that takes into account the statistical distribution of each group. Overall, ReDy greatly reduces the activity of the ReRAM crossbars and the number of A/D conversions compared to static 8-bit uniform quantization. We evaluate ReDy on a popular set of modern CNNs. On average, ReDy provides 13% energy savings over an ISAAC-like accelerator with negligible area overhead.
- 12 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1042-1051
Open AccessReDy: A Novel ReRAM-centric Dynamic Quantization Approach for Energy-efficient CNNs
Deep Neural Networks (DNNs) have achieved enormous success for a large variety of applications. The primary operation in DNNs is the dot product of quantized input activations and weights. Prior works have proposed the design of memory-centric architectures based on the Processing-In-Memory (PIM) paradigm. Resistive RAM (ReRAM) technology is especially appealing for PIM-based DNN accelerators due to its high density to store weights, low leakage energy, low read latency, and high performance capabilities to perform the DNN dot-products massively in parallel within the ReRAM crossbars. However, the main bottleneck of these architectures is the energy-hungry analog-to-digital conversions (ADCs) required to perform analog computations in-ReRAM, which penalizes the efficiency and performance benefits of PIM. To improve energy-efficiency of in-ReRAM analog dot-product computations we present ReDy, a hardware accelerator that implements a novel ReRAM-centric Dynamic quantization scheme to take advantage of the bit serial streaming and processing of activations. The energy consumption of ReRAM-based DNN accelerators is directly proportional to the numerical precision of the input activations of each DNN layer. In particular, ReDy exploits the fact that activations of CONV layers of DNNs are commonly grouped according to the size of their filters and the size of the ReRAM crossbars. Then, ReDy quantizes on-the-fly each group of activations with a different precision based on a novel heuristic that takes into account the statistical distribution of each group. Overall, ReDy greatly reduces the activity of the ReRAM crossbars and the number of A/D conversions compared to static 8-bit uniform quantization. We evaluate ReDy on a popular set of modern CNNs. On average, ReDy provides 13% energy savings over an ISAAC-like accelerator with negligible area overhead.
- Open Access
- 30 July 2024
- Published by Elsevier in Microprocessors and Microsystems
- Vol. 109
Mixture-of-Rookies: Saving DNN computations by predicting ReLU outputs
- 30 July 2024
- Published by Elsevier in Microprocessors and Microsystems
- Vol. 109
Open AccessMixture-of-Rookies: Saving DNN computations by predicting ReLU outputs
- Open Access
- 7 June 2022
- Published by Elsevier in Journal of Systems Architecture
- Vol. 129
CREW: Computation reuse and efficient weight storage for hardware-accelerated MLPs and RNNs
- 7 June 2022
- Published by Elsevier in Journal of Systems Architecture
- Vol. 129
Open AccessCREW: Computation reuse and efficient weight storage for hardware-accelerated MLPs and RNNs
- Open Access
- 17 January 2022
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 4 (1) , 66-102
A Survey of Near-Data Processing Architectures for Neural Networks
Data-intensive workloads and applications, such as machine learning (ML), are fundamentally limited by traditional computing systems based on the von-Neumann architecture. As data movement operations and energy consumption become key bottlenecks in the design of computing systems, the interest in unconventional approaches such as Near-Data Processing (NDP), machine learning, and especially neural network (NN)-based accelerators has grown significantly. Emerging memory technologies, such as ReRAM and 3D-stacked, are promising for efficiently architecting NDP-based accelerators for NN due to their capabilities to work as both high-density/low-energy storage and in/near-memory computation/search engine. In this paper, we present a survey of techniques for designing NDP architectures for NN. By classifying the techniques based on the memory technology employed, we underscore their similarities and differences. Finally, we discuss open challenges and future perspectives that need to be explored in order to improve and extend the adoption of NDP architectures for future computing platforms. This paper will be valuable for computer architects, chip designers, and researchers in the area of machine learning.
- 17 January 2022
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 4 (1) , 66-102
Open AccessA Survey of Near-Data Processing Architectures for Neural Networks
Data-intensive workloads and applications, such as machine learning (ML), are fundamentally limited by traditional computing systems based on the von-Neumann architecture. As data movement operations and energy consumption become key bottlenecks in the design of computing systems, the interest in unconventional approaches such as Near-Data Processing (NDP), machine learning, and especially neural network (NN)-based accelerators has grown significantly. Emerging memory technologies, such as ReRAM and 3D-stacked, are promising for efficiently architecting NDP-based accelerators for NN due to their capabilities to work as both high-density/low-energy storage and in/near-memory computation/search engine. In this paper, we present a survey of techniques for designing NDP architectures for NN. By classifying the techniques based on the memory technology employed, we underscore their similarities and differences. Finally, we discuss open challenges and future perspectives that need to be explored in order to improve and extend the adoption of NDP architectures for future computing platforms. This paper will be valuable for computer architects, chip designers, and researchers in the area of machine learning.
- Open Access
- 1 January 2022
- Published by Elsevier in Journal of Systems Architecture
- Vol. 122
DNN pruning with principal component analysis and connection importance estimation
- 1 January 2022
- Published by Elsevier in Journal of Systems Architecture
- Vol. 122
Open AccessDNN pruning with principal component analysis and connection importance estimation
- 24 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 39 (5) , 36-45
CGPA: Coarse-Grained Pruning of Activations for Energy-Efficient RNN Inference
- 24 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 39 (5) , 36-45
CGPA: Coarse-Grained Pruning of Activations for Energy-Efficient RNN Inference
- 18 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 68 (5) , 765-783
SyRA: Early System Reliability Analysis for Cross-Layer Soft Errors Resilience in Memory Arrays of Microprocessor Systems
- 18 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 68 (5) , 765-783
SyRA: Early System Reliability Analysis for Cross-Layer Soft Errors Resilience in Memory Arrays of Microprocessor Systems