Mohammad Sabri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mohammad Sabri has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
Antonio González
2 shared publicationsMarc Riera
2 shared publications- Antonio González
Universitat Politecnica de Catalunya, Barcelona, Spain
1 shared publication - Marc Riera
Universitat Politcnica de Catalunya (UPC), Barcelona, Spain
1 shared publication
Latest Publications
- Open Access
- 20 December 2025
- Published by Elsevier in Journal of Systems Architecture
- Vol. 172
ARAS: Adaptive low-cost ReRAM-based accelerator for DNNs
- 20 December 2025
- Published by Elsevier in Journal of Systems Architecture
- Vol. 172
Open AccessARAS: Adaptive low-cost ReRAM-based accelerator for DNNs
- Open Access
- 20 May 2025
- Published by Elsevier in Journal of Systems Architecture
- Vol. 166
Hamun: An approximate computing method to prolong the lifespan of ReRAM-based accelerators
- 20 May 2025
- Published by Elsevier in Journal of Systems Architecture
- Vol. 166
Open AccessHamun: An approximate computing method to prolong the lifespan of ReRAM-based accelerators
- 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.