Mahdi Taheri

Mahdi Taheri

Auto-generated profile, based on publicly available information

Mahdi Taheri

Tallinn University of Technology

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
22 January 2024 in ACM Computing Surveys
Verified
Journal Article
Open access
MAMohammad Hasan Ahmadilivani
Mohammad Hasan Ahmadilivani
MTMahdi Taheri
Mahdi Taheri
JRJaan Raik
Jaan Raik
Masoud DaneshtalabMasoud Daneshtalab
Masoud Daneshtalab
MJMaksim Jenihhin
Maksim Jenihhin
Artificial Intelligence (AI) and, in particular, Machine Learning (ML), have emerged to be utilized in various applications due to their capability to learn how to solve complex problems. Over the past decade, rapid advances in ML have presented Deep Neural Networks (DNNs) consisting of a large number of neurons and layers. DNN Hardware Accelerators (DHAs) are leveraged to deploy DNNs in the target applications. Safety-critical applications, where hardware faults/errors would result in catastrophic consequences, also benefit from DHAs. Therefore, the reliability of DNNs is an essential subject of research. In recent years, several studies have been published accordingly to assess the reliability of DNNs. In this regard, various reliability assessment methods have been proposed on a variety of platforms and applications. Hence, there is a need to summarize the state-of-the-art to identify the gaps in the study of the reliability of DNNs. In this work, we conduct a Systematic Literature Review (SLR) on the reliability assessment methods of DNNs to collect relevant research works as much as possible, present a categorization of them, and address the open challenges. Through this SLR, three kinds of methods for reliability assessment of DNNs are identified, including Fault Injection (FI), Analytical, and Hybrid methods. Since the majority of works assess the DNN reliability by FI, we characterize different approaches and platforms of the FI method comprehensively. Moreover, Analytical and Hybrid methods are propounded. Thus, different reliability assessment methods for DNNs have been elaborated on their conducted DNN platforms and reliability evaluation metrics. Finally, we highlight the advantages and disadvantages of the identified methods and address the open challenges in the research area. We have concluded that Analytical and Hybrid methods are light-weight yet sufficiently accurate and have the potential to be extended in future research and to be utilized in establishing novel DNN reliability assessment frameworks.

27 December 2024 in IEEE Transactions on Device and Materials Reliability
Verified
Journal Article
Closed access
MTMahdi Taheri
Mahdi Taheri
NCNatalia Cherezova
Natalia Cherezova
SNSamira Nazari
Samira Nazari
AAAli Azarpeyvand
Ali Azarpeyvand
TGTARA GHASEMPOURI
TARA GHASEMPOURI
MJMaksim Jenihhin
Maksim Jenihhin
Deep Neural Network (DNN) hardware accelerators are essential in a spectrum of safety-critical edge-AI applications with stringent reliability, energy efficiency, and latency requirements. Multiplication is the most resource-hungry operation in the neural network’s processing elements. This paper proposes a scalable adaptive fault-tolerant approximate multiplier (AdAM) tailored for ASIC-based DNN accelerators at the algorithm and circuit levels. AdAM employs an adaptive adder that relies on an unconventional use of input Leading One Detector (LOD) values for fault detection by optimizing unutilized adder resources. A gate-level optimized LOD design and a hybrid adder design are also proposed as a part of the adaptive multiplier to improve the hardware performance. The proposed architecture uses a lightweight fault mitigation technique that sets the detected faulty bits to zero. The hardware resource utilization and the DNN accelerator’s reliability metrics are used to compare the proposed solution against the Triple Modular Redundancy (TMR) in multiplication, unprotected exact multiplication, and unprotected approximate multiplication. It is demonstrated that the proposed architecture enables a multiplication with a reliability level close to the multipliers protected by TMR while at the same time utilizing 2.74× less area and with 39.06% less power-delay product compared to the exact multiplier. Moreover, it has similar area, delay, and power consumption parameters compared to the state-of-the-art approximate multipliers with similar accuracy while providing fault detection and mitigation capability.

6 May 2024 in TechRxiv
Verified
Preprint
Open access
PDF file
MTMahdi Taheri
Mahdi Taheri
NCNatalia Cherezova
Natalia Cherezova
SNSamira Nazari
Samira Nazari
AAAli Azarpeyvand
Ali Azarpeyvand
TGTara Ghasempouri
Tara Ghasempouri
MJMaksim Jenihhin
Maksim Jenihhin
Deep Neural Network (DNN) hardware accelerators are essential in a spectrum of safety-critical edge-AI applications with stringent reliability, energy efficiency, and latency requirements. Multiplication is the most resource-hungry operation in the neural network's processing elements. This paper proposes a scalable adaptive fault-tolerant approximate multiplier (AdAM) tailored for ASIC-based DNN accelerators at the algorithm and circuit levels. AdAM employs an adaptive adder that relies on an unconventional use of input Leading One Detector (LOD) values for fault detection by optimizing unutilized adder resources. A gate-level optimized LOD design and a hybrid adder design are also proposed as a part of the adaptive multiplier to improve the hardware performance. The proposed architecture uses a lightweight fault mitigation technique that sets the detected faulty bits to zero. The hardware resource utilization and the DNN accelerator's reliability metrics are used to compare the proposed solution against the Triple Modular Redundancy (TMR) in multiplication, unprotected exact multiplication, and unprotected approximate multiplication. It is demonstrated that the proposed architecture enables a multiplication with a reliability level close to the multipliers protected by TMR while at the same time utilizing 2.74 × less area and with 39.06% less power-delay product compared to the exact multiplier. Moreover, it has similar area, delay, and power consumption parameters compared to the state-of-the-art approximate multipliers with similar accuracy while providing fault detection and mitigation capability.

17 May 2021 in IET Computers & Digital Techniques
Verified
Journal Article
Open access
PDF file
SSSaeideh Sheikhpur
Saeideh Sheikhpur
MTMahdi Taheri
Mahdi Taheri
MAMohammad Saeed Ansari
Mohammad Saeed Ansari
AMAli Mahani
Ali Mahani
Digital data transmission is day by day more vulnerable to both malicious and natural faults. With an aim to assure reliability, security and privacy in communication, a low‐cost fault resilient architecture for Advanced Encryption Standard (AES) is proposed. In order not to degrade the reliability of our AES architecture, the reliability of voter is very important, for which reason we have introduced a novel voting scheme include a majority voter (named TMR voter) and an error barrier element (named DMR voter). In this paper, a reliable and secure 32‐bit data‐path AES implementation based on our robust fault resilient approach is developed. We illustrate that the proposed architecture can tolerate up to triple‐bit (byte) simultaneous faults at each pipeline stage’s logic and verify our claim through extensive error simulations. Error simulation results also show that our architecture achieves close to 100% fault‐masking capability for multiple‐bit (byte) faults. Finally, it is shown that the Application‐Specific Integrated Circuit implementation of the fault‐tolerant architectures using the composite field‐based S‐box, CFB‐AES, and ROM‐based S‐box, RB‐AES allows better area usage, throughput and fault resilience trade‐off compared to their counterparts. So, it provides the most appropriate features to be used in highly‐secure resource‐constraint applications.

21 December 2020 in IET Circuits, Devices & Systems
Verified
Journal Article
Open access
PDF file
MTMahdi Taheri
Mahdi Taheri
MAMohammad Saeed Ansari
Mohammad Saeed Ansari
SMSebastian Magierowski
Sebastian Magierowski
AMAli Mahani
Ali Mahani
Next‐generation sequencing techniques have dramatically increased the amount of genomic data being sequenced, which calls for the acceleration of the alignment algorithms. This article proposes an FPGA‐based accelerated implementation of the seed extension kernel of the Burrows–Wheeler alignment genomic mapping algorithm. The well‐known Smith–Waterman algorithm is used during the seed extension to find the optimum alignment between the sequences. The state‐of‐the‐art architectures in the literature use one‐dimensional (1‐D) systolic arrays to fill a similarity matrix, based on the best score out of all match combinations, mismatches and gaps are computed. The cells on the same anti‐diagonal are computed in parallel in these architectures. We propose a novel 2‐dimensional architecture in which all the cells on the same rows and the same columns are computed in parallel and, thereby, significantly accelerated the process. The similarity matrix cells are computed in two phases: (1) the calculation phase and (2) error compensation phase. The calculation phase roughly approximate the cell values and the approximation error is fixed up during the error compensation phase. Our simulation results show that the proposed architecture can be up to 718x and 1.7x faster than the software execution and the 1‐D systolic arrays, respectively.

23 February 2026 in Journal of Systems Architecture
Verified
Journal Article
Open access
HHHector Gerardo Muñoz Hernandez
Hector Gerardo Muñoz Hernandez
MTMahdi Taheri
Mahdi Taheri
MAMuhammad Ali
Muhammad Ali
KSKeyvan Shahin
Keyvan Shahin
ASAlireza Syavashi
Alireza Syavashi
MHMichael Huebner
Michael Huebner