Ardalan Najafi

Ardalan Najafi

Auto-generated profile, based on publicly available information

Ardalan Najafi

Institute of Electrodynamics and Microelectronics, University of Bremen, 28359 Bremen, Germany

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
19 April 2018 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
ADAyad Dalloo
Ayad Dalloo
ANArdalan Najafi
Ardalan Najafi
AGAlberto Garcia-Ortiz
Alberto Garcia-Ortiz
Exploiting the tradeoff between accuracy and hardware cost has a tremendous potential to improve the efficiency of integrated systems. Using this concept, numerous approximate adders have been proposed in the last ten years. Although conceptually different, all previous architectures have been obtained with an ad hoc and nonsystematic methodology. Instead, this brief generalizes and systematically optimizes an architectural template for approximate adders. The outcome, called optimized lower part constant-OR adder (LOCA), outperforms previous approaches in terms of accuracy and hardware cost. For example, an 8-bit approximate adder implemented with our new approach improves the mean squared error by 58.5%, while simultaneously reducing the cost by 7.2% with respect to the previously reported best architecture.

4 May 2018 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Closed access
ANArdalan Najafi
Ardalan Najafi
MWMoritz Weibbrich
Moritz Weibbrich
GPGuillermo Paya-Vaya
Guillermo Paya-Vaya
AGAlberto Garcia-Ortiz
Alberto Garcia-Ortiz
Numerous approximate adders have been proposed in the literature in response to the languishing benefits of technology scaling. However, they have been obtained with an adhoc and non-systematic methodology which does not fully exploit the design space possibilities. This work provides a conceptual framework for the systematic design of approximate adders including hybrid and non-equally segmented approaches as well as more robust error metrics. The framework discriminates the scenarios where approximate processing does not provide significant benefits from those where it does; in this later case, it aids to obtain optimal configurations for the adders. Experimental results with a commercial technology assesses the significant improvements of our systematic approach. Furthermore, a case study with a processor enhanced with an approximate accelerator highlights the usability of the methods.

1 May 2014
Verified
Conference Paper
Closed access
ANArdalan Najafi
Ardalan Najafi
STSomayeh Timarchi
Somayeh Timarchi
ANAmir Najafi
Amir Najafi
Multipliers are important components that dictate the overall arithmetic circuits' performance. The most critical components of multipliers are compressors. In this paper, a new 5:2 compressor architecture based on changing some internal equations is proposed. In addition, using an efficient full-adder (FA) block is considered to have a high-speed compressor. The number of transistors in the proposed design is less than the best existing 5:2 compressor architectures. Three 5:2 compressors are considered for comparison. The proposed architecture is compared with the best existing designs presented in the state-of-the-art literature in terms of power, delay and area. Architectures are simulated in 90-nm CMOS technology under 1 V supply voltage. The simulation results show that the proposed compressor improves power and delay by 24.59% and 18.54% respectively, compared to two of the best existing architectures. In addition, voltage scaling and temperature analysis show that the proposed architecture outperforms the other designs from power-delay product (PDP) point of view in comparison to the aforementioned designs.

1 September 2017
Verified
Conference Paper
Closed access
ANArdalan Najafi
Ardalan Najafi
MWMoritz Weisbrich
Moritz Weisbrich
GVGuillermo Paya Vaya
Guillermo Paya Vaya
AGAlberto Garcia-Ortiz
Alberto Garcia-Ortiz
The demands of high-speed and power-efficient systems have resulted into the emergence of the approximate computing. Existing approximate circuits as well as stochastic techniques have shown promising advances in improving various figures of merit. However, a through fair comparison of arithmetic units still remains an issue which has not been studied. This paper reviews the prerequisites for a fair comparison of approximate arithmetic units. As one of the key components of arithmetic circuits, adders are the focus of this paper. For the first time in this paper, approximate and exact adders are studied together in the stochastic regime. Simulation results show that both the equal segmentation adder (ESA) and the error tolerant adder type II (ETAII) outperform exact adders working stochastically, if and only if the right configuration and sub-adder architectures are chosen. Otherwise, there is no reason to use the aforementioned architectures. In all, considering the cost-error trade-off, Lower-part OR adder (LOA) has the best behavior in the stochastic regime.

30 March 2020 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
ANAmir Najafi
Amir Najafi
ANArdalan Najafi
Ardalan Najafi
AGAlberto Garcia-Ortiz
Alberto Garcia-Ortiz
A major bottleneck of current integrated circuits is the performance of on-chip communication. It can be dramatically improved using wave-pipelining, which is very power efficient since it avoids additional pipeline registers. However, the error-free operation is getting challenging as technology scales down. Recently, approximate/stochastic communication is gaining interest since it allows to trade-off transmission quality by performance/power in resilient applications such as machine learning. Taking into account the challenges of classical wave-pipelining, this work proposes the concept of stochastic wave-pipelining communication. A comprehensive experimental result using a 65 nm commercial technology evaluates the proposed communication technique. Furthermore, the proposed approach is assessed using a case study employing Optical Character Recognition (OCR).

26 November 2020 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
WYWanli Yu
Wanli Yu
ANArdalan Najafi
Ardalan Najafi
YHYanqiu Huang
Yanqiu Huang
AGAlberto Garcia-Ortiz
Alberto Garcia-Ortiz
Achieving energy efficiency is always a primary concern for fog architecture based Internet of Things (IoT) applications. As the IoT devices are typically of small sizes and powered by battery energy, it is essential to address the energy consumption at all levels from circuit to system. Two of the promising solutions at circuit and system levels are approximate computing and energy aware task allocation, respectively. However, the existing task allocation approaches are designed without considering the aspect of approximate computing. In this work, we fill this gap and aim to maximize the network lifetime subject to the accuracy requirements of the applications. By considering both the approximate computing and task allocation simultaneously, a non-linear problem is obtained to allocate the tasks for the devices (fog nodes and IoT end devices) and to select the corresponding execution modes (tasks in approximate or exact modes). To efficiently solve this problem, a centralized algorithm is firstly proposed by transferring the above non-linear problem as a linear programming problem. As executing the centralized algorithm is a challenge for the resource limited IoT devices, this work further proposes an optimal distributed algorithm based on Dantzig-Wolf decomposition to solve the problem of tasks distribution and execution modes selection. The centralized large-scaled LP problem is decomposed into small-scaled sub-problems, which can be efficiently solved by each IoT device. The proposed algorithms are tested by extensive simulations. The results demonstrate that the distributed algorithm achieves the same results as the centralized algorithm, and both of them significantly outperform the previous approaches.