Kiamal Pekmestzi

Kiamal Pekmestzi

Auto-generated profile, based on publicly available information

Kiamal Pekmestzi

National Technical University of Athens, Zografou Greece

Research Focus & Metrics

Academic Career Length

26Years (2001-Present)

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

Representative Publications

View All Publications
5 March 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
VLVasileios Leon
Vasileios Leon
MHMuhammad Abdullah Hanif
Muhammad Abdullah Hanif
GAGiorgos Armeniakos
Giorgos Armeniakos
XJXun Jiao
Xun Jiao
DSDR SHAFIQUE
DR SHAFIQUE
DSDimitrios Soudris
Dimitrios Soudris
The rapid growth of demanding applications in domains applying multimedia processing and machine learning has marked a new era for edge and cloud computing. These applications involve massive data and compute-intensive tasks, and thus, typical computing paradigms in embedded systems and data centers are stressed to meet the worldwide demand for high performance. Concurrently, over the last 15 years, the semiconductor industry has established power efficiency as a first-class design concern. As a result, the community of computing systems is forced to find alternative design approaches to facilitate high-performance and power-efficient computing. Among the examined solutions, Approximate Computing has attracted an ever-increasing interest, which has resulted in novel approximation techniques for all the layers of the traditional computing stack. More specifically, during the last decade, a plethora of approximation techniques in software (programs, frameworks, compilers, runtimes, languages), hardware (circuits, accelerators), and architectures (processors, memories) have been proposed in the literature. The current article is Part I of a comprehensive survey on Approximate Computing. It reviews its motivation, terminology, and principles, as well as it classifies the state-of-the-art software & hardware approximation techniques, presents their technical details, and reports a comparative quantitative analysis.

20 February 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
VLVasileios Leon
Vasileios Leon
MHMuhammad Abdullah Hanif
Muhammad Abdullah Hanif
GAGiorgos Armeniakos
Giorgos Armeniakos
XJXun Jiao
Xun Jiao
DSDR SHAFIQUE
DR SHAFIQUE
DSDimitrios Soudris
Dimitrios Soudris
The challenging deployment of compute-intensive applications from domains such as Artificial Intelligence (AI) and Digital Signal Processing (DSP), forces the community of computing systems to explore new design approaches. Approximate Computing appears as an emerging solution, allowing to tune the quality of results in the design of a system in order to improve the energy efficiency and/or performance. This radical paradigm shift has attracted interest from both academia and industry, resulting in significant research on approximation techniques and methodologies at different design layers (from system down to integrated circuits). Motivated by the wide appeal of Approximate Computing over the last 10 years, we conduct a two-part survey to cover key aspects (e.g., terminology and applications) and review the state-of-the-art approximation techniques from all layers of the traditional computing stack. Part II of the survey classifies and presents the technical details of application-specific and architectural approximation techniques, which both target the design of resource-efficient processors/accelerators and systems. Moreover, it reports a quantitative analysis of the techniques and a detailed analysis of the application spectrum of Approximate Computing, and finally, it discusses open challenges and future directions.

10 January 2005 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
PBP. Bougas
P. Bougas
PKP. Kalivas
P. Kalivas
ATA. Tsirikos
A. Tsirikos
KPK.Z. Pekmestzi
K.Z. Pekmestzi
The elaborate design of folded finite-impulse response (FIR) filters based on pipelined multiplier arrays is presented in this paper. The design is considered at the bit-level and the internal delays of the pipelined multiplier array are fully exploited in order to reduce hardware complexity. Both direct and transposed FIR filter forms are considered. The carry-save and the carry-propagate multiplier arrays are studied for the filter implementations. Partially folded architectures are also proposed which are implemented by cascading a number of folded FIR filters. The proposed schemes are compared as to the aspect of hardware complexity with a straightforward implementation of a folded FIR filter based on the pipelined Wallace Tree multiplier. The comparison reveals that the proposed schemes require 20%-30% less hardware. Finally, efficient implementation of partially folded FIR filter circuits is presented when constraints in area, power consumption and clock frequency are given.

23 November 2020
Verified
Conference Paper
Closed access
GLGeorge Lentaris
George Lentaris
GCGeorge Chatzitsompanis
George Chatzitsompanis
VLVasileios Leon
Vasileios Leon
KPKiamal Pekmestzi
Kiamal Pekmestzi
DSDimitrios Soudris
Dimitrios Soudris
Convolutional Neural Networks (CNN) plea for improved design at circuit level. Instead of compression, we adopt here arithmetic approximation techniques supporting seamlessly the original structure and arithmetic type of a given network. We focus on the convolution and explore various approximations towards refining the resources and/or throughput of any CNN implementation. We develop hybrid high radix multipliers, block floating point arithmetic, as well as parallel architectures and Winograd convolutions to further enhance our design. Results show half cost or even quadruple FPS, depending on ASIC/FPGA technology, with only negligible 0.1-0.4% loss of CNN accuracy.

13 January 2020 in Technologies
Verified
Journal Article
Open access
PDF file
VLVasileios Leon
Vasileios Leon
SMSpyridon Mouselinos
Spyridon Mouselinos
KKKonstantina Koliogeorgi
Konstantina Koliogeorgi
SXSotirios Xydis
Sotirios Xydis
DSDimitrios Soudris
Dimitrios Soudris
KPKiamal Pekmestzi
Kiamal Pekmestzi
The workloads of Convolutional Neural Networks (CNNs) exhibit a streaming nature that makes them attractive for reconfigurable architectures such as the Field-Programmable Gate Arrays (FPGAs), while their increased need for low-power and speed has established Application-Specific Integrated Circuit (ASIC)-based accelerators as alternative efficient solutions. During the last five years, the development of Hardware Description Language (HDL)-based CNN accelerators, either for FPGA or ASIC, has seen huge academic interest due to their high-performance and room for optimizations. Towards this direction, we propose a library-based framework, which extends TensorFlow, the well-established machine learning framework, and automatically generates high-throughput CNN inference engines for FPGAs and ASICs. The framework allows software developers to exploit the benefits of FPGA/ASIC acceleration without requiring any expertise on HDL development and low-level design. Moreover, it provides a set of optimization knobs concerning the model architecture and the inference engine generation, allowing the developer to tune the accelerator according to the requirements of the respective use case. Our framework is evaluated by optimizing the LeNet CNN model on the MNIST dataset, and implementing FPGA- and ASIC-based accelerators using the generated inference engine. The optimal FPGA-based accelerator on Zynq-7000 delivers 93% less memory footprint and 54% less Look-Up Table (LUT) utilization, and up to 10× speedup on the inference execution vs. different Graphics Processing Unit (GPU) and Central Processing Unit (CPU) implementations of the same model, in exchange for a negligible accuracy loss, i.e., 0.89%. For the same accuracy drop, the 45 nm standard-cell-based ASIC accelerator provides an implementation which operates at 520 MHz and occupies an area of 0.059 mm 2 , while the power consumption is ∼7.5 mW.

6 September 2019 in IET Circuits, Devices & Systems
Verified
Journal Article
Open access
PDF file
VLVasileios Leon
Vasileios Leon
SXSotirios Xydis
Sotirios Xydis
DSDimitrios Soudris
Dimitrios Soudris
KPKiamal Pekmestzi
Kiamal Pekmestzi
Multiplication is an arithmetic operation that has a significant impact on the performance of various real‐life applications, such as digital signal processing, image processing and computer vision. In this study, targeting to exploit the efficiency of alternative number representation formats, the authors propose an energy‐efficient scheme for multiplying 2's‐complement binary numbers with two least significant bits (LSBs). The double‐LSB (DLSB) arithmetic delivers several benefits, such as the symmetric representation range, the number negation performed only by bitwise inversion, and the facilitation of the rounding process in the results of floating point architectures. The hardware overhead of the proposed circuit, when implemented at 45 nm, is negligible in comparison with the conventional Modified Booth multiplier for the ordinary 2's‐complement numbers (3.1% area and 3.3% energy average overhead for different multiplier's bit‐width). Moreover, the proposed DLSB multiplier outperforms the previous state‐of‐the‐art implementation by providing 10.2% energy and 7.8% area average gains. Finally, they demonstrate how the DLSB multipliers can be effectively used as a building block for the implementation of larger multiplications, delivering area and energy savings.