International Journal of High Performance Systems Architecture (5 papers in press)
A VLSI Architecture of CORDIC based Popular Windows and Its FPGA Prototype
by VIKAS KUMAR, Kailash Chandra Ray, Preetam Kumar
Abstract: Popular window technique such as Hamming, Hanning, Blackman, Blackman - Harris and Flat Top windows are an obvious choice before Fast Fourier Transform(FFT) in the domain of signal processing, communication system and image processing to minimize the undesirable phenomenon i.e. spectral leakage and picket fence effect arise due to direct truncation by rectangular window. As the window characteristics depends upon the type of the function and length of window used, hence this is necessary to choose a particular window function and window length depending upon the applications. In other hand, real time implementation of window function demands efficient and flexible VLSI architecture. Hence this paper presents a new hardware efficient CORDIC based VLSI architecture which is capable of reconfigurability to choose a window function among aforesaid popular window functions and window length ranging from 8 to 32K, depending upon the application. Further this proposed architecture is prototyped on FPGA for real time validation and implementation results have been highlighted along with error analysis.
Keywords: CORDIC; Flat Top Window; Blackman-Harris Window; Blackman Window; Hamming Window; Hanning Window; FFT; FPGA; Signal Processing.ORDIC; Flat Top Window; Blackman-Harris Window; Blackman Window; Hamming Window; Hanning Window; FFT; FPGA; Signal Processing.C.
Synthesis of Standard Functions and Generic Ex-OR Module using Layered T Gate
by Chiradeep Mukherjee, Saradindu Panda, Asish Kr Mukhopadhyay, Bansibadan Maji
Abstract: The Quantum-dot Cellular Automata (QCA) which is the most promising technology in the paradigm of Nano electronics has already been claimed to possess ultra-high packing density, high clocking speed and extremely low power dissipation. In the last year with the advancement of successful instantiation of QCA, it proves proper functionality even in room temperature. The previous logic reduction schemes of QCA have made multi-level complex digital design simpler. Still their exist lack of optimal design of generic Exclusive OR Gate design in this field. This work proposes a novel design of high fan-in Exclusive-OR Gate by using the Layered T Gate of QCA. The Robustness Analysis of Layered T Gate has also been done to focus the advantage of Layered T Architecture in generic sense considering the defects of QCA. The Layered T architecture is implemented in standard function realization to verify the scalable and reusable nature of Layered T module. The impacts of device-fabrication metrics such as Layer Separation, Radius of Effect, Cell Spacing and AUF on Layered T Gate are thoroughly investigated. Based on AUF analysis of different QCA logic gates, the proper logic reduction technique for complex digital circuit is proposed. The synthesis of Three-Literal Standard Functions by using Layered T Gate reports an average 29.31% less area requirement as compared to the best reported design so far. Primarily two-input Layered T Exclusive OR shows 18.75% less Cell Requirement and 6.20% less area requirement as compared to the conventional two-input Exclusive OR Designs. An important QCA Circuit Design metric Costα is also calculated for QCA Exclusive OR Designs. The analysis shows 36.37% improvement in Costα with respect to the best reported Exclusive OR design so far. Finally, two-input Layered T Exclusive OR Module extends its design methodology to implement high fan-in Exclusive OR Gate designs with proper formulation of O-Cost and delay in QCA.
Keywords: QCA; Area Utilization Factor; O-Cost; Layered T Gate; Defects of QCA; Standard Function; Exclusive OR Gate; QCADesigner.
An Enhanced Model for Reliable Deflection Routing in Mesh Network On Chip
by Simi Zerine Sleeba, M.G. Mini
Abstract: Massive integration of processing cores into a finite chip area increases the possibility of damage and failure of various chip components. Issues and solutions related to reliable on-chip communication is of great importance in this context. On-chip routers play a vital role in routing packets through the NoC. In this paper, we propose a new fault tolerant routing model for NoCs using deflection routing mechanism. This model intelligently utilizes fault-free unidirectional links between the routers to forward flits to their destinations in few number of hops. These links are activated at regular time intervals so that they serve as alternate productive paths for flits which are delayed due to faults in their computed routes. We also present a routing algorithm that exploits the path diversity in the network generated by the enhanced model. From experimental analysis, we obtain significant improvement in the network performance parameters like flit latency, deflection rate and dynamic energy dissipation across router links for the proposed model compared to the state-of-the-art fault tolerant routing methods in NoC.
Keywords: Network on Chip; Fault tolerant routing; Deflection routing; Average latency; Dynamic link energy.
Partial Dynamic Reconfiguration Framework for FPGAs through Remote Access
by Anitha Arumalla, Madhavi Latha Makkena
Abstract: With the advent of Internet of Things (IoT) and Ubiquitous computing, the need for resource aware reconfiguration platform is increasing tremendously. Though a number of dynamic partial reconfiguration systems are available, they consume a significant portion of base system area in comparison with the application running on the system. Larger area requirements of reconfigurable platform cannot take the advantage of reconfigurable systems. Hence a light weighted and flexible reconfigurable framework with remote access reconfiguration is proposed. The system occupied less than 1% of the total device resources and attained 400MBps reconfiguration throughput. This framework can be used to any number of reconfiguration regions and is suitable for any application. The proposed framework for partial dynamic reconfiguration through remote access is tested on Virtex5 XC5VFX70T and Virtex6 XC6VLX240T FPGAs with 1Gbps Ethernet link.
Keywords: dynamic partial reconfiguration; ICAP controller; remote access.
Special Issue on: Internet of Things Principles, Methodologies, and Applications
A New Ontology Ranking Method with OntoDUIA for Ontology Retrieval System
by Jianghua Li, Boyu Li
Abstract: Ontology is being widely used for data integration and knowledge discovery in the field of data engineering. Ontology ranking is one of the important function of ontology search engine, which ranks the searched ontologies in a reasonable order. A good ranking method can help a user acquiring the satisfied ontology efficiently from a considerable amount of search results. However, existing methods in literatures are unable to rank ontologies to well meet users ranking demand due to their inherent shortcomings. In this paper, a novel ontology ranking method OntoDUIA is proposed and presented. It evaluates user-query related ontologies and ranks them based on a set of metrics of query relevance, usability, instance distribution and authority of ontology. To evaluate OntoDUIA, a series of experiments are conducted to compare the performance among OntoDUIA and some existing ontology ranking methods as well as human experts. Experimental results show that OntoDUIA can effectively meet users ontology ranking demand, and it achieves stable and reliable ranking results. Finally, OntoDUIA can also be applied to ontology retrieval system.
Keywords: Ontology ranking; Relevance metrics; Usability quality metrics; Instance metrics.