Current Issue : January - March Volume : 2018 Issue Number : 1 Articles : 5 Articles
Computing systems with field-programmable gate arrays (FPGAs) often achieve fault tolerance in high-energy radiation\nenvironments via triple-modular redundancy (TMR) and configuration scrubbing. Although effective, TMR suffers from a 3x\narea overhead, which can be prohibitive for many embedded usage scenarios. Furthermore, this overhead is often worsened\nbecause TMR often has to be applied to existing register-transfer-level (RTL) code that designers created without considering the\ntriplicated resource requirements. Although a designer could redesign the RTL code to reduce resources, modifying RTL schedules\nand resource allocations is a time-consuming and error-prone process. In this paper, we present a more transparent high-level\nsynthesis approach that uses scheduling and binding to provide attractive tradeoffs between area, performance, and redundancy,\nwhile focusing on FPGA implementation considerations, such as resource realization costs, to produce more efficient architectures.\nCompared to TMR applied to existing RTL, our approach shows resource savings up to 80% with average resource savings of 34%\nand an average clock degradation of 6%. Compared to the previous approach, our approach shows resource savings up to 74%with\naverage resource savings of 19%and an average heuristic execution time improvement of 96x....
The fa�§ade cleaning of high rise buildings is one of the hazardous tasks that is performed\nby human operators. Even after a significant advancement in construction technologies, several\nnewfangled skyscrapers are still using the manual method for cleaning the glass panels. This research\nis aimed at the development of a glass fa�§ade cleaning robot, capable of adapting to any kind\nof building architecture. A robotic system capable of cleaning vertical glass surfaces demands\na transformable morphology. A self-reconfigurable robot is one of the potential solutions to realize\nhigh degrees of adaptability. Following the design principles we derived, we propose a nested\nreconfigurable design approach for glass fa�§ade cleaning and develope a system of robot modules\nthat performs glass fa�§ade cleaning. Throughout this research article, we discuss the brief concept and\nscheme of nested reconfigurable design principle and the hardware-software challenges associated\nwith it. This article also discusses the capability to maximize the flexibility and modularity of the\nrobot by using intra- and inter-reconfigurations. The effectiveness of the designed system is verified\nby experimental means....
In sensory swarms, minimizing energy consumption under performance constraint\nis one of the key objectives. One possible approach to this problem is to monitor application\nworkload that is subject to change at runtime, and to adjust system configuration adaptively to\nsatisfy the performance goal. As today�s sensory swarms are usually implemented using multi-core\nprocessors with adjustable clock frequency, we propose to monitor the CPU workload periodically\nand adjust the task-to-core allocation or clock frequency in an energy-efficient way in response\nto the workload variations. In doing so, we present an online heuristic that determines the most\nenergy-efficient adjustment that satisfies the performance requirement. The proposed method is\nbased on a simple yet effective energy model that is built upon performance prediction using IPC\n(instructions per cycle) measured online and power equation derived empirically. The use of IPC\naccounts for memory intensities of a given workload, enabling the accurate prediction of execution\ntime. Hence, the model allows us to rapidly and accurately estimate the effect of the two control\nknobs, clock frequency adjustment and core allocation. The experiments show that the proposed\ntechnique delivers considerable energy saving of up to 45%compared to the state-of-the-art multi-core\nenergy management technique....
A 1-bit digital reconfigurable reflective metasurface (RRM) with 20 Ã?â?? 20 cells is presented,\nfabricated and measured for beam-scanning performance in this paper. The cell is designed with a\nsingle layer structure and one varactor diode, controlled electronically. The cellââ?¬â?¢s phase compensation\nis over 180ââ??¦ between 3 GHz and 4 GHz and the two states with 180ââ??¦ phase difference are selected\nas coding ââ?¬Å?0ââ?¬Â and coding ââ?¬Å?1ââ?¬Â. By the fuzzy quantification theory, all the elements on the RRM are\nset to be coding ââ?¬Å?0ââ?¬Â or coding ââ?¬Å?1ââ?¬Â according to the phase compensation calculated by MATLAB.\nFurthermore, by changing the coding of the RRM, it can achieve beam-scanning. The simulation\nresults show that the beam-scanning range is over Ã?±60ââ??¦. The RRM prototype is fabricated and\nexperimentally tested for principle. The gain of the RRM is 18 dB and the 3 dB bandwidth is about\n16.6%. The 1-bit digital RRM is preferred in practical implementations due to less error and much\neasier bias voltage control. The proposed RRM successfully balances the performance and system\ncomplexity, especially in the large-scale antenna designs. The experimental and simulated results are\nin good agreement to prove the correctness and feasibility of the design of the 1-bit digital RRM....
Modern cryptography seeks to guarantee the information confidentiality and\nprevent unauthorized people from having access to it. These principles may be\napplied in portable devices that require the protection of the information that has\nbeen stored and processed. These types of applications require certain design\ncommitments that are achieved using high-performance hardware and the\nimplementation of light-weight algorithms, specifically the Present algorithm.\nThis method uses a block-based light encryption scheme which is relatively new,\nthat has not been infringed at the present date, with features that make it appealing\nfor an implementation on reconfigurable architectures such as FPGA. This work\npresents the study, design, implementation and tests of this encryption algorithm....
Loading....