Genetic Programming of Pipelined Datapaths for FPGA

Sergiyenko, Anatoliy; Serhienko, Anastasia; Romankevich, Vitaliy

doi:10.1109/elnano50318.2020.9088773

Cited by 2 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the first stage of the synthesis according to the indicated method of the vertex-operator of the homogeneous spatial SDF together with arcs are located in three-dimensional space as sets of vectors Ki and Dj з taking into account the conditions given in [21]. At the same time, the coordinates of the vector Ki = (s,q,t) T mean the number s of PE, where the operator is executed, type q of PE and frequency component t, which is equal to the clock number in the algorithm execution period.…”

Section: Methods Of Synthesis Of Buffer Schemes Based On Spatial Spd ...mentioning

confidence: 99%

“…At the second stage, the spatial SDF is being balanced, which consists in adding delay vertices to the arcs of the graph until the time components of all vectors Dj are equal to 0 or 1. After that, the spatial SDF is optimized by mutual permutations of vectors-vertices from one layer in order to minimize the number of registers and the number of multiplexer inputs in the resulting structure and/or using other strategies, for example, resynchronization [20] or using genetic programming [21]. Also, the number of registers is minimized by gluing delay vertices from the same tier that store the same operand.…”

Section: Methods Of Synthesis Of Buffer Schemes Based On Spatial Spd ...mentioning

confidence: 99%

“…The design method of pipeline calculators with register buffers looks like this: Initial data -SDF, execution period of algorithm L and other optimization parameters. The method is performed in the same way as described in [21], with the exceptions described below.…”

Section: The Methods Of Synthesis Of Buffer Circuits For Processing O...mentioning

confidence: 99%

See 2 more Smart Citations

Image buffering in application specific processors

Sergienko¹,

Romankevich²,

Serhiienko³

2022

AAIT

View full text Add to dashboard Cite

In many digital image-processingapplications, which are implementedin field programmable gate arrays,the currently processed image's frames are stored in external dynamic memory.The performance of such an application dependson the dynamic memoryspeed and the necessaryrequests quantity during algorithm’sruntime. This performance is being optimized through field programmable gate arrays -implemented buffer memory usage.But there is no common method for the formal buffer memory synthesis with preset throughput, input and output data sequenceorderand minimizedhardwarecosts.In this article,the featuresof image input and processing based on Field Programmable Gate Arrayareconsidered.The methods of building buffer circuits in field programmable gate arrays, due to which the intensity of data exchanges with external memory is reduced, are analyzed. Themethod of synthesizing pipeline circuits with specified performance characteristics and the data sequence order is given, which is based on the mapping of the spatial synchronous data flows into the structure implemented in the field programmable gate arrays.A method of designing buffer schemes is proposed, which is based on the mapping of spatial synchronous data flows into local memory in the form of chains of pipeline registers.The method helpsto organize the data flow of at the input of built-in pipeline units of image processing, in which the data follow in a given order, andto minimize the amount of buffer memory.The method ensures the use of dynamically adjustable register delays built into the field programmable gate arrays, which increases the efficiency of buffering.Thismethod was tested during the development of an intelligent video camera. The embedded hardware implements a video image compression algorithm with a wide dynamic range according to the Retinexalgorithm. The same time it selects characteristic points in the image for the further pattern recognition.At the same time, multiple decimation of the frame is performed. Due to themultirate buffering of the image in the field programmable gate arrays,it was possible to avoid using of external dynamic memory

show abstract

Section: Methods Of Synthesis Of Buffer Schemes Based On Spatial Spd ...mentioning

confidence: 99%

Section: Methods Of Synthesis Of Buffer Schemes Based On Spatial Spd ...mentioning

confidence: 99%

See 1 more Smart Citation

Image buffering in application specific processors

Sergienko¹,

Romankevich²,

Serhiienko³

2022

AAIT

View full text Add to dashboard Cite

show abstract

“…The framework is able to perform the graphical input of SDF of the DSP algorithms with the given period L and data bit width. SDF can be optimized either manually or automatically using one of the genetic programming algorithms [40]. One of two strategies of the buffer design are used by the optimization as well.…”

Section: Synthesis Frameworkmentioning

confidence: 99%

Розробка Буферів Даних На Програмованих Логічних Інтегральних Схемах

Sergiyenko¹,

Serhiienko

Мозговий

et al. 2022

ІО&ІС

View full text Add to dashboard Cite

The need to intensify the extraction process using the influence of chemical reagents on beet chips was substantiated. The analysis of appli-cation of natural sorbents in food production technologies was carried out. The physical and chemical properties of zeolite were explored. The indicators that make it possible to apply natural zeolite for additional treatment of water and juices in sugar production were shown. The effectiveness of the use of natural zeolite for feed water treat-ment with the view to enhancing the technological quality of diffusive juice was determined. Experimental research revealed that feed water treatment with zeolite decreases the content of total iron, ammonium, and permanganate oxidation indicator. It was proved that microbial seeding of feed water and diffusive juice decreases in case of treatment with zeolite. It was established experimentally that the purification of diffu-sion juice occurs during zeolite application for feed water treatment. We determined the effectiveness of removal of macromolecular compounds, including dextran, from diffusive juice obtained during processing sugar beets of various technological quality with natural zeolite. It was shown that at the zeolite consumption of 0.1...0.4 % to the weight of beets, the content of high-molecular compounds and pectic substances in diffusive juice decreases by 30–40 %, and the content of dextran – by 20–40 %, respectively. During the zeolite treatment, an enhancement of the quality of purified juice and improvement of filtration and saturation proper-ties of defeco-saturated precipitate are observed. Thus, the average rate of sedimentation of the precipitate of juice of І carbonation S5 m, when using zeolite for feed water preparation increases by 10–50 % for the beet different technological quality. In the course of research, we designed the technique of zeolite application, which ensures a decrease in coloration, an increase in the purity of the cleared juice, enhancement of filtration and sedimentation properties of the precipitate of juice of I carbon-ation. High effectiveness of the proposed method is pronounced in processing raw materials of lowered quality. Thus, there are some grounds to claim the effectiveness of zeolite application to enhance the quality of diffusion juice and products in sugar production. Keywords: diffusion juice, dextran, sucrose extraction, purification of diffusion juice, zeolite.

show abstract

Genetic Programming of Pipelined Datapaths for FPGA

Cited by 2 publications

References 19 publications

Image buffering in application specific processors

Image buffering in application specific processors

Розробка Буферів Даних На Програмованих Логічних Інтегральних Схемах

Contact Info

Product

Resources

About