The Experts below are selected from a list of 180720 Experts worldwide ranked by ideXlab platform
Daniel Menard - One of the best experts on this subject based on the ideXlab platform.
-
New evaluation scheme for Software Function approximation with non-uniform segmentation
2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:—Modern applications embed complex mathematical processing based on composition of elementary Functions. A good balance between approximation accuracy, and implementation cost, i.e. memory space requirement and computation time, is needed to design an efficient implementation. From this point of view, approaches working with polynomial approximation obtain results of a monitored accuracy with a moderate implementation cost. For Software implementation in fixed-point processors, accurate results can be obtained if the segment on which the Function is computed I is segmented accurately enough, to have an approximating polynomial on each segment. Non-uniform segmentation is required to limit the number of segments and then the implementation cost. The proposed recursive scheme exploits the trade-off between memory requirement and evaluation time. The method is illustrated with the Function exp(− (x)) on the segment [2 −6 ; 2 5 ] and showed a mean speed-up ratio of 98.7 compared to math.h on the Digital Signal Processor C55x.
-
New Non-Uniform Segmentation Technique for Software Function Evaluation
2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:Embedded applications use more and more sophisticated computatious. These computations can integrate composition of elementary Functions and can easily be approximated by polynomials. Indeed, polynomial approximation methods allow to find a trade-off between accuracy and computation time. Software implementation of polynomial approximation in fixed-point processors is considered in this paper. To obtain a moderate approximation error, segmentation of the interval I on which the Function is computed is necessary. This paper proposes a new method to compute the values of a Function on I using non-uniform segmentation and polynomial approximation. Non-uniform segmentation allows one to minimize the number of segments created and is modeled by a tree-structure. The specifications of the segmentation set the balance between memory space requirement and computation time. Besides, compared to table-based methods or the CORDIC algorithm, our approach significantly reduces, the memory size and the Function evaluation time respectively.
-
ASAP - New non-uniform segmentation technique for Software Function evaluation
2016 IEEE 27th International Conference on Application-specific Systems Architectures and Processors (ASAP), 2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:Embedded applications use more and more sophisticated computations. These computations can integrate composition of elementary Functions and can easily be approximated by polynomials. Indeed, polynomial approximation methods allow to find a trade-off between accuracy and computation time. Software implementation of polynomial approximation in fixed-point processors is considered in this paper. To obtain a moderate approximation error, segmentation of the interval I on which the Function is computed is necessary. This paper proposes a new method to compute the values of a Function on I using non-uniform segmentation and polynomial approximation. Non-uniform segmentation allows one to minimize the number of segments created and is modeled by a tree-structure. The specifications of the segmentation set the balance between memory space requirement and computation time. Besides, compared to table-based methods or the CORDIC algorithm, our approach significantly reduces, the memory size and the Function evaluation time respectively.
-
EUSIPCO - New evaluation scheme for Software Function approximation with non-uniform segmentation
2016 24th European Signal Processing Conference (EUSIPCO), 2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:Modern applications embed complex mathematical processing based on composition of elementary Functions. A good balance between approximation accuracy, and implementation cost, i.e. memory space requirement and computation time, is needed to design an efficient implementation. From this point of view, approaches working with polynomial approximation obtain results of a monitored accuracy with a moderate implementation cost. For Software implementation in fixed-point processors, accurate results can be obtained if the segment on which the Function is computed I is segmented accurately enough, to have an approximating polynomial on each segment. Non-uniform segmentation is required to limit the number of segments and then the implementation cost. The proposed recursive scheme exploits the trade-off between memory requirement and evaluation time. The method is illustrated with the Function exp(−√(x)) on the segment [2−6; 25] and showed a mean speed-up ratio of 98.7 compared to the mathematical C standard library on the Digital Signal Processor C55x.
Justine Bonnot - One of the best experts on this subject based on the ideXlab platform.
-
New evaluation scheme for Software Function approximation with non-uniform segmentation
2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:—Modern applications embed complex mathematical processing based on composition of elementary Functions. A good balance between approximation accuracy, and implementation cost, i.e. memory space requirement and computation time, is needed to design an efficient implementation. From this point of view, approaches working with polynomial approximation obtain results of a monitored accuracy with a moderate implementation cost. For Software implementation in fixed-point processors, accurate results can be obtained if the segment on which the Function is computed I is segmented accurately enough, to have an approximating polynomial on each segment. Non-uniform segmentation is required to limit the number of segments and then the implementation cost. The proposed recursive scheme exploits the trade-off between memory requirement and evaluation time. The method is illustrated with the Function exp(− (x)) on the segment [2 −6 ; 2 5 ] and showed a mean speed-up ratio of 98.7 compared to math.h on the Digital Signal Processor C55x.
-
New Non-Uniform Segmentation Technique for Software Function Evaluation
2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:Embedded applications use more and more sophisticated computatious. These computations can integrate composition of elementary Functions and can easily be approximated by polynomials. Indeed, polynomial approximation methods allow to find a trade-off between accuracy and computation time. Software implementation of polynomial approximation in fixed-point processors is considered in this paper. To obtain a moderate approximation error, segmentation of the interval I on which the Function is computed is necessary. This paper proposes a new method to compute the values of a Function on I using non-uniform segmentation and polynomial approximation. Non-uniform segmentation allows one to minimize the number of segments created and is modeled by a tree-structure. The specifications of the segmentation set the balance between memory space requirement and computation time. Besides, compared to table-based methods or the CORDIC algorithm, our approach significantly reduces, the memory size and the Function evaluation time respectively.
-
ASAP - New non-uniform segmentation technique for Software Function evaluation
2016 IEEE 27th International Conference on Application-specific Systems Architectures and Processors (ASAP), 2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:Embedded applications use more and more sophisticated computations. These computations can integrate composition of elementary Functions and can easily be approximated by polynomials. Indeed, polynomial approximation methods allow to find a trade-off between accuracy and computation time. Software implementation of polynomial approximation in fixed-point processors is considered in this paper. To obtain a moderate approximation error, segmentation of the interval I on which the Function is computed is necessary. This paper proposes a new method to compute the values of a Function on I using non-uniform segmentation and polynomial approximation. Non-uniform segmentation allows one to minimize the number of segments created and is modeled by a tree-structure. The specifications of the segmentation set the balance between memory space requirement and computation time. Besides, compared to table-based methods or the CORDIC algorithm, our approach significantly reduces, the memory size and the Function evaluation time respectively.
-
EUSIPCO - New evaluation scheme for Software Function approximation with non-uniform segmentation
2016 24th European Signal Processing Conference (EUSIPCO), 2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:Modern applications embed complex mathematical processing based on composition of elementary Functions. A good balance between approximation accuracy, and implementation cost, i.e. memory space requirement and computation time, is needed to design an efficient implementation. From this point of view, approaches working with polynomial approximation obtain results of a monitored accuracy with a moderate implementation cost. For Software implementation in fixed-point processors, accurate results can be obtained if the segment on which the Function is computed I is segmented accurately enough, to have an approximating polynomial on each segment. Non-uniform segmentation is required to limit the number of segments and then the implementation cost. The proposed recursive scheme exploits the trade-off between memory requirement and evaluation time. The method is illustrated with the Function exp(−√(x)) on the segment [2−6; 25] and showed a mean speed-up ratio of 98.7 compared to the mathematical C standard library on the Digital Signal Processor C55x.
Erwan Nogues - One of the best experts on this subject based on the ideXlab platform.
-
New evaluation scheme for Software Function approximation with non-uniform segmentation
2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:—Modern applications embed complex mathematical processing based on composition of elementary Functions. A good balance between approximation accuracy, and implementation cost, i.e. memory space requirement and computation time, is needed to design an efficient implementation. From this point of view, approaches working with polynomial approximation obtain results of a monitored accuracy with a moderate implementation cost. For Software implementation in fixed-point processors, accurate results can be obtained if the segment on which the Function is computed I is segmented accurately enough, to have an approximating polynomial on each segment. Non-uniform segmentation is required to limit the number of segments and then the implementation cost. The proposed recursive scheme exploits the trade-off between memory requirement and evaluation time. The method is illustrated with the Function exp(− (x)) on the segment [2 −6 ; 2 5 ] and showed a mean speed-up ratio of 98.7 compared to math.h on the Digital Signal Processor C55x.
-
New Non-Uniform Segmentation Technique for Software Function Evaluation
2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:Embedded applications use more and more sophisticated computatious. These computations can integrate composition of elementary Functions and can easily be approximated by polynomials. Indeed, polynomial approximation methods allow to find a trade-off between accuracy and computation time. Software implementation of polynomial approximation in fixed-point processors is considered in this paper. To obtain a moderate approximation error, segmentation of the interval I on which the Function is computed is necessary. This paper proposes a new method to compute the values of a Function on I using non-uniform segmentation and polynomial approximation. Non-uniform segmentation allows one to minimize the number of segments created and is modeled by a tree-structure. The specifications of the segmentation set the balance between memory space requirement and computation time. Besides, compared to table-based methods or the CORDIC algorithm, our approach significantly reduces, the memory size and the Function evaluation time respectively.
-
ASAP - New non-uniform segmentation technique for Software Function evaluation
2016 IEEE 27th International Conference on Application-specific Systems Architectures and Processors (ASAP), 2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:Embedded applications use more and more sophisticated computations. These computations can integrate composition of elementary Functions and can easily be approximated by polynomials. Indeed, polynomial approximation methods allow to find a trade-off between accuracy and computation time. Software implementation of polynomial approximation in fixed-point processors is considered in this paper. To obtain a moderate approximation error, segmentation of the interval I on which the Function is computed is necessary. This paper proposes a new method to compute the values of a Function on I using non-uniform segmentation and polynomial approximation. Non-uniform segmentation allows one to minimize the number of segments created and is modeled by a tree-structure. The specifications of the segmentation set the balance between memory space requirement and computation time. Besides, compared to table-based methods or the CORDIC algorithm, our approach significantly reduces, the memory size and the Function evaluation time respectively.
-
EUSIPCO - New evaluation scheme for Software Function approximation with non-uniform segmentation
2016 24th European Signal Processing Conference (EUSIPCO), 2016Co-Authors: Justine Bonnot, Erwan Nogues, Daniel MenardAbstract:Modern applications embed complex mathematical processing based on composition of elementary Functions. A good balance between approximation accuracy, and implementation cost, i.e. memory space requirement and computation time, is needed to design an efficient implementation. From this point of view, approaches working with polynomial approximation obtain results of a monitored accuracy with a moderate implementation cost. For Software implementation in fixed-point processors, accurate results can be obtained if the segment on which the Function is computed I is segmented accurately enough, to have an approximating polynomial on each segment. Non-uniform segmentation is required to limit the number of segments and then the implementation cost. The proposed recursive scheme exploits the trade-off between memory requirement and evaluation time. The method is illustrated with the Function exp(−√(x)) on the segment [2−6; 25] and showed a mean speed-up ratio of 98.7 compared to the mathematical C standard library on the Digital Signal Processor C55x.
Cai Li-zhi - One of the best experts on this subject based on the ideXlab platform.
-
Research on Size Estimation Model for Software Function Test and Its Application
Computer Engineering, 2011Co-Authors: Cai Li-zhiAbstract:In this paper,a Function testing size estimation model based on Function point analysis is proposed.The model applies to black box testing,and can be used in system test and acceptance test.Its basic steps are: define test scope,estimate Software size,define size factor,and calculate test points.The model is applied in some Function test projects.The applications indicate that this model can be used to estimate the size,and bring positive effect to Software test.
Yang Xiu-xia - One of the best experts on this subject based on the ideXlab platform.
-
On Test Case Generation for Interactive Software
Journal of Chinese Computer Systems, 2010Co-Authors: Yang Xiu-xiaAbstract:For interactive Software,Function is completed with complicated human-machine interactions.Current test case generation methods of Function testing usually consider Software interface,while ignoring Software requirement and logic completion process.With these testing methods,test cases are generated ignorantly,and testing process may be disordered.In this paper,considering Function's logic completion process and interface together,a test case generation method based on data flow graph for interactive Software Function testing is proposed.This method describes transaction and generates test cases with data flows.This method could generate effective test cases,test interactive Software Function more comprehensively,and locate faults conveniently.
-
A Function Testing Method for Interactive Software
International Workshop on Computer Science and Engineering, 2009Co-Authors: Cao Wen-jing, Xu Sheng-hong, Yang Xiu-xiaAbstract:Interactive Software Function is executed through complicated human-machine interactions. For Interactive Software, current Function testing methods usually only consider Software interface information, while ignoring the inner performance process. With these testing methods, testing process may be disordered. To resolve the problem, a Function testing method based on data flow graph is proposed in this paper. Considering both the inner performance process and the interface information of Function, this method organizes Function testing process with data flows.
