Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
2 results
Search Results
Article Performance and Accuracy Predictions of Approximation Methods for Shortest-Path Algorithms on Gpus(Elsevier, 2022) Aktılav, Busenur; Öz, IşılApproximate computing techniques, where less-than-perfect solutions are acceptable, present performance-accuracy trade-offs by performing inexact computations. Moreover, heterogeneous architectures, a combination of miscellaneous compute units, offer high performance as well as energy efficiency. Graph algorithms utilize the parallel computation units of heterogeneous GPU architectures as well as performance improvements offered by approximation methods. Since different approximations yield different speedup and accuracy loss for the target execution, it becomes impractical to test all methods with various parameters. In this work, we perform approximate computations for the three shortest-path graph algorithms and propose a machine learning framework to predict the impact of the approximations on program performance and output accuracy. We evaluate random predictions for both synthetic and real road-network graphs, and predictions of the large graph cases from small graph instances. We achieve less than 5% prediction error rates for speedup and inaccuracy values.Conference Object Citation - WoS: 1Citation - Scopus: 3Automated Estimation of Functional Size From Code(IEEE, 2020) Özen, Özgesu; Özsoy, Bora; Aktılav, Busenur; Güleç, Eren Can; Demirörs, OnurDetermination of the size of a software project is challenging as well as crucial for both self-employed software developers and corporate businesses. That's why it is subjected to a lot of academic studies where it is discussed how to determine the size more accurately. Functional Size Measurement (FSM) is one the most popular measurement techniques for a software from the point of the delivered functionality. However, the aspects of know-how, the cost, time, and manual operation creates difficulties to apply FSM techniques. This study aims to solve these issues by automating the measurement process to approximate the functional size of a project using the COSMIC Functional Size Measurement. The end product of this study is called 'Cosmic APP' that utilizes the sequence diagram of a software after reverse engineering it from the given code using a third-party tool called 'SequenceDiagram'. The working principles, the estimation process, and the obtained results of 'Cosmic APP' are described thoroughly in this paper. © 2020 IEEE.