Code Transform Model Producing High-Performance Program

Bao Chang; Hsiu-Fen Tsai; Po-Wen Su

doi:10.32604/cmes.2021.015673

Table of Content

Open Access

ARTICLE

Code Transform Model Producing High-Performance Program

Bao Rong Chang^1,*, Hsiu-Fen Tsai², Po-Wen Su¹
1 Department of Computer Science and Information Engineering, National University of Kaohsiung, Kaohsiung, Taiwan
2 Department of Fragrance and Cosmetic Science, Kaohsiung Medical University, Kaohsiung, Taiwan
* Corresponding Author: Bao Rong Chang. Email:
(This article belongs to this Special Issue: Hybrid Intelligent Methods for Forecasting in Resources and Energy Field)

Computer Modeling in Engineering & Sciences 2021, 129(1), 253-277. https://doi.org/10.32604/cmes.2021.015673

Received 04 January 2021; Accepted 21 May 2021; Issue published 24 August 2021

Abstract

This paper introduces a novel transform method to produce the newly generated programs through code transform model called the second generation of Generative Pre-trained Transformer (GPT-2) reasonably, improving the program execution performance significantly. Besides, a theoretical estimation in statistics has given the minimum number of generated programs as required, which guarantees to find the best one within them. The proposed approach can help the voice assistant machine resolve the problem of inefficient execution of application code. In addition to GPT-2, this study develops the variational Simhash algorithm to check the code similarity between sample program and newly generated program, and conceives the piecewise longest common subsequence algorithm to examine the execution’s conformity from the two programs mentioned above. The code similarity check deducts the redundant generated programs, and the output conformity check finds the best-performing generative program. In addition to texts, the proposed approach can also prove the other media, including images, sounds, and movies. As a result, the newly generated program outperforms the sample program significantly because the number of code lines reduces 27.21%, and the program execution time shortens 24.62%.

Keywords

Newly generated programs; GPT-2; predetermined generative programs; variational Simhash algorithm; piecewise longest common subsequence

Cite This Article

Chang, B. R., Tsai, H., Su, P. (2021). Code Transform Model Producing High-Performance Program. CMES-Computer Modeling in Engineering & Sciences, 129(1), 253–277.

This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.