Julia Programming Language Benchmark Using a Flight Simulation

• Published in: 2020 IEEE Aerospace Conference pp. 1 - 8
• Main Author: Sells, Ray
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.03.2020
• Subjects: Aerospace simulation; Benchmark testing; C++ languages; Dynamical systems; Encoding; Java; Missiles; Python; Runtime; Time-domain analysis
• DOI: 10.1109/AERO47225.2020.9172277

Julia's goal to provide scripting language ease-of-coding with compiled language speed is explored. The runtime speed of the relatively new Julia programming language is assessed against other commonly used languages including Python, Java, and C++. An industry-standard missile and rocket simulation, coded in multiple languages, was used as a test bench for runtime speed. All language versions of the simulation, including Julia, were coded to a highly-developed object-oriented simulation architecture tailored specifically for time-domain flight simulation. A "speed-of-coding" second-dimension is plotted against runtime for each language to portray a space that characterizes Julia's scripting language efficiencies in the context of the other languages. With caveats, Julia runtime speed was found to be in the class of compiled or semi-compiled languages. However, some factors that affect runtime speed at the cost of ease-of-coding are shown. Julia's built-in functionality for multi-core processing is briefly examined as a means for obtaining even faster runtime speed. The major contribution of this research to the extensive language benchmarking body-of-work is comparing Julia to other mainstream languages using a complex flight simulation as opposed to benchmarking with single algorithms.