Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Muhammad Rizal Ma'rufi
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Implementasi Komputasi Paralel GPU pada Algoritme Cellular Automata Menggunakan CUDA® Muhammad Rizal Ma'rufi; Imam Cholissodin; Eriq Muh. Adams Jonemaro
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 4 (2019): April 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1162.18 KB)

Abstract

Video games industry is expanding fast in this modern era. This expansion needs to be balanced with quality and production time from creator. Procedural Content Generation (PCG) is one of innovations that suit with that condition. In PCG world, there are many algorithms can be used, one of the most well know in PCG is cellular automata (CA) algorithm. But CA has efficiency problem, but it can be solved with parallel computing. In this research, parallel computing is implemented using CUDA® technology. But there is another problem, that is the map result from CA is not always giving good result, sometimes it cannot be played due to isolated cave in map, but it can be solved using flood fill algorithm. In this research, the implementation will go through few steps, implementation of CA CPU, CA GPU and Flood Fill. Then those implementations will be integrated with Unity® game engine, then time to implement it to game. The game implementations will use Unity® game engine with C# as scripting language. CA CPU, CA GPU and Flood Fill algorithms computation time will be tested to know their performances. From the test result, CA GPU algorithm has better performance than CA CPU up to 227 times. In the other hand, flood fill algorithm that being used in this research has very high computation time, so the map size is very limited.
Co-Authors Eriq Muh. Adams Jonemaro Imam Cholissodin