Exploiting cache locality to speedup register clustering

Fontana, Tiago Augusto; Almeida, Sheiny Fabre; Netto, Renan; Livramento, Vinicius; Guth, Chrystian; Pilla, Laércio Lima; Güntzel, José Luís

doi:10.1145/3109984.3110005

Cited by 1 publication

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly to our work, Fontana et al [16] investigated the performance impact of multi-threading for both design patterns in the domain of electronic design automation tools. The results showed that DOD was faster than OOD where the cache misses were fewer and the performance was faster.…”

Section: Related Workmentioning

confidence: 76%

See 1 more Smart Citation

Evaluating the performance of object-oriented and data-oriented design with multi-threading in game development

Wingqvist

Wickstrom

Memeti

2022

2022 IEEE Games, Entertainment, Media Conference (GEM)

View full text Add to dashboard Cite

The frame rate of a game is important for both the end-user and the developer, and for a game to be considered playable, the minimum requirement of 60 FPS should be maintained. With respect to the programming design pattern, the current industry standard is to use Object-Oriented Design (OOD). While the demand for effcient game applications is increasing, applications developed using OOD are struggling to effciently utilize the available computing resources and consequently meet the minimum frame-rate requirements. A design pattern that may be able to cope with the current and future requirements of resource-intensive game applications is the Data-Oriented Design (DOD), which focuses on the effcient CPU memory utilization. The main difference between OOD and DOD is related to the way data is organized and accessed. While DOD is able to effciently utilize the cache memory, programming using the dataoriented design is perceived as much more complex compared to programming applications using object-oriented design.In this paper, we will frst develop a simple game application using both programming design patterns. Thereafter, we evaluate the performance of both implementations with respect to the overall execution time, CPU and memory utilization. Furthermore, we will develop the corresponding multi-threading versions to explore how the memory is utilized when multiple cores access data from shared cache memory. The results of the empirical evaluation show that the code sections that use DOD perform signifcantly faster than the corresponding parts implemented using OOD for both single-threaded and multithreaded applications. The maximum observed speedup of 13.25 times demonstrates that games and applications developed using DOD can utilize the available resources more effciently.

show abstract

Section: Related Workmentioning

confidence: 76%

“…The work by Fontana et al [16] is the only one of the related articles that is concerned with comparing the multi-threaded and single-threaded performance of DOD and OOD.…”

Section: Related Workmentioning

confidence: 99%