A Hybrid Round-Robin Scheduler for GPU Batch Rendering  in Constrained Cloud Environments

Ibnu Hadi Purwanto; Dhani Ariatmanto; M. Shahkhir Mozamir; Afifah Nur Aini

doi:10.29207/resti.v10i1.7117

Authors

Ibnu Hadi Purwanto Universitas AMIKOM Yogyakarta
Dhani Ariatmanto Universitas AMIKOM Yogyakarta
M. Shahkhir Mozamir Universiti Teknikal Malaysia Melaka
Afifah Nur Aini Universitas AMIKOM Yogyakarta

DOI:

https://doi.org/10.29207/resti.v10i1.7117

Keywords:

cloud rendering, computational efficiency, hybrid scheduler, quantum optimization, task scheduling

Abstract

Creating high-quality 2D and 3D assets is essential for digital content, but inefficient scheduling and inaccurate time estimates often hamper the rendering process. Traditional methods, which assume rendering time is directly proportional to frame count, fail to account for variations in scene complexity, resulting in severe estimation errors averaging 97.0% across all tasks. We propose a Hybrid Round-Robin Scheduler (HRRS) that intelligently manages batch rendering tasks through complexity-aware classification. Our method first categorizes tasks by complexity (Low, Medium, High) and routes them to appropriate queues with tiered quantum allocations. It then employs non-linear time estimation models and dynamically adjusts processing priorities based on real-time performance metrics. We evaluated our scheduler against standard algorithms—First-Come-First-Served (FCFS), Shortest Job First (SJF), and Round Robin (RR)—using 21 diverse rendering tasks with frame counts ranging from 10 to 420 frames. The results demonstrate that our approach reduces average waiting time by 45.9% (from 29.63s to 16.02s) and cuts bottleneck-induced delays by 78% (from 41s to 9s), while maintaining optimal CPU utilization at 85% and limiting context switches to only nine occurrences. A key finding reveals that complexity, rather than frame count, is the primary driver of processing time; high-complexity tasks required significantly longer processing (averaging 238.27 seconds) compared to medium-complexity tasks (averaging 34.52 seconds), representing a 6.9-fold performance differential. Our hybrid framework effectively overcomes the primary limitations of existing algorithms: it prevents bottlenecks from large tasks (FCFS), avoids the parallelism issues of SJF, and minimizes the performance overhead from frequent switching in Round Robin. This work provides a robust foundation for intelligent resource allocation in cloud rendering environments where task demands are variable and difficult to predict, establishing that effective scheduling requires complexity-aware algorithms rather than universal approaches.

Downloads

Download data is not yet available.

References

X. Ma, S. Wang, S. Zhang, P. Yang, C. Lin, and X. Shen, “Cost-Efficient Resource Provisioning for Dynamic Requests in Cloud Assisted Mobile Edge Computing,” Ieee Transactions on Cloud Computing, vol. 9, no. 3, pp. 968–980, 2021, doi: 10.1109/tcc.2019.2903240.

C. Jin, Y. Han, Z. Deng, Y. Chen, C. Liu, and J. Huang, “Reinforcement Learning-Based Intelligent Task Scheduling for Large-Scale IoT Systems,” Wirel. Commun. Mob. Comput., vol. 2023, pp. 1–11, 2023, doi: 10.1155/2023/3660882.

Z. Du, “An Improved Method Research on Graphics and Image Processing System,” Security and Communication Networks, vol. 2022, pp. 1–8, 2022, doi: 10.1155/2022/4213597.

X. Wang and Y. Han, “Research on Cloud Native Batch Scheduler Technology,” 2023, doi: 10.1117/12.3009420.

Y. Du, T. K. S. Kumar, Y. Wang, and J. Wang, “An Investigation into Multi-Stage, Variable-Batch Scheduling Across Multiple Production Units,” Journal of engineering management and systems engineering, vol. 3, no. 1, pp. 1–20, 2024, doi: 10.56578/jemse030101.

R. M. da Silva Ferreira, M. Canesche, and J. C. Penha, “Google Colab para Ensino de Computação,” 2023, doi: 10.5753/educomp_estendido.2023.228279.

A. Wilczyński and A. Jakóbik, “Using Polymatrix Extensive Stackelberg Games in Security – Aware Resource Allocation and Task Scheduling in Computational Clouds,” Journal of Telecommunications and Information Technology, vol. 1, no. 2017, pp. 71–80, 2017, doi: 10.26636/jtit.2017.1.653.

A. Jalaluddin, E. K. Budiardjo, and K. Mahatma, “Recommendation for Scrum-Based Software Development Process with Scrum at Scale: A Case Study of Software House XYZ,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 8, no. 3, pp. 401–412, 2024, doi: 10.29207/resti.v8i3.5646.

N. T. Muay, E. Sediyono, and J. Tambotoh, “Integration Waterfall and Scrum Methodology in The Development of SIMARGA Web Application,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 8, no. 2, pp. 223–233, 2024, doi: 10.29207/resti.v8i2.5652.

“schlably: A Python Framework for Deep Reinforcement Learning Based Scheduling Experiments,” 2023, doi: 10.48550/arxiv.2301.04182.

A. Nyporko and L. Chrpa, “Towards an Effective Framework Combining Planning and Scheduling [Extended Abstract],” Proceedings of the International Symposium on Combinatorial Search, vol. 16, pp. 173–174, 2023, doi: 10.1609/socs.v16i1.27300.

P. M. Castro, A. P. Barbosa‐Póvoa, H. A. Matos, and A. Q. Novais, “Simple Continuous-Time Formulation for Short-Term Scheduling of Batch and Continuous Processes,” Ind. Eng. Chem. Res., vol. 43, no. 1, pp. 105–118, 2003, doi: 10.1021/ie0302995.

“Deficit Round-Robin: A Second Network Calculus Analysis,” IEEE ACM Transactions on Networking, vol. 30, no. 5, pp. 2216–2230, 2022, doi: 10.1109/tnet.2022.3164772.

R. M. Al-Khatib, A. Al-Khateeb, E. Al-Daom, I. T. Al-Dagamseh, A. A. Tawalbeh, and L. Abualigah, “A New Enhanced IGBTQ-based Model for CPU Scheduling,” Applied and Computational Engineering, vol. 8, no. 1, pp. 411–417, 2023, doi: 10.54254/2755-2721/8/20230207.

P. K. Bal, S. K. Mohapatra, T. K. Das, K. Srinivasan, and Y. Hu, “A Joint Resource Allocation, Security With Efficient Task Scheduling in Cloud Computing Using Hybrid Machine Learning Techniques,” Sensors, vol. 22, no. 3, p. 1242, 2022, doi: 10.3390/s22031242.

S. Manna and K. S. P. Mudigonda, “Revitalizing the single batch environment: a ‘Quest’ to achieve fairness and efficiency,” International Journal of Computers and Applications, pp. 1–15, 2024, doi: 10.1080/1206212x.2024.2380660.

H. Singh, S. Tyagi, P. Kumar, S. S. Gill, and R. Buyya, “Metaheuristics for Scheduling of Heterogeneous Tasks in Cloud Computing Environments: Analysis, Performance Evaluation, and Future Directions,” Simul. Model. Pract. Theory, vol. 111, p. 102353, 2021, doi: 10.1016/j.simpat.2021.102353.

F. Alhaidari and T. Balharith, “Enhanced Round-Robin Algorithm in the Cloud Computing Environment for Optimal Task Scheduling,” Computers, vol. 10, no. 5, p. 63, 2021, doi: 10.3390/computers10050063.

M. Iqbal et al., “Optimizing Task Execution: The Impact of Dynamic Time Quantum and Priorities on Round Robin Scheduling,” Future Internet, vol. 15, no. 3, p. 104, 2023, doi: 10.3390/fi15030104.

Y. Zhou, T. Kelly, J. L. Wiener, and E. Anderson, “An Extended Evaluation of Two-Phase Scheduling Methods for Animation Rendering,” pp. 123–145, 2005, doi: 10.1007/11605300_6.

A. Ahmad, “Improved Round Robin CPU Scheduling Algorithm with Different Arrival Times Based on Dynamic Quantum,” JES, vol. 31, no. 4, pp. 105–115, 2022, doi: 10.33899/edusj.2022.135082.1273.

M. M. Tajwar, Md. N. Pathan, L. Hussaini, and A. Abubakar, “CPU Scheduling With a Round Robin Algorithm Based on an Effective Time Slice,” Journal of Information Processing Systems, 2017, doi: 10.3745/jips.01.0018.

E. Anderson et al., “Value-Maximizing Deadline Scheduling and Its Application to Animation Rendering,” pp. 299–308, 2005, doi: 10.1145/1073970.1074019.

S. S. Olofintuyi, T. O. Omotehinwa, and J. S. Owotogbe, “A survey of variants of round robin cpu scheduling algorithms,” vol. 4, no. 4, pp. 526–546, 2021, doi: 10.33003/FJS-2020-0404-513.

Z. A. Kerwad, B. M. algubbi, and R. mahdi baka, “Scheduling Algorithms for CPU,” vol. 27, no. 1, pp. 458–463, 2021, doi: 10.52155/IJPSAT.V27.1.3186.