A Novel Heterogeneous Multi-GPU Parallel Rendering Framework in UE4 Scene

被引:0
|
作者
Zhang, Siyu [1 ]
Wang, Yanfeng [1 ]
Guo, Jianjun [1 ]
机构
[1] Beijing Weiling Times Technol Co Ltd, Beiijng, Peoples R China
关键词
Parallel rendering; UE4; heterogeneous; Multi-adapters;
D O I
暂无
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Parallel rendering of heterogeneous multi-GPU in UE4 scene can be realized by explicitly calling graphics API, instead of relying on hardware limitations or drivers. Dual GPUs can bring better performance improvement. In this paper, we mainly design a novel multi-thread rendering framework in UE4 scene, which has a better improvement in performance. Under the current multi-GPU implementation, we have expanded the multithreading architecture and added a new RHI Thread, which we call MRHI Thread, to handle the rendering instruction operation for the newly added GPU. Then, in the design of rendering architecture, rendering objects are divided into U Object main thread logic component object, F Render Object rendering thread object, and FRHI Render Object RHI thread object. Moreover, Because the requirement is to render two scenes, the Scene Capture component is used as the entrance of GPU1 rendering. In the test, we used two Nvida RTX3070, and realized parallel rendering of two GPUs. The performance improved by 150-160%, and the parallel efficiency was close to 95%. Under our proposed framework, the parallel efficiency of the GPU will be greatly improved compared with the previous version.
引用
收藏
页码:133 / 144
页数:12
相关论文
共 50 条
  • [31] A Massively Parallel and Scalable Multi-GPU Material Point Method
    Wang, Xinlei
    Qiu, Yuxing
    Slattery, Stuart R.
    Fang, Yu
    Li, Minchen
    Zhu, Song-Chun
    Zhu, Yixin
    Tang, Min
    Manocha, Dinesh
    Jiang, Chenfanfu
    ACM TRANSACTIONS ON GRAPHICS, 2020, 39 (04):
  • [32] Performance Analysis of Parallel FFT on Large Multi-GPU Systems
    Ayala, Alan
    Tomov, Stan
    Stoyanov, Miroslav
    Haidar, Azzam
    Dongarra, Jack
    2022 IEEE 36TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW 2022), 2022, : 372 - 381
  • [33] HPSM: A Programming Framework for Multi-CPU and Multi-GPU Systems
    Lima, Joao V. F.
    Di Domenico, Daniel
    2017 INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND HIGH PERFORMANCE COMPUTING WORKSHOPS (SBAC-PADW), 2017, : 31 - 36
  • [34] Multi-CPU/Multi-GPU Based Framework for Multimedia Processing
    Mahmoudi, Sidi Ahmed
    Manneback, Pierre
    COMPUTER SCIENCE AND ITS APPLICATIONS, CIIA 2015, 2015, 456 : 54 - 65
  • [35] Strategies for maximizing utilization on multi-CPU and multi-GPU heterogeneous architectures
    Angeles Navarro
    Antonio Vilches
    Francisco Corbera
    Rafael Asenjo
    The Journal of Supercomputing, 2014, 70 : 756 - 771
  • [36] Multi-GPU multi-display rendering of extremely large 3D environments
    Dong, Yangzi
    Peng, Chao
    VISUAL COMPUTER, 2023, 39 (12): : 6473 - 6489
  • [37] PARTANS: An Autotuning Framework for Stencil Computation on Multi-GPU Systems
    Lutz, Thibaut
    Fensch, Christian
    Cole, Murray
    ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION, 2013, 9 (04)
  • [38] Multi-GPU multi-display rendering of extremely large 3D environments
    Yangzi Dong
    Chao Peng
    The Visual Computer, 2023, 39 : 6473 - 6489
  • [39] Strategies for maximizing utilization on multi-CPU and multi-GPU heterogeneous architectures
    Navarro, Angeles
    Vilches, Antonio
    Corbera, Francisco
    Asenjo, Rafael
    JOURNAL OF SUPERCOMPUTING, 2014, 70 (02): : 756 - 771
  • [40] A Multi-GPU Framework for In-Memory Text Data Analytics
    Chong, Poh Kit
    Karuppiah, Ettikan K.
    Yong, Keh Kok
    2013 IEEE 27TH INTERNATIONAL CONFERENCE ON ADVANCED INFORMATION NETWORKING AND APPLICATIONS WORKSHOPS (WAINA), 2013, : 1411 - 1416