arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.10463cs.AR
收藏

XR工作负载的架构分类:跨层范式及其影响

Architectural Classification of XR Workloads: Cross-Layer Archetypes and Implications

Xinyu Shi, Simei Yang, Francky Catthoor

AI总结:

本文提出了一种跨层方法对XR工作负载进行架构分类,提炼出关键架构范式,并为下一代XR SoC提供了设计指导。

摘要:

增强现实和虚拟现实的边缘和移动平台,统称为扩展现实(XR),必须在严格功率和面积约束下提供确定性的超低延迟性能。然而,XR工作负载的多样性正在迅速增加,其特点是异构的操作符类型和复杂的数据流结构。这种趋势对以卷积神经网络(CNN)为中心的传统加速器架构构成了重大挑战,导致传统以计算为中心的优化策略效益递减。尽管这个问题的重要性,但对完整XR流水线的系统架构理解仍然缺乏。在本文中,我们通过一种跨层方法对XR工作负载进行架构分类,该方法将基于模型的高层设计空间探索(DSE)与在商业GPU和CPU硬件上的实证分析相结合。通过分析涵盖12种不同XR内核的一组代表性工作负载,我们将它们复杂的架构特性提炼为一小组跨层工作负载范式(例如,容量受限和开销敏感)。基于这些范式,我们进一步提取了关键的架构洞察,并为下一代XR SoC提供了可操作的设计指南。我们的研究强调,XR架构设计必须从通用资源扩展转向面向阶段的调度和弹性资源分配,以在未来的XR系统中实现更高的能效和高性能。

英文摘要:

Edge and mobile platforms for augmented and virtual reality, collectively referred to as extended reality (XR) must deliver deterministic ultra-low-latency performance under stringent power and area constraints. However, the diversity of XR workloads is rapidly increasing, characterized by heterogeneous operator types and complex dataflow structures. This trend poses significant challenges to conventional accelerator architectures centered around convolutional neural networks (CNNs), resulting in diminishing returns for traditional compute-centric optimization strategies. Despite the importance of this problem, a systematic architectural understanding of the full XR pipeline remains lacking. In this paper, we present an architectural classification of XR workloads using a cross-layer methodology that integrates model-based high-level design space exploration (DSE) with empirical profiling on commercial GPU and CPU hardware. By analyzing a representative set of workloads spanning 12 distinct XR kernels, we distill their complex architectural characteristics into a small set of cross-layer workload archetypes (e.g., capacity-limited and overhead-sensitive). Building on these archetypes, we further extract key architectural insights and provide actionable design guidelines for next-generation XR SoCs. Our study highlights that XR architecture design must shift from generic resource scaling toward phase-aware scheduling and elastic resource allocation in order to achieve greater energy efficiency and high performance in future XR systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑