G10：通过智能张量迁移实现高效的统一GPU内存与存储架构
G10: Enabling An Efficient Unified GPU Memory and Storage Architecture with Smart Tensor Migrations
AI总结：
G10提出统一GPU内存与存储架构，利用编译器预测张量行为并智能调度迁移，隐藏数据传输开销，性能最高提升1.75倍，达到理想性能的90.3%。
摘要：
为了突破GPU内存墙以扩展深度学习工作负载，近年来提出了多种架构和系统技术。其典型方法包括使用闪存进行内存扩展和直接存储访问。然而，这些技术仍然存在性能次优的问题，并给GPU内存管理带来了复杂性，使其难以满足当今深度学习工作负载的可扩展性要求。在本文中，我们基于深度学习工作负载的张量行为高度可预测这一事实，提出了一种名为G10的统一GPU内存与存储架构。G10将主机内存、GPU内存和闪存集成到一个统一的内存空间中，以扩展GPU内存容量，同时实现透明的数据迁移。基于这种统一的GPU内存与存储架构，G10利用编译器技术来表征深度学习工作负载中的张量行为。因此，它可以通过考虑闪存和主机内存的可用带宽来提前调度数据迁移。深度学习编译器与统一内存架构之间的协作机制使G10能够以透明的方式隐藏数据传输开销。我们基于一个开源GPU模拟器实现了G10。我们的实验表明，G10在无需对深度学习工作负载进行代码修改的情况下，性能比最先进的GPU内存解决方案最高提升1.75倍。借助智能数据迁移机制，G10可以达到假设无限GPU内存的理想情况性能的90.3%。
英文摘要：
To break the GPU memory wall for scaling deep learning workloads, a variety of architecture and system techniques have been proposed recently. Their typical approaches include memory extension with flash memory and direct storage access. However, these techniques still suffer from suboptimal performance and introduce complexity to the GPU memory management, making them hard to meet the scalability requirement of deep learning workloads today. In this paper, we present a unified GPU memory and storage architecture named G10 driven by the fact that the tensor behaviors of deep learning workloads are highly predictable. G10 integrates the host memory, GPU memory, and flash memory into a unified memory space, to scale the GPU memory capacity while enabling transparent data migrations. Based on this unified GPU memory and storage architecture, G10 utilizes compiler techniques to characterize the tensor behaviors in deep learning workloads. Therefore, it can schedule data migrations in advance by considering the available bandwidth of flash memory and host memory. The cooperative mechanism between deep learning compilers and the unified memory architecture enables G10 to hide data transfer overheads in a transparent manner. We implement G10 based on an open-source GPU simulator. Our experiments demonstrate that G10 outperforms state-of-the-art GPU memory solutions by up to 1.75$\times$, without code modifications to deep learning workloads. With the smart data migration mechanism, G10 can reach 90.3\% of the performance of the ideal case assuming unlimited GPU memory.
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。
