Dissecting the CUDA scheduling hierarchy: a Performance and Predictability Perspective
Dissecting the CUDA scheduling hierarchy: a Performance and Predictability Perspective
复制标题
剖析 CUDA 调度层次结构：性能和可预测性视角
DOI：
10.1109/rtas48715.2020.000-5
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
M. Bertogna
中科院分区：
文献类型：
--
作者：
Ignacio Sañudo Olmedo;Nicola Capodieci;Jorge Martinez;A. Marongiu;M. Bertogna
在过去的几年里，图形处理单元（GPU）在安全相关领域的使用不断增加，在实时社区中开辟了许多研究问题。例如，NVIDIA GPU中部署的调度机制的封闭性和专有性是为延迟敏感型应用程序进行适当的可扩展性分析的主要障碍。现有文献通过以下方式解决这些问题：（i）为异构CPUGPU系统及其相关调度策略提供简化模型，或（ii）提供通过逆向工程获得的有关这些仲裁机制的见解。在本文中，我们更进一步，纠正和巩固了先前发表的关于NVIDIA GPU及其专有CUDA应用程序编程接口的分层调度策略的假设。我们还讨论了这种机制如何演变与最近发布的GPU微架构，以及这些变化如何影响调度模型被实时系统工程师利用。
Over the last few years, the ever-increasing use of Graphic Processing Units (GPUs) in safety-related domains has opened up many research problems in the real-time community. The closed and proprietary nature of the scheduling mechanisms deployed in NVIDIA GPUs, for instance, represents a major obstacle in deriving a proper schedulability analysis for latency-sensitive applications. Existing literature addresses these issues by either (i) providing simplified models for heterogeneous CPUGPU systems and their associated scheduling policies, or (ii) providing insights about these arbitration mechanisms obtained through reverse engineering. In this paper, we take one step further by correcting and consolidating previously published assumptions about the hierarchical scheduling policies of NVIDIA GPUs and their proprietary CUDA application programming interface. We also discuss how such mechanisms evolved with recently released GPU micro-architectures, and how such changes influence the scheduling models to be exploited by real-time system engineers.
DOI：
10.4230/lipics.ecrts.2018.20
发表时间：
2018-06
期刊：
--
影响因子：
--
作者：
Ming Yang;Nathan Otterness;Tanya Amert;Joshua Bakita;James H. Anderson;F. D. Smith
通讯作者：
Ming Yang;Nathan Otterness;Tanya Amert;Joshua Bakita;James H. Anderson;F. D. Smith