Automatic Virtualization of Accelerators

Hangchen Yu, Arthur Peters, Amogh Akshintala, Christopher J. Rossbach
The University of Texas at Austin
17th Workshop on Hot Topics in Operating Systems (HotOS XVII), 2019


   title={Automatic Virtualization of Accelerators},

   author={Yu, Hangchen and Peters, Arthur M and Akshintala, Amogh and Rossbach, Christopher J},



Download Download (PDF)   View View   Source Source   



Applications are migrating en masse to the cloud, while accelerators such as GPUs, TPUs, and FPGAs proliferate in the wake of Moore’s Law. These technological trends are incompatible. Cloud applications run on virtual platforms, but traditional I/O virtualization techniques have not provided production-ready solutions for accelerators. As a result, cloud providers expose accelerators by using pass-through techniques which dedicate physical devices to individual guests. The multi-tenancy that drives their business is lost as a consequence. This paper proposes automatic generation of virtual accelerator stacks to address the fundamental tradeoffs between virtualization properties and techniques for accelerators. AvA (Automatic Virtualization of Accelerators) repurposes a para-virtual I/O stack design based on API remoting to present virtual accelerator APIs to guest VMs. Conventional wisdom is that API remoting sacrifices interposition and compatibility. AvA forwards invocations over hypervisor-managed transport to recover interposition. AvA compensates for lost compatibility by automatically generating guest libraries, drivers, hypervisor-level schedulers, and API servers. AvA supports pluggable transport layers, allowing VMs to use disaggregated accelerators. With AvA, a single developer could virtualize a core subset of OpenCL at near-native performance in just a few days.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: