CoreTSAR: Task Scheduling for Accelerator-aware Runtimes

Thomas R. W. Scogland, Wu-chun Feng, Barry Rountree, Bronis R. de Supinski
Department of Computer Science, Virginia Tech, Blacksburg, VA 24060 USA
Virginia Tech., Technical Report TR-12-20, 2012


   title={CoreTSAR: Task Scheduling for Accelerator-aware Runtimes},

   author={Scogland, T.R.W. and Feng, W. and Rountree, B. and de Supinski, B.R.},



Download Download (PDF)   View View   Source Source   



Heterogeneous supercomputers that incorporate computational accelerators such as GPUs are increasingly popular due to their high peak performance, energy efficiency and comparatively low cost. Unfortunately, the programming models and frameworks designed to extract performance from all computational units still lack the flexibility of their CPU-only counterparts. Accelerated OpenMP improves this situation by supporting natural migration of OpenMP code from CPUs to a GPU. However, these implementations currently lose one of OpenMP’s best features, its flexibility: typical OpenMP applications can run on any number of CPUs. GPU implementations do not transparently employ multiple GPUs on a node or a mix of GPUs and CPUs. To address these shortcomings, we present CoreTSAR, our runtime library for dynamically scheduling tasks across heterogeneous resources, and propose straightforward extensions that incorporate this functionality into Accelerated OpenMP. We show that our approach can provide nearly linear speedup to four GPUs over only using CPUs or one GPU while increasing the overall flexibility of Accelerated OpenMP.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: