Data parallel patterns on CPU/GPU mix

T. Serban, M. Danelutto, M. Coppola
Dipartimento di Informatica, Universita di Pisa
Universita di Pisa, Technical Report: TR-13-01, 2013


   title={Data parallel patterns on CPU/GPU mix},

   author={CNR–Pisa, I.},



Download Download (PDF)   View View   Source Source   



We propose a model that uses a small set of quite simple parameters to devise a proper partitioning{between CPU and GPU cores{of the tasks deriving from structured data parallel patterns/algorithmic skeletons. The model takes into account both hardware related and application dependent parameters. It eventually computes the percentage of tasks to be executed on CPU and GPU cores such that both kind of cores are exploited and performance figures are optimized. Different experimental results on state-of-the-art CPU/GPU architectures are shown that assess the model properties.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: