9874

DistCL: A Framework for the Distributed Execution of OpenCL Kernels

Tahir Diopy, Steven Gurfinkel, Jason Anderson, Natalie Enright Jerger
Department of Electrical and Computer Engineering, University of Toronto, Ontario, Canada
International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS), 2013

@article{diop2013distcl,

   title={DistCL: A Framework for the Distributed Execution of OpenCL Kernels},

   author={Diop, Tahir and Gurfinkel, Steven and Anderson, Jason and Jerger, Natalie Enright},

   year={2013}

}

Download Download (PDF)   View View   Source Source   

2314

views

GPUs are used to speed up many scientific computations; however, to use several networked GPUs concurrently, the programmer must explicitly partition work and transmit data between devices. We propose DistCL, a novel framework that distributes the execution of OpenCL kernels across a GPU cluster. DistCL makes multiple distributed compute devices appear to be a single compute device. DistCL abstracts and manages many of the challenges associated with distributing a kernel across multiple devices including: (1) partitioning work into smaller parts, (2) scheduling these parts across the network, (3) partitioning memory so that each part of memory is written to by at most one device, and (4) tracking and transferring these parts of memory. Converting an OpenCL application to DistCL is straightforward and requires little programmer effort. This makes it a powerful and valuable tool for exploring the distributed execution of OpenCL kernels. We compare DistCL to SnuCL, which also facilitates the distribution of OpenCL kernels. We also give some insights: distributed tasks favor more compute bound problems and favour large contiguous memory accesses. DistCL achieves a maximum speedup of 29.1 and average speedups of 7.3 when distributing kernels among 32 peers over an Infiniband cluster.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: