6484

GROPHECY: GPU performance projection from CPU code skeletons

Jiayuan Meng, Vitali A. Morozov, Kalyan Kumaran, Venkatram Vishwanath, Thomas D. Uram
Argonne National Laboratory
Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis (SC ’11), 2011

@inproceedings{meng2011grophecy,

   title={GROPHECY: GPU performance projection from CPU code skeletons},

   author={Meng, J. and Morozov, V.A. and Kumaran, K. and Vishwanath, V. and Uram, T.D.},

   booktitle={Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis},

   pages={14},

   year={2011},

   organization={ACM}

}

Download Download (PDF)   View View   Source Source   

1942

views

We propose GROPHECY, a GPU performance projection framework that can estimate the performance benefit of GPU acceleration without actual GPU programming or hardware. Users need only to skeletonize pieces of CPU code that are targets for GPU acceleration. Code skeletons are automatically transformed in various ways to mimic tuned GPU codes with characteristics resembling real implementations. The synthesized characteristics are used by an existing analytical model to project GPU performance. The cost and benefit of GPU development can then be estimated according to the transformed code skeleton that yields the best projected performance. With GROPHECY, users can leap toward GPU acceleration only when the cost-benefit makes sense. The framework is validated using kernel benchmarks and data-parallel codes in legacy scientific applications. The measured performance of manually tuned codes deviates from the projected performance by 17% in geometric mean.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: