15742

A Unified, Hardware-Fitted, Cross-GPU Performance Model

James Stevens, Andreas Klockner
Department of Computer Science, University of Illinois at Urbana-Champaign
arXiv:1604.04997 [cs.PF], (18 Apr 2016)

@article{stevens2016unified,

   title={A Unified, Hardware-Fitted, Cross-GPU Performance Model},

   author={Stevens, James and Klockner, Andreas},

   year={2016},

   month={apr},

   archivePrefix={"arXiv"},

   primaryClass={cs.PF}

}

Download Download (PDF)   View View   Source Source   

1480

views

We present a mechanism to symbolically gather performance-relevant operation counts from numerically-oriented subprograms (‘kernels’) expressed in the Loopy programming system, and apply these counts in a simple, linear model of kernel run time. We use a series of ‘performance-instructive’ kernels to fit the parameters of a unified model to the performance characteristics of GPU hardware from multiple hardware generations and vendors. We evaluate the predictive power of the model on a broad array of computational kernels relevant to scientific computing. In terms of the geometric mean, our simple, vendor- and GPU-type-independent model achieves relative accuracy comparable to that of previously published work using hardware specific models.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: