7842

Automatic Optimization of In-Flight Memory Transactions for GPU Accelerators based on a Domain-Specific Language for Medical Imaging

Richard Membarth, Frank Hannig, Jurgen Teich, Mario Korner, Wieland Eckert
Department of Computer Science, University of Erlangen-Nuremberg, Germany
11th International Symposium on Parallel and Distributed Computing (ISPDC), 2012

@conference{membarth2012aoi,

   author={Membarth, Richard and Hannig, Frank and Teich, J{"u}rgen and K{"o}rner, Mario and Eckert, Wieland},

   address={Munich, Germany},

   booktitle={Proceedings of the 11th International Symposium on Parallel and Distributed Computing (ISPDC)},

   title={Automatic Optimization of In-Flight Memory Transactions for GPU Accelerators based on a Domain-Specific Language for Medical Imaging},

   year={2012},

   month={jun},

   date={2012-06-25/2012-06-29},

   organization={IEEE}

}

An efficient memory bandwidth utilization for GPU accelerators is crucial for memory bound applications. In medical imaging, the performance of many kernels is limited by the available memory bandwidth since only a few operations are performed per pixel. For such kernels only a fraction of the compute power provided by GPU accelerators can be exploited and performance is predetermined by memory bandwidth. As a remedy, this paper investigates the optimal utilization of available memory bandwidth by means of increasing in-flight memory transactions. Instead of doing this manually for different GPU accelerators, the required CUDA and OpenCL code is automatically generated from descriptions in a Domain-Specific Language (DSL) for the considered application domain. Moreover, the DSL is extended to also support global reduction operators. We show that the generated target-specific code improves bandwidth utilization for memory-bound kernels significantly. Moreover, competitive performance compared to the GPU back end of the widely used image processing library OpenCV can be achieved.
No votes yet.
Please wait...

Recent source codes

* * *

* * *

HGPU group © 2010-2018 hgpu.org

All rights belong to the respective authors

Contact us: