Exploiting SPMD Horizontal Locality

Chunyang Gou, Georgi Gaydadjiev
Delft University of Technology, Delft
IEEE Computer Architecture Letters, Volume 10 Issue 1, January 2011


   title={Exploiting SPMD Horizontal Locality},

   author={Gou, C. and Gaydadjiev, G.},

   journal={IEEE Computer Architecture Letters},





   publisher={IEEE Computer Society}


Source Source   



In this paper, we analyze a particular spatial locality case (called horizontal locality) inherent to manycore accelerator architectures employing barrel execution of SPMD kernels, such as GPUs. We then propose an adaptive memory access granularity framework to exploit and enforce the horizontal locality in order to reduce the interferences among accelerator cores memory accesses and hence improve DRAM efficiency. With the proposed technique, DRAM efficiency grows by 1.42X on average, resulting in 12.3% overall performance gain, for a set of representative memory intensive GPGPU applications.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2019 hgpu.org

All rights belong to the respective authors

Contact us: