Optimizing Sparse Matrix-Matrix Multiplication for the GPU

Steven Dalton, Nathan Bell, Luke N. Olson
Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL 61801
University of Illinois at Urbana-Champaign, Technical Report, 2013


   title={Optimizing Sparse Matrix-Matrix Multiplication for the GPU},

   author={Dalton, Steven and Bell, Nathan and Olson, Luke N},





Download Download (PDF)   View View   Source Source   



Sparse matrix-matrix multiplication (SpMM) is a key operation in numerous areas from information to the physical sciences. Implementing SpMM efficiently on throughput-oriented processors, such as the graphics processing unit (GPU), requires the programmer to expose substantial fine-grained parallelism while conserving the limited off-chip memory bandwidth. Balancing these concerns, we decompose the SpMM operation into three, highly-parallel phases: expansion, sorting, and compression, and introduce a set of complementary bandwidth-saving performance optimizations. Our implementation is fully general and our optimizations lead to substantial efficiencies for a SpMM product.
No votes yet.
Please wait...

Recent source codes

* * *

* * *

HGPU group © 2010-2018 hgpu.org

All rights belong to the respective authors

Contact us: