Scalability analysis of matrix-matrix multiplication on heterogeneous clusters

The paper is devoted to scalability analysis of a typical linear algebra algorithm on heterogeneous clusters. We proof that traditional scalability metrics proposed for analysis of linear algebra algorithms is applicable on heterogeneous platform and investigate influence of three heterogeneous strategies of computation distribution to scalable universal matrix multiplication algorithm (SUMMA) scalability.

[1]  Luis Pastor,et al.  An efficiency and scalability model for heterogeneous clusters , 2001, Proceedings 42nd IEEE Symposium on Foundations of Computer Science.

[2]  Alexey Kalinov,et al.  Multidimensional Static Block Data Decomposition for Heterogeneous Clusters , 2003, PPAM.

[3]  Robert A. van de Geijn,et al.  SUMMA: scalable universal matrix multiplication algorithm , 1995, Concurr. Pract. Exp..

[4]  Yves Robert,et al.  A Proposal for a Heterogeneous Cluster ScaLAPACK (Dense Linear Solvers) , 2001, IEEE Trans. Computers.

[5]  Alexey L. Lastovetsky,et al.  mpC + ScaLAPACK = Efficient Solving Linear Algebra Problems on Heterogeneous Networks , 1999, Euro-Par.

[6]  Yves Robert,et al.  Matrix Multiplication on Heterogeneous Platforms , 2001, IEEE Trans. Parallel Distributed Syst..

[7]  Robert A. van de Geijn,et al.  Scalability Issues Affecting the Design of a Dense Linear Algebra Library , 1994, J. Parallel Distributed Comput..

[8]  Alexey L. Lastovetsky,et al.  Heterogeneous Distribution of Computations While Solving Linear Algebra Problems on Networks of Heterogeneous Computers , 1999, HPCN Europe.

[9]  Alexey L. Lastovetsky,et al.  Heterogeneous Distribution of Computations Solving Linear Algebra Problems on Networks of Heterogeneous Computers , 2001, J. Parallel Distributed Comput..

[10]  Alexey Kalinov,et al.  Natural block data decomposition for heterogeneous clusters , 2003, Proceedings International Parallel and Distributed Processing Symposium.

[11]  Robert A. van de Geijn,et al.  SUMMA: Scalable Universal Matrix Multiplication Algorithm , 1995 .

[12]  Yong Yan,et al.  Modeling and characterizing parallel computing performance on heterogeneous networks of workstations , 1995, Proceedings.Seventh IEEE Symposium on Parallel and Distributed Processing.

[13]  Vipin Kumar,et al.  Isoefficiency: measuring the scalability of parallel algorithms and architectures , 1993, IEEE Parallel & Distributed Technology: Systems & Applications.