Using recursion to boost ATLAS's performance

Authors:
Paolo D'Alberto;Alexandru Nicolau
Affiliations:
Department of Electrical and Computer Engineering, Carnegie Mellon University;Department of Computer Science, University of California at Irvine
Venue:
ISHPC'05/ALPS'06 Proceedings of the 6th international symposium on high-performance computing and 1st international conference on Advanced low power systems
Year:
2005

Citing 11
Cited 2

Matrix multiplication via arithmetic progressions

STOC '87 Proceedings of the nineteenth annual ACM symposium on Theory of computing
A Strassen-Newton algorithm for high-speed parallelizable matrix inversion

Proceedings of the 1988 ACM/IEEE conference on Supercomputing
Exploiting fast matrix multiplication within the level 3 BLAS

ACM Transactions on Mathematical Software (TOMS)
Optimizing matrix multiply using PHiPAC: a portable, high-performance, ANSI C coding methodology

ICS '97 Proceedings of the 11th international conference on Supercomputing
Auto-blocking matrix-multiplication or tracking BLAS3 performance from source code

PPOPP '97 Proceedings of the sixth ACM SIGPLAN symposium on Principles and practice of parallel programming
GEMM-based level 3 BLAS: high-performance model implementations and performance evaluation benchmark

ACM Transactions on Mathematical Software (TOMS)
Algorithm 784: GEMM-based level 3 BLAS: portability and optimization issues

ACM Transactions on Mathematical Software (TOMS)
Implementation of Strassen's algorithm for matrix multiplication

Supercomputing '96 Proceedings of the 1996 ACM/IEEE conference on Supercomputing
Tuning Strassen's matrix multiplication for memory efficiency

SC '98 Proceedings of the 1998 ACM/IEEE conference on Supercomputing
Automatically tuned linear algebra software

SC '98 Proceedings of the 1998 ACM/IEEE conference on Supercomputing
Algorithms for matrix multiplication

Algorithms for matrix multiplication

Adaptive Strassen's matrix multiplication

Proceedings of the 21st annual international conference on Supercomputing
Adaptive Winograd's matrix multiplications

ACM Transactions on Mathematical Software (TOMS)

Quantified Score

Hi-index	0.00

Visualization

Abstract

We investigate the performance benefits of a novel recursive formulation of Strassen's algorithm over highly tuned matrix-multiply (MM) routines, such as the widely used ATLAS for high-performance systems. We combine Strassen's recursion with high-tuned version of ATLAS MM and we present a family of recursive algorithms achieving up to 15% speed-up over ATLAS alone. We show experimental results for 7 different systems.