Accession Number:

ADA561678

Title:

Auto-tuning the Matrix Powers Kernel with SEJITS

Descriptive Note:

Technical rept.

Corporate Author:

CALIFORNIA UNIV BERKELEY DEPT OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE

Personal Author(s):

• Morlan, Jeffrey

Report Date:

2012-05-11

Pagination or Media Count:

18.0

Abstract:

The matrix powers kernel, used in communication-avoiding Krylov subspace methods, requires runtime auto-tuning for best performance. We demonstrate how the SEJITS Selective Embedded Just-In- Time Specialization approach can be used to deliver a high-performance and performance-portable implementation of the matrix powers kernel to application authors, while separating their high-level concerns from those of auto-tuner implementers involving low-level optimizations. The benefits of delivering this kernel in the form of a specializer, rather than a traditional library, are discussed. Performance of the matrix powers kernel specializer is evaluated in the context of a communication-avoiding conjugate gradient CA-CG solver, which compares favorably to traditional CG.

Descriptors:

• *ALGORITHMS
• EIGENVALUES
• EIGENVECTORS
• LINEAR ALGEBRA
• LINEAR SYSTEMS
• PERFORMANCE(ENGINEERING)
• PROBLEM SOLVING
• SPECIALIZATION
• TIME

Subject Categories:

• Numerical Mathematics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE