Managing code transformations for better performance portability

Thiago S.F.X. Teixeira, William Gropp, David Padua

Research output: Contribution to journalArticlepeer-review

Abstract

Code optimization is an intricate task that is getting more complex as computing systems evolve. Managing the program optimization process, including the implementation and evaluation of code variants, is tedious, inefficient, and errors are likely to be introduced in the process. Moreover, because each platform typically requires a different sequence of transformations to fully harness its computing power, the optimization process complexity grows as new platforms are adopted. To address these issues, systems and frameworks have been proposed to automate the code optimization process. They, however, have not been widely adopted and are primarily used by experts with deep knowledge about underlying architecture and compiler intricacies. This article describes the requirements that we believe necessary for making automatic performance tuning more broadly used, especially in complex, long-lived high-performance computing applications. Besides discussing limitations of current systems and strategies to overcome these, we describe the design of a system that is able to semi-automatically generate efficient platform-specific code. In the proposed system, the code optimization is programmer-guided, separately from application code, on an external file in what we call optimization programming. The language to program the optimization process is able to represent complex collections of transformations and, as a result, generate efficient platform-specific code. A database manages different optimized versions of code regions, providing a pragmatic approach to performance portability, and the framework itself has separate components, allowing the optimized code to be used on systems without installing all of the modules required for the code generation. We present experiments on two different platforms to illustrate the generation of efficient platform-specific code that performs comparable to hand-optimized, vendor-provided code.

Original languageEnglish (US)
Pages (from-to)1290-1306
Number of pages17
JournalInternational Journal of High Performance Computing Applications
Volume33
Issue number6
DOIs
StatePublished - Nov 1 2019

Keywords

  • Code generation
  • compilers
  • domain-specific language
  • high-performance computing
  • optimization

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture

Fingerprint Dive into the research topics of 'Managing code transformations for better performance portability'. Together they form a unique fingerprint.

Cite this