Revec: Program rejuvenation through revectorization

Charith Mendis, Ajay Jain, Paras Jain, Saman Amarasinghe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Modern microprocessors are equipped with Single Instruction Multiple Data (SIMD) or vector instructions which expose data level parallelism at a fine granularity. Programmers exploit this parallelism by using low-level vector intrinsics in their code. However, once programs are written using vector intrinsics of a specific instruction set, the code becomes non-portable. Modern compilers are unable to analyze and retarget the code to newer vector instruction sets. Hence, programmers have to manually rewrite the same code using vector intrinsics of a newer generation to exploit higher data widths and capabilities of new instruction sets. This process is tedious, error-prone and requires maintaining multiple code bases. We propose Revec, a compiler optimization pass which revectorizes already vectorized code, by retargeting it to use vector instructions of newer generations. The transformation is transparent, happening at the compiler intermediate representation level, and enables performance portability of hand-vectorized code. Revec can achieve performance improvements in real-world performance critical kernels. In particular, Revec achieves geometric mean speedups of 1.160× and 1.430× on fast integer unpacking kernels, and speedups of 1.145× and 1.195× on hand-vectorized x265 media codec kernels when retargeting their SSE-series implementations to use AVX2 and AVX-512 vector instructions respectively. We also extensively test Revec’s impact on 216 intrinsic-rich implementations of image processing and stencil kernels relative to hand-retargeting.

Original languageEnglish (US)
Title of host publicationCC 2019 - Proceedings of the 28th International Conference on Compiler Construction
EditorsMilind Kulkarni, J. Nelson Amaral
PublisherAssociation for Computing Machinery
Pages29-41
Number of pages13
ISBN (Electronic)9781450362771
DOIs
StatePublished - Feb 16 2019
Externally publishedYes
Event28th International Conference on Compiler Construction, CC 2019 - Washington, United States
Duration: Feb 16 2019Feb 17 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference28th International Conference on Compiler Construction, CC 2019
Country/TerritoryUnited States
CityWashington
Period2/16/192/17/19

Keywords

  • Optimizing compilation
  • Program rejuvenation
  • Single Instruction Multiple Data (SIMD)
  • Vectorization

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Revec: Program rejuvenation through revectorization'. Together they form a unique fingerprint.

Cite this