An Evaluation of Vectorizing Compilers
Citations Over TimeTop 10% of 2011 papers
Abstract
Most of today's processors include vector units that have been designed to speedup single threaded programs. Although vector instructions can deliver high performance, writing vector code in assembly language or using intrinsics in high level languages is a time consuming and error-prone task. The alternative is to automate the process of vectorization by using vectorizing compilers. This paper evaluates how well compilers vectorize a synthetic benchmark consisting of 151 loops, two application from Petascale Application Collaboration Teams (PACT), and eight applications from Media Bench II. We evaluated three compilers: GCC (version 4.7.0), ICC (version 12.0) and XLC (version 11.01). Our results show that despite all the work done in vectorization in the last 40 years 45-71% of the loops in the synthetic benchmark and only a few loops from the real applications are vectorized by the compilers we evaluated.
Related Papers
- → Evaluating Auto-Vectorizing Compilers through Objective Withdrawal of Useful Information(2019)12 cited
- → Auto-vectorization for image processing DSLs(2017)7 cited
- → The Phase-Ordering Problem: An Intermediate Speedup Prediction Approach(2017)3 cited
- → Pathway to petascale---The pathway to petascale science(2006)
- Evaluation and Analysis of Effects of Auto-vectorization in Typical Compilers(2013)