goSLP: Globally Optimized Superword Level Parallelism Framework
Abstract
Modern microprocessors are equipped with single instruction multiple data (SIMD) or vector instruction sets which allow compilers to exploit superword level parallelism (SLP), a type of fine-grained parallelism. Current SLP auto-vectorization techniques use heuristics to discover vectorization opportunities in high-level language code. These heuristics are fragile, local and typically only present one vectorization strategy that is either accepted or rejected by a cost model. We present goSLP, a novel SLP auto-vectorization framework which solves the statement packing problem in a pairwise optimal manner. Using an integer linear programming (ILP) solver, goSLP searches the entire space of statement packing opportunities for a whole function at a time, while limiting total compilation time to a few minutes. Furthermore, goSLP optimally solves the vector permutation selection problem using dynamic programming. We implemented goSLP in the LLVM compiler infrastructure, achieving a geometric mean speedup of 7.58% on SPEC2017fp, 2.42% on SPEC2006fp and 4.07% on NAS benchmarks compared to LLVM's existing SLP auto-vectorizer.
- Publication:
-
arXiv e-prints
- Pub Date:
- April 2018
- DOI:
- 10.48550/arXiv.1804.08733
- arXiv:
- arXiv:1804.08733
- Bibcode:
- 2018arXiv180408733M
- Keywords:
-
- Computer Science - Programming Languages;
- Computer Science - Distributed;
- Parallel;
- and Cluster Computing
- E-Print:
- Published at OOPSLA 2018