Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.compilers > #3700 > unrolled thread

Paper: Retrofitting Control Flow Graphs in LLVM IR for Auto Vectorization

Back to article view | Back to comp.compilers

Contents

  Paper: Retrofitting Control Flow Graphs in LLVM IR for Auto Vectorization John R Levine <johnl@taugh.com> - 2025-10-08 17:07 -0400

#3700 — Paper: Retrofitting Control Flow Graphs in LLVM IR for Auto Vectorization

This paper says it significantly improves vector performance in GCC and
LLVM.

https://arxiv.org/abs/2510.04890

Retrofitting Control Flow Graphs in LLVM IR for Auto Vectorization

Shihan Fang, Wenxin Zheng

Modern processors increasingly rely on SIMD instruction sets, such as AVX
and RVV, to significantly enhance parallelism and computational
performance. However, production-ready compilers like LLVM and GCC often
fail to fully exploit available vectorization opportunities due to
disjoint vectorization passes and limited extensibility. Although recent
attempts in heuristics and intermediate representation (IR) designs have
attempted to address these problems, efficiently simplifying control flow
analysis and accurately identifying vectorization opportunities remain
challenging tasks.

To address these issues, we introduce a novel vectorization pipeline
featuring two specialized IR extensions: SIR, which encodes high-level
structural information, and VIR, which explicitly represents instruction
dependencies through data dependency analysis. Leveraging the detailed
dependency information provided by VIR, we develop a flexible and
extensible vectorization framework. This approach substantially improves
interoperability across vectorization passes and expands the search space
for identifying isomorphic instructions, ultimately enhancing both the
scope and efficiency of automatic vectorization. Experimental evaluations
demonstrate that our proposed vectorization pipeline achieves significant
performance improvements, delivering speedups of up to 53% and 58%
compared to LLVM and GCC, respectively.

Regards,
John Levine, johnl@taugh.com, Taughannock Networks, Trumansburg NY
Please consider the environment before reading this e-mail. https://jl.ly

[toc] | [standalone]

Back to top | Article view | comp.compilers

csiph-web