Landing: c3c082917c72

← All landings

Project / Subsystem

gcc / tree-optimization

Date

2026-08-21

Author

Richard Biener

Commit

c3c082917c72ccf2928a39dc5e54a65245f46568

Source

github

Perf win

Breaking

View on GitHub →

All attributes

project: gcc
subsystem: tree-optimization
patch_id: —
commit_hash: c3c082917c72ccf2928a39dc5e54a65245f46568
source_type: github
headline: Fix SLP pattern representative checks for VEC_PERM nodes.
tldr: Corrects SLP vectorization by properly handling VEC_PERM nodes in pattern comparisons.
author: Richard Biener
outcome: committed
performance_win: false
breaking_change: false
series_id: —
series_parts: []
tags: • optimization
• vectorization
• SLP
discussion_id_link: —
bugzilla_pr: —
url: https://github.com/gcc-mirror/gcc/commit/c3c082917c72ccf2928a39dc5e54a65245f46568
date: 2026-08-21T00:00:00.000Z

This commit fixes an issue in the SLP (Superword Level Parallelism) vectorization pass where comparisons of complex nodes failed due to improper handling of VEC_PERM nodes. When these nodes still had a representative, the comparison logic incorrectly used arbitrary operations, leading to incorrect vectorization decisions. The fix ensures that VEC_PERM nodes are special-cased, preventing erroneous comparisons and improving the accuracy of vectorization.