Landing: d7bd302654fa

← All landings

Project / Subsystem

gcc / vect

Date

2026-10-02

Author

Tamar Christina

Commit

d7bd302654fab2ddd8d7e8539f163db63a2f07e5

Source

github

Perf win

Breaking

View on GitHub →

All attributes

project: gcc
subsystem: vect
patch_id: —
commit_hash: d7bd302654fab2ddd8d7e8539f163db63a2f07e5
source_type: github
headline: vect: Fix scalar iteration bounds for alignment peeling with partial vectors
tldr: Corrects scalar loop bounds calculation during alignment peeling to prevent underflow with partial vectors.
author: Tamar Christina
outcome: committed
performance_win: false
breaking_change: false
series_id: —
series_parts: []
tags: • vectorization
• RISC-V
• loop optimization
discussion_id_link: —
bugzilla_pr: —
url: https://github.com/gcc-mirror/gcc/commit/d7bd302654fab2ddd8d7e8539f163db63a2f07e5
date: 2026-10-02T00:00:00.000Z

A bug in the vectorization pass could cause scalar iteration bounds to underflow when alignment peeling was combined with partial vector execution, particularly on RISC-V. This fix ensures correct calculation of remaining iterations, preventing incorrect loop behavior and potential crashes.