Landing: 09021961ea02

Project / Subsystem

gcc / vect

Date

2026-07-08

Author

Tamar Christina

Commit

09021961ea027196cafca0d0308fd7c5e997bff8

Source

github

Perf win

Yes

Breaking

No

All attributes

project
gcc
subsystem
vect
patch_id
commit_hash
09021961ea027196cafca0d0308fd7c5e997bff8
source_type
github
headline
Unshare header computation for more CSE in vectorized loops
tldr
Vectorization now shares address computations between scalar and vector code for better common subexpression elimination.
author
Tamar Christina
outcome
committed
performance_win
true
breaking_change
false
series_id
series_parts
[]
tags
  • vect
  • optimization
  • cse
discussion_id_link
bugzilla_pr
date
2026-07-08T00:00:00.000Z

This patch improves vectorization by delaying the folding of offsets into base addresses. By keeping base addresses separate, the compiler can perform more common subexpression elimination (CSE) in the pre-header of vectorized loops, reducing instruction count and improving performance.