Landing: 91cc9b3402bb

Project / Subsystem

gcc / gcc

Date

2026-03-03

Author

Richard Biener

Commit

91cc9b3402bb33c1f5c9a0822ff6609aace7b670

Source

github

Perf win

Yes

Breaking

No

All attributes

project
gcc
subsystem
gcc
patch_id
commit_hash
91cc9b3402bb33c1f5c9a0822ff6609aace7b670
source_type
github
headline
Cost each BB vect live lane only once
tldr
GCC's vectorizer now costs each basic block's live lane only once, optimizing code generation for SLP trees.
author
Richard Biener
outcome
committed
performance_win
true
breaking_change
false
series_id
series_parts
[]
tags
  • optimization
  • vectorization
  • slp
  • code generation
discussion_id_link
bugzilla_pr
date
2026-03-03T00:00:00.000Z

This commit optimizes the costing of live scalar statements within basic blocks during SLP (Superword Level Parallelism) vectorization. By ensuring that each live lane is costed only once, even if it appears in multiple SLP nodes, the compiler can make more accurate decisions about which SLP node to use for code generation. This leads to more efficient vectorization and potentially improved performance.