Landing: 93d5e1be87ca
Project / Subsystem
gcc / aarch64
Date
2026-08-07
Author
Rohith Kapelli
Commit
93d5e1be87cab45513ac5ee524c773a6368f61d7
Source
github
Perf win
Yes
Breaking
No
All attributes
- project
- gcc
- subsystem
- aarch64
- patch_id
- —
- commit_hash
- 93d5e1be87cab45513ac5ee524c773a6368f61d7
- source_type
- github
- headline
- Optimize two-element vector lane copies on AArch64
- tldr
- Eliminates unnecessary register moves for two-element vector lane copies, fixing a performance regression.
- author
- Rohith Kapelli
- outcome
- committed
- performance_win
- true
- breaking_change
- false
- series_id
- —
- series_parts
- []
- tags
-
- • aarch64
- • vectorization
- • optimization
- • arm
- discussion_id_link
- —
- bugzilla_pr
- —
- date
- 2026-08-07T00:00:00.000Z
This commit resolves a performance regression on AArch64 where copying lanes in two-element vectors resulted in an extra register move instruction. By adding new patterns that correctly tie the destination register to the appropriate input, the compiler now generates more efficient code, reducing instructions from two to one for these operations.