Landing: 70ebcf89f853
Project / Subsystem
gcc / aarch64
Date
2026-08-13
Author
Kyrylo Tkachov
Commit
70ebcf89f8534fe410163415f18c527b7b694b0b
Source
github
Perf win
Yes
Breaking
No
All attributes
- project
- gcc
- subsystem
- aarch64
- patch_id
- —
- commit_hash
- 70ebcf89f8534fe410163415f18c527b7b694b0b
- source_type
- github
- headline
- aarch64: Use SVE SPLICE for scalable recurrences
- tldr
- Vectorizer now recognizes and uses the SVE SPLICE instruction for scalable recurrences, improving code generation for certain patterns.
- author
- Kyrylo Tkachov
- outcome
- committed
- performance_win
- true
- breaking_change
- false
- series_id
- —
- series_parts
- []
- tags
-
- • aarch64
- • vectorization
- • SVE
- • optimization
- discussion_id_link
- —
- bugzilla_pr
- —
- date
- 2026-08-13T00:00:00.000Z
The vectorizer can now represent first-order recurrences as scalable permutations, specifically recognizing the two-input permutation pattern. It builds a predicate for D elements and uses the SVE SPLICE instruction. This change improves code generation by utilizing specialized hardware instructions, as demonstrated by a before-and-after assembly comparison showing more efficient code for a recurrence loop.