Landing: 2f389cf7ac91
Project / Subsystem
gcc / aarch64
Date
2026-09-23
Author
Tamar Christina
Commit
2f389cf7ac917207f93103cf7f955432580681d1
Source
github
Perf win
Yes
Breaking
No
All attributes
- project
- gcc
- subsystem
- aarch64
- patch_id
- —
- commit_hash
- 2f389cf7ac917207f93103cf7f955432580681d1
- source_type
- github
- headline
- Cost SAD and ABD reductions accurately for AArch64 SIMD vs SVE.
- tldr
- AArch64 cost model now reflects the true performance of SAD/ABD reductions for Adv.SIMD and SVE.
- author
- Tamar Christina
- outcome
- committed
- performance_win
- true
- breaking_change
- false
- series_id
- —
- series_parts
- []
- tags
-
- • aarch64
- • optimization
- • cost model
- • vectorization
- discussion_id_link
- —
- bugzilla_pr
- —
- date
- 2026-09-23T00:00:00.000Z
The AArch64 backend’s cost model has been updated to accurately reflect the performance of Signed Absolute Difference (SAD) and Absolute Difference (ABD) reduction operations. This change accounts for extra work required by Adv.SIMD for 128-bit vectors and the more efficient SVE approach using udot, ensuring the compiler makes better vectorization and instruction selection decisions.