Landing: 7c7ace08e4aa

← All landings

Project / Subsystem

gcc / gcc/aarch64

Date

2026-01-09

Author

Artemiy Volkov

Commit

7c7ace08e4aab91ca0ce4bbd318af181da7c460f

Source

github

Perf win

Breaking

View on GitHub →

All attributes

project: gcc
subsystem: gcc/aarch64
patch_id: —
commit_hash: 7c7ace08e4aab91ca0ce4bbd318af181da7c460f
source_type: github
headline: AArch64: Add zeroing forms for predicated SVE int-/FP-to-FP conversions
tldr: The compiler now supports zeroing predication for SVE integer/FP-to-FP conversion instructions under SVE2.2 or SME2.2 when the merge operand is a constant zero…
author: Artemiy Volkov
outcome: committed
performance_win: false
breaking_change: false
series_id: —
series_parts: []
tags: • aarch64
• sve
• sme
• intrinsics
discussion_id_link: —
bugzilla_pr: —
url: https://github.com/gcc-mirror/gcc/commit/7c7ace08e4aab91ca0ce4bbd318af181da7c460f
date: 2026-01-09T00:00:00.000Z

The compiler now supports zeroing predication for SVE integer/FP-to-FP conversion instructions under SVE2.2 or SME2.2 when the merge operand is a constant zero vector. A new alternative is added to the patterns to emit a single zeroing-predication version of an instruction when the merge operand is a constant zero vector and the sve2p2_or_sme2p2 condition holds.