Landing: 2aa3beeb892a

← All landings

Project / Subsystem

gcc / risc-v

Date

2026-01-13

Author

Pan Li

Commit

2aa3beeb892ac38ca5a7ca9e3a25b0eaab567cd5

Source

github

Perf win

Yes

Breaking

View on GitHub →

All attributes

project: gcc
subsystem: risc-v
patch_id: —
commit_hash: 2aa3beeb892ac38ca5a7ca9e3a25b0eaab567cd5
source_type: github
headline: RISC-V: Combine vec_duplicate + vmsle.vv to vmsle.vx based on GR2VR cost
tldr: GCC now combines RISC-V ``vec_duplicate`` and ``vmsle.vv`` instructions into ``vmsle.vx`` when the cost of moving data to vector registers is low enough.
author: Pan Li
outcome: committed
performance_win: true
breaking_change: false
series_id: —
series_parts: []
tags: • risc-v
• vectorization
• rvv
• optimization
discussion_id_link: —
bugzilla_pr: —
url: https://github.com/gcc-mirror/gcc/commit/2aa3beeb892ac38ca5a7ca9e3a25b0eaab567cd5
date: 2026-01-13T00:00:00.000Z

GCC now combines the vec_duplicate and vmsle.vv RISC-V vector instructions into a single vmsle.vx instruction when the cost of transferring data from general-purpose registers to vector registers (GR2VR) is sufficiently low (zero). This optimization reduces the number of instructions executed and improves performance. The compiler makes this decision based on the GR2VR cost, performing the late-combine optimization only when it’s beneficial.