Landing: f0551dea5fba

Project / Subsystem

gcc / gcc/risc-v

Date

2026-09-18

Author

Bohan Lei

Commit

f0551dea5fba27ba06c6900391eccf0d0a5661ba

Source

github

Perf win

Yes

Breaking

No

All attributes

project
gcc
subsystem
gcc/risc-v
patch_id
—
commit_hash
f0551dea5fba27ba06c6900391eccf0d0a5661ba
source_type
github
headline
RISC-V: Optimize vector loop costs with dynamic LMUL
tldr
Improves RISC-V vector code generation by comparing costs for dynamic LMUL.
author
Bohan Lei
outcome
committed
performance_win
true
breaking_change
false
series_id
gcc:risc-v: compare costs under -mrvv-max-lmul=dynamic
series_parts
[]
tags
  • • risc-v
  • • optimization
  • • vector
  • • compiler
discussion_id_link
—
bugzilla_pr
—
date
2026-09-18T00:00:00.000Z

This commit enhances the RISC-V vector code generation by more accurately comparing the costs of different vector length multiplier (LMUL) modes when -mrvv-max-lmul=dynamic is used. It avoids premature rejection of vectorization and considers scenarios where different loop structures might incur varying spill costs, leading to better optimization choices for unknown iteration count loops.