Skip to content

Enable vectorization of std::rotate on ARM64 - #5845

Merged
Stephan T. Lavavej (StephanTLavavej) merged 2 commits into
microsoft:mainfrom
hazzlim:rotate-neon-pr
Nov 12, 2025
Merged

Enable vectorization of std::rotate on ARM64#5845
Stephan T. Lavavej (StephanTLavavej) merged 2 commits into
microsoft:mainfrom
hazzlim:rotate-neon-pr

Conversation

@hazzlim

Copy link
Copy Markdown
Contributor

Add an implementation of _Swap_3_ranges using Neon intrinsics and enable vectorization of std::rotate on ARM64 targets.

Add an implementation of _Swap_3_ranges using Neon intrinsics and enable
vectorization of std::rotate on ARM64 targets.
@StephanTLavavej Stephan T. Lavavej (StephanTLavavej) added performance Must go faster ARM64 Related to the ARM64 architecture labels Nov 11, 2025
@StephanTLavavej

Copy link
Copy Markdown
Member

Thanks! BTW, if you're having issues with code formatting, if you use VSCode and install Microsoft's C/C++ Extension, you can add "C_Cpp.clang_format_path": "C:/Program Files/Microsoft Visual Studio/18/Insiders/VC/Tools/Llvm/x64/bin/clang-format.exe", to your settings. Combined with how our .vscode/settings.json enables format-on-save for C++ files, that'll keep your code always-formatted with the exact version of clang-format that we use in the repo.

@StephanTLavavej Stephan T. Lavavej (StephanTLavavej) moved this from Initial Review to Ready To Merge in STL Code Reviews Nov 11, 2025
@StephanTLavavej Stephan T. Lavavej (StephanTLavavej) moved this from Ready To Merge to Merging in STL Code Reviews Nov 11, 2025
@StephanTLavavej

Copy link
Copy Markdown
Member

I'm mirroring this to the MSVC-internal repo - please notify me if any further changes are pushed.

@StephanTLavavej
Stephan T. Lavavej (StephanTLavavej) merged commit ab6dec6 into microsoft:main Nov 12, 2025
41 checks passed
@github-project-automation github-project-automation Bot moved this from Merging to Done in STL Code Reviews Nov 12, 2025
@StephanTLavavej

Copy link
Copy Markdown
Member

Thanks - when things spin, science happens! 🔃 🔄 🧑‍🔬

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ARM64 Related to the ARM64 architecture performance Must go faster

2 participants