Skip to content

Unify SIMD arithmetic under a shared transform_binary template #740

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tigercosmos wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Unify SIMD arithmetic under a shared transform_binary template #740

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 36 additions & 0 deletions cpp/modmesh/buffer/pymod/buffer_pymod.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,12 +28,40 @@

#include <modmesh/buffer/pymod/buffer_pymod.hpp> // Must be the first include.

#include <modmesh/simd/simd_support.hpp>

namespace modmesh
{

namespace python
{

namespace
{

char const * simd_feature_name()
{
using namespace modmesh::simd::detail;
switch (detect_simd())
{
case SIMD_NONE: return "NONE";
case SIMD_NEON: return "NEON";
case SIMD_SSE: return "SSE";
case SIMD_SSE2: return "SSE2";
case SIMD_SSE3: return "SSE3";
case SIMD_SSSE3: return "SSSE3";
case SIMD_SSE41: return "SSE41";
case SIMD_SSE42: return "SSE42";
case SIMD_AVX: return "AVX";
case SIMD_AVX2: return "AVX2";
case SIMD_AVX512: return "AVX512";
case SIMD_UNKNOWN: return "UNKNOWN";
}
return "UNKNOWN";
}

} // namespace

struct buffer_pymod_tag;

template <>
Expand All @@ -52,6 +80,14 @@ void initialize_buffer(pybind11::module & mod)
wrap_ConcreteBuffer(mod);
wrap_SimpleArray(mod);
wrap_SimpleArrayPlex(mod);

// Reports the runtime-detected SIMD feature so pytest can verify that
// NEON dispatch is active on aarch64. Without this guard, a regression
// that silently routes everything to the scalar path would still pass
// every correctness check. Kept under an underscore-prefixed name
// because detect_simd() only meaningfully reflects the dispatched
// backend on aarch64 today; on other targets it would mislead users.
mod.def("_simd_feature", &simd_feature_name);
Copy link
Copy Markdown
Collaborator Author

@tigercosmos tigercosmos Apr 27, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

For checking if simd is working.

Copy link
Copy Markdown
Member

@yungyuc yungyuc Apr 29, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

cpp/modmesh/toggle/ may be a more on-topic module for the SIMD check, but it's fine to have it here in buffer.

};

OneTimeInitializer<buffer_pymod_tag>::me()(mod, initialize_impl);
Expand Down
Loading
Loading