DLTcollab/sse2neon

Health v2 · maintenance only

Adoption not part of the score

1529 stars · 235 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A single-header C/C++ library that translates Intel SSE (MMX through SSE4.2 and AES) intrinsics to Arm/Aarch64 NEON intrinsics. It enables rapid porting of x86 SIMD code to Arm platforms by providing drop-in replacement headers with preserved semantics.

Use cases

• port x86 SIMD code to Apple Silicon Macs
• compile SSE-based C++ libraries on ARM64 servers
• migrate Intel intrinsic code to Arm NEON without rewriting
• build x86-originating projects on aarch64 Linux
• run SSE-dependent code on Windows ARM64 via ARM64EC
• port MMX and SSE4.2 intrinsics to ARMv8

When to choose

• you need to port existing x86 SIMD code to Arm quickly with minimal source changes
• you target Apple Silicon, ARM servers, or Windows on ARM
• you want a header-only drop-in replacement for Intel intrinsic headers

When to avoid

• you are writing new Arm-native code and can use NEON intrinsics directly
• you need bit-exact IEEE-754 floating-point behavior without precision flags
• you target big-endian ARM or AVX/AVX-512 extensions

Facets

library · maturity active

compiler developer-tools graphics math developer-tools cross-platform performance hardware cpp cross-platform windows simd neon sse arm64 header-only porting apple-silicon intrinsics macos linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="DLTcollab/sse2neon")