simd-everywhere/simde

Health v2 · maintenance only

Flags: prerelease_only

Adoption not part of the score

3092 stars · 320 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

SIMDe is a header-only C/C++ library providing portable implementations of SIMD intrinsics (SSE, AVX, NEON, AltiVec, etc.) on hardware that doesn't natively support them. It enables porting SIMD-optimized code across architectures with no performance penalty when native support exists.

Use cases

• port SSE/AVX code to ARM without rewriting
• run NEON code on x86 for development without an emulator
• get a cross-architecture port working quickly before optimizing
• write code against ISA extensions not available on local hardware
• keep SIMD code portable across x86, ARM, and PowerPC

When to choose

• you need to port existing SIMD intrinsics code to another architecture
• you want a gradual migration path rather than a full rewrite
• you need to develop/test SIMD code for hardware you don't have access to

When to avoid

• you only target a single architecture and can use native intrinsics directly
• you want a higher-level abstraction like a portable vector library rather than intrinsic-level compatibility
• maximum performance on unsupported hardware is critical, since emulated paths are slower

Facets

library · maturity active

graphics simulation developer-tools cross-platform developer-tools performance cross-platform cpp c windows simd intrinsics header-only sse avx neon altivec portability vectorization algorithms linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="simd-everywhere/simde")