SIMD cannot be solved at the compiler level. The capabilities of silicon SIMD implementations are fundamentally so disjoint that code using SIMD requires contextual and platform-specific data structures and algorithms.
SIMD on different silicon is incompatible at layers of abstraction far above the codegen manipulation a compiler can do.
> SIMD cannot be solved at the compiler level.
ISPC doesn't a pretty good job of it: https://ispc.github.io/
That's why it needs a lot of work. Writing SIMD in c++ is like writing assembly.
You'll never get the full feature set of all SIMD implementations in a single generic abstraction but I'm not sure that's the only way a SIMD abstraction could provide value. There is a pretty consistent set of narrow SIMD that behaves close enough to consistently get better performance across generic targets with high level abstractions better than auto vectorized scalar code but worse than platform tuned SIMD.