Various problems on arm64

[omegacoleman]

I'm testing FBGEMM on a Macbook M1. The kernels are fine, but the build system and ISA detection fail. Currently

2. The env override is missing on arm64
3. The ISA selector function and the actual kernels are built with different macro definitions.
4. A few misalignments in the build script also create problems.
5. The SVE kernel currently produces wrong results

This issue is created to track those problems.