Cycles: refactor intrinsic functions implementation

* Add processor independent fallbacks
* Use uint32_t and uint64_t types
* Remove unused functions
* Better comments and less indentation

Ref D8237, T78710

Cycles: add support for Arm Neon instructions using sse2neon

Based on patch contributed by Apple and Stefan Werner.

Ref D8237, T78710

macOS: add Embree, OpenImageDenoise and sse2neon libraries for ARM

This required using a fork of Embree, newer LLVM version, unreleased ISPC
version and sse2neon directly from Git. Hopefully over time all the required
changes end up in official releases. For now we deviate from other platforms.

Patch based on contributions by Apple and Stefan Werner.

Ref D9527, D8237, T78710

BLI: add BLI_simd.h header to wrap SSE includes

In preparation of adding Neon support.

Ref T78710

macOS: use sse2neon to emulate SSE instructions with Arm Neon

* WITH_CPU_SSE was renamed to WITH_CPU_SIMD, and now covers both SSE and Neon.
* For macOS sse2neon.h is included as part of the precompiled libraries.
* Adding Linux support should be possible too, but the best way to handle this
library without official releases or availability in distributions is to be
decided still.

Ref T78710

macOS: fix Cycles not detecting 64 bit and failing to build with Embree

Contributed by Apple

Ref D9527, T78710