More cores are great for running more processes, but how can you make individual operations within a process faster? SIMD is one solution.
Apple silicon
Benchmarking 32-bit Float vector dot-product calculations using Swift, NEON assembly, and Apple’s SIMD libraries, on Intel and M1 Macs.
Details options available for rounding floating point numbers, and all the scalar floating point operations. There’s another cheat sheet summary too.
When should we expect macOS 11.6? When will Monterey be released, and when will the next Apple Silicon models be announced? Here are some wild guesses.
Floating point numbers are very different from integers, but are loaded and stored much the same. Conversion between registers, including to and from integers, is complex.
What do you need to do before selling or giving away your Mac to someone else? Here’s a summary, covering all from Intel to M1 models.
M1 Macs have an elaborate system of keys and certificates which allow the installation of second operating systems, as well as the primary OS, based on Ownership.
Where code can make simple selections according to a conditional test, it may be possible to eliminate branching and ensure rapid execution.
The primary admin account on an M1 Mac is its Owner, responsible for authorising the installation and use of second operating systems. Here’s what can go wrong with Ownership.
An overview of bit operations, including MOVK for 16-bit immediate values, bit shift operations, bitwise AND, OR, XOR, and more, plus a cheat sheet.
The Eclectic Light Company 