I just don’t understand - Apple decided to implement a more capable SIMD instruction set and just … didn’t document it? SIMD is hugely important in anything remotely HPC related. My first gen apple silicon laptop still favorably competes against Intel’s current best, years later. Why would they hide such an advantage?
My guess is that it's not complete or stable or qualified enough for them to publish it as a supported feature. Maybe the power draw is too high and it triggers thermal throttling too quickly, similar to early Intel AVX-512? Maybe they are still sorting out how to have each process choose SVE vs NEON mode, so libraries using the other one don't cause a fault? (Note that this seems limited to M4 and newer CPUs.)
I agree this is an important feature. I have very often wished that my Mac had wider vectors.
Why can’t I scroll on mobile Safari on this site? What in the world are we doing with websites these days where a user can’t even scroll?
I just don’t understand - Apple decided to implement a more capable SIMD instruction set and just … didn’t document it? SIMD is hugely important in anything remotely HPC related. My first gen apple silicon laptop still favorably competes against Intel’s current best, years later. Why would they hide such an advantage?
My guess is that it's not complete or stable or qualified enough for them to publish it as a supported feature. Maybe the power draw is too high and it triggers thermal throttling too quickly, similar to early Intel AVX-512? Maybe they are still sorting out how to have each process choose SVE vs NEON mode, so libraries using the other one don't cause a fault? (Note that this seems limited to M4 and newer CPUs.)
I agree this is an important feature. I have very often wished that my Mac had wider vectors.
Besides Apple who is doing hpc on Apple silicon
can people publish blog posts (and other things) literally anywhere else? especially now with nitter/xcancel/etc getting taken down