9 comments

[ 2.6 ms ] story [ 10.8 ms ] thread
I'm reserve judgement on all of these benchmark stories until actual, real benchmarks are supported like Blender renders, Cinebench R20, or 3DMark.
All of which will have performance loss due to x86 emulation.
Cinebench R23 and Blender were ported to be native on Apple Silicon macs.
... which seems reasonable to factor in, because most of the software that I use will not be ported to ARM CPUs anytime soon.
Apple's new chip "shreds" a 2016-era GPU?

Wow.

Apple’s new integrated graphics chip shreds a discrete GPU.

The models announced last week were all the low end models that currently only have integrated Intel graphics. This is a huge upgrade for those systems. The expectation is that when Apple announces replacements for their higher end products, some of which use discrete GPUs, there will be a similar upgrade in performance.

Does anyone know how good the M1 is for training ML (since there's no CUDA support)?