Retrospectively Reverse-Engineering Apple's Neural Engine
eiln.github.io113 points by zdw 4 hours ago
113 points by zdw 4 hours ago
How does this relate to the more recent work on the M4 ANE found at https://maderix.github.io/articles/ ? Does the M4 and later ANE expose any additional capabilities, or is it just a higher-performance iteration of the same thing?
As an aside, the introduction to this article seems to conflate the ANE with the Neural Accelerators (NAX) found in the M5+ (and A-series equivalents) GPUs. These are very different things, and Apple is still working on the ANE - the M6 and A20 will apparently feature doubled ANE blocks.
This one's authored by a human, the other one is authored by Claude.
> Does the M4 and later ANE expose any additional capabilities, or is it just a higher-performance iteration of the same thing?
IIUC, M4 introduced a fast path for INT8 weights and activations (w8a8). M5 Ultra, M6 and A20 have two ANEs.
> As an aside, the introduction to this article seems to conflate the ANE with the Neural Accelerators (NAX)
Yeah, that part is true. NAX cores are matmult accelerators, closer to tensor cores in NVIDIA GPUs.
Ported a transformer to ANE and the whole job was pretending it was a CNN, 4D tensors with seq in the last axis and 1x1 convs instead of matmuls.
This isn't ai slop. It's fascinating and well written.
But I learned something really basic - i didn't know that the ANE (and the data pipeline around it) was designed for CNN rather than transformers. It's always been an open loop in my head, wondering why the ANE was less impactful than i understood it should be.
>i didn't know that the ANE (and the data pipeline around it) was designed for CNN rather than transformers.
Multiple stories have reported that ANE came from Apple's self-driving car project that got canceled. (Makes sense since CNN is used for vision-related machine learning and enables cars to analyze their surroundings.) They spent 10 years and ~10 billion on research & development on a product that never got released so Apple is probably happy they're able to salvage some of that ai technology and put it in iPhones and Macs.
A lot of neural engine, particularly in the embedded domain (ARM/RISC MCUs) have the same problem. Designing other models means on top of this means a lot of profiling to get convolution blocks right to get good speedups. (We optimized this in the past e.g. using Neural Architecture Search on super networks)
> But I learned something really basic
Same for me!
Also, just imagine being the group at Apple responsible for designing this section of the chip, starting probably almost a decade back – under the constant uncertainty of not knowing what direction ML workloads would develop in…
ML research was a rather known quantity, or the separate "Neural Engine" CPU explicitly aimed at existing ML pipelines wouldn't exist.
However, very few used it for anything, even within Apple. I feel like it was a huge wasted opportunity.
I'm all for compassion, but engineers knew the NE was empty when it sat idle for 10 years on our computers.
- when you're given no usecase for your engineering piece, apart from "detour characters in pictures". It's an exageration but AI's contributions in iOS aren't visible; Meanwhile Google has features that people actually notice like removing tourists from your holidays photos — worse: it's mostly a simple collage feature working on the main CPU, and it has the same social effect as green bubbles in iMessage ("ah. Tourists on your photos. iPhone user?")
- and you tout it as "16 Neural Engine cores" during the sales, with no associated software, no listed material feature, just hand-waving,
- Siri maxxes out at "There is no contact named 'What's the weather today' in your agenda",
Then can't really claim that Apple engineers' problem was really the bad luck that ML wasn't the determining part of the future. It's more like misreading the room for 5 to 10 years straight.
Apple engineering's excellence on vertical integration and supply chain control gave them absolute power over our world (with merit), it just failed at that particular project. Which occupies 40% of our CPUs.
The ANE hasn't been sitting empty for 10 years. All those Photos features like face recognition and auto classification run on ANE.
> what workloads it was designed for and accels at.
excels!
Could've been a pun as a neural processor is an accelerator, so it 'accels' at machine learning tasks!
[flagged]
[dead]