zlacker

[parent] [thread] 2 comments
1. Y_Y+(OP)[view] [source] 2025-12-27 15:39:30
The specific NPU doesn't seem to be mentioned in TFA, but my guess is that the blessed way to deal with it is the Neon SDK: https://www.arm.com/technologies/neon

I've not found Neon to be fun or easy to use, and I frequently see devices ignoring the NPU and inferring on CPU because it's easier. Maybe you get lucky and someone has made a backend for something specific you want, but it's not common.

replies(1): >>snops+i31
2. snops+i31[view] [source] 2025-12-27 23:34:33
>>Y_Y+(OP)
TFA does directly mention the NPU "Arm-China Zhouyi: 30 TOPS (Dedicated)"

"you cannot simply use standard versions of PyTorch or TensorFlow out of the box. You must use the NeuralONE AI SDK."

Neon is a SIMD instruction set for the CPU, not a separate accelerator. It doesn't need an SDK to use, it's supported by compiler intrinsics and assembly language in any modern ARM compiler.

replies(1): >>Y_Y+Wb1
◧◩
3. Y_Y+Wb1[view] [source] [discussion] 2025-12-28 00:44:52
>>snops+i31
Quite right, I mixed up Neon with NN:

https://www.arm.com/products/silicon-ip-cpu/ethos/arm-nn

[go to top]