Re:TinyML: Ultra-low power Machine Learning
by jononor on Thursday January 18, 2024 @04:12PM
(#39047820)
The latest extensions from ARM are codenamed Helium, and they are an extension on the previously mentioned NEON.
Both NEON and Helium are quite simple vector extensions, and yes it is also used for classic DSP stuff. I believe Helium also supports fp16, though for inference on MCUs I believe that int8 will continue to dominate. Here is book on Helium from ARM that seems informational
https://github.com/arm-university/Arm-Helium-Technology
There is another chip that is generally available, that has a CNN accelerator/co-processor - the MAX78000 https://www.embedded.com/hardware-conversion-of-convolutiona...
Re:TinyML: Ultra-low power Machine Learning
by a2code on Thursday January 18, 2024 @04:57PM
(#39048395)
Thanks again. I have to correct my previous reply. The ESP32-S3 has an extended instruction set detailed in the technical reference manual. These include vector operations (8, 16, or 32 bit).
I'm curious, why do you believe int8 will dominate?
On the other hand, esp-nn seems to be code for the xtensa instruction set. I briefly overviewed the instructions. They seem optimized for DSP rather than ML applications. Searching for SIMD returned no arithmetic instructions. Searching for parallel returned instructions for multiply and accumulate. Further, the FPU does not compute any kind of 16-bit floating point numbers.
>ARM has also defined a new set of extensions for NN acceleration Can you provide some more info about this?